Token | his |
Token ID | 465 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ilon | +0.076 |
earch | +0.075 |
Daddy | +0.075 |
Strait | +0.071 |
WN | +0.067 |
Neg logit contributions | |
gradation | -0.091 |
================================= | -0.086 |
Templ | -0.082 |
�� | -0.079 |
clot | -0.077 |
Token | job |
Token ID | 1693 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ilon | +0.199 |
earch | +0.197 |
Daddy | +0.196 |
Strait | +0.187 |
WN | +0.178 |
Neg logit contributions | |
gradation | -0.202 |
================================= | -0.190 |
Templ | -0.181 |
�� | -0.173 |
clot | -0.168 |
Token | as |
Token ID | 355 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
ilon | +0.248 |
earch | +0.245 |
Daddy | +0.244 |
Strait | +0.231 |
WN | +0.220 |
Neg logit contributions | |
gradation | -0.296 |
================================= | -0.281 |
Templ | -0.267 |
�� | -0.256 |
clot | -0.250 |
Token | chairman |
Token ID | 8900 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
gradation | +0.044 |
================================= | +0.041 |
Templ | +0.039 |
�� | +0.038 |
clot | +0.037 |
Neg logit contributions | |
ilon | -0.037 |
earch | -0.037 |
Daddy | -0.036 |
Strait | -0.035 |
WN | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
gradation | +0.208 |
================================= | +0.197 |
Templ | +0.187 |
�� | +0.180 |
clot | +0.175 |
Neg logit contributions | |
ilon | -0.179 |
earch | -0.177 |
Daddy | -0.176 |
Strait | -0.167 |
WN | -0.158 |
Token | PD |
Token ID | 14340 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
gradation | +0.109 |
================================= | +0.104 |
Templ | +0.099 |
�� | +0.095 |
clot | +0.092 |
Neg logit contributions | |
ilon | -0.086 |
earch | -0.085 |
Daddy | -0.085 |
Strait | -0.080 |
WN | -0.076 |
Token | V |
Token ID | 53 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
gradation | +1.621 |
================================= | +1.501 |
Templ | +1.415 |
�� | +1.397 |
clot | +1.308 |
Neg logit contributions | |
ilon | -1.988 |
earch | -1.915 |
Daddy | -1.912 |
Strait | -1.871 |
WN | -1.819 |
Token | SA |
Token ID | 4090 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
gradation | +1.565 |
================================= | +1.472 |
Templ | +1.412 |
�� | +1.394 |
clot | +1.337 |
Neg logit contributions | |
ilon | -1.042 |
earch | -1.020 |
Daddy | -1.011 |
Strait | -0.965 |
WN | -0.920 |
Token | in |
Token ID | 287 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
gradation | +0.355 |
================================= | +0.337 |
Templ | +0.320 |
�� | +0.310 |
clot | +0.300 |
Neg logit contributions | |
ilon | -0.285 |
earch | -0.281 |
Daddy | -0.279 |
Strait | -0.265 |
WN | -0.251 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ilon | +0.006 |
earch | +0.006 |
Daddy | +0.006 |
Strait | +0.006 |
WN | +0.006 |
Neg logit contributions | |
gradation | -0.007 |
================================= | -0.007 |
Templ | -0.006 |
�� | -0.006 |
clot | -0.006 |
Token | resh |
Token ID | 27179 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
gradation | +0.167 |
================================= | +0.159 |
Templ | +0.151 |
�� | +0.146 |
clot | +0.141 |
Neg logit contributions | |
ilon | -0.133 |
earch | -0.132 |
Daddy | -0.130 |
Strait | -0.124 |
WN | -0.117 |
Token | rich |
Token ID | 7527 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
gradation | +0.046 |
================================= | +0.044 |
Templ | +0.041 |
�� | +0.040 |
clot | +0.038 |
Neg logit contributions | |
ilon | -0.043 |
earch | -0.043 |
Daddy | -0.042 |
Strait | -0.040 |
WN | -0.038 |
Token | Ha |
Token ID | 9398 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
gradation | +0.257 |
================================= | +0.240 |
Templ | +0.225 |
�� | +0.218 |
clot | +0.208 |
Neg logit contributions | |
ilon | -0.300 |
earch | -0.297 |
Daddy | -0.295 |
Strait | -0.284 |
WN | -0.270 |
Token | uss |
Token ID | 1046 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
gradation | +0.582 |
================================= | +0.544 |
Templ | +0.511 |
�� | +0.492 |
clot | +0.461 |
Neg logit contributions | |
ilon | -0.817 |
earch | -0.808 |
Daddy | -0.806 |
Strait | -0.774 |
WN | -0.739 |
Token | ler |
Token ID | 1754 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ilon | +0.274 |
earch | +0.271 |
Daddy | +0.268 |
Strait | +0.254 |
WN | +0.240 |
Neg logit contributions | |
gradation | -0.384 |
================================= | -0.367 |
Templ | -0.350 |
�� | -0.337 |
clot | -0.329 |
Token | ( |
Token ID | 357 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
gradation | +0.408 |
================================= | +0.385 |
Templ | +0.366 |
�� | +0.357 |
clot | +0.342 |
Neg logit contributions | |
ilon | -0.353 |
earch | -0.348 |
Daddy | -0.346 |
Strait | -0.330 |
WN | -0.312 |
Token | Gar |
Token ID | 27676 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
gradation | +0.466 |
================================= | +0.443 |
Templ | +0.423 |
�� | +0.410 |
clot | +0.398 |
Neg logit contributions | |
ilon | -0.344 |
Daddy | -0.339 |
earch | -0.339 |
Strait | -0.319 |
WN | -0.304 |
Token | min |
Token ID | 1084 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gradation | +2.082 |
================================= | +1.969 |
Templ | +1.910 |
�� | +1.895 |
clot | +1.790 |
Neg logit contributions | |
ilon | -1.444 |
Daddy | -1.393 |
earch | -1.390 |
Strait | -1.315 |
Hus | -1.247 |
Token | - |
Token ID | 12 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
gradation | +0.799 |
================================= | +0.758 |
Templ | +0.714 |
�� | +0.698 |
clot | +0.673 |
Neg logit contributions | |
ilon | -0.622 |
earch | -0.614 |
Daddy | -0.606 |
Strait | -0.582 |
WN | -0.545 |
Token | C |
Token ID | 34 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
gradation | +0.531 |
================================= | +0.498 |
Templ | +0.463 |
�� | +0.443 |
clot | +0.423 |
Neg logit contributions | |
ilon | -0.750 |
Daddy | -0.741 |
earch | -0.740 |
Strait | -0.707 |
WN | -0.686 |
Token | er |
Token ID | 263 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
gradation | +0.595 |
================================= | +0.563 |
Templ | +0.530 |
�� | +0.513 |
clot | +0.491 |
Neg logit contributions | |
ilon | -0.591 |
earch | -0.579 |
Daddy | -0.578 |
Strait | -0.546 |
WN | -0.525 |
Token | vel |
Token ID | 626 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
gradation | +0.672 |
================================= | +0.646 |
Templ | +0.619 |
�� | +0.605 |
clot | +0.589 |
Neg logit contributions | |
ilon | -0.311 |
earch | -0.302 |
Daddy | -0.300 |
Strait | -0.278 |
WN | -0.260 |
Token | o |
Token ID | 78 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
gradation | +1.506 |
================================= | +1.433 |
Templ | +1.366 |
�� | +1.351 |
clot | +1.298 |
Neg logit contributions | |
ilon | -0.980 |
Daddy | -0.948 |
earch | -0.918 |
Strait | -0.904 |
Hus | -0.846 |
Token | Gu |
Token ID | 1962 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
ilon | +0.198 |
earch | +0.196 |
Daddy | +0.194 |
Strait | +0.185 |
WN | +0.176 |
Neg logit contributions | |
gradation | -0.215 |
================================= | -0.204 |
Templ | -0.194 |
�� | -0.185 |
clot | -0.180 |
Token | arn |
Token ID | 1501 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ilon | +0.251 |
earch | +0.247 |
Daddy | +0.245 |
Strait | +0.230 |
WN | +0.214 |
Neg logit contributions | |
gradation | -0.471 |
================================= | -0.451 |
Templ | -0.432 |
�� | -0.417 |
jar | -0.410 |
Token | ieri |
Token ID | 29864 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
gradation | +0.287 |
================================= | +0.265 |
Templ | +0.245 |
�� | +0.234 |
clot | +0.221 |
Neg logit contributions | |
ilon | -0.481 |
earch | -0.475 |
Daddy | -0.472 |
Strait | -0.456 |
WN | -0.438 |
Token | ( |
Token ID | 357 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ilon | +0.072 |
earch | +0.071 |
Daddy | +0.070 |
Strait | +0.067 |
WN | +0.064 |
Neg logit contributions | |
gradation | -0.080 |
================================= | -0.076 |
Templ | -0.072 |
�� | -0.069 |
clot | -0.067 |
Token | Ast |
Token ID | 33751 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
gradation | +0.260 |
================================= | +0.246 |
Templ | +0.234 |
�� | +0.227 |
clot | +0.220 |
Neg logit contributions | |
ilon | -0.210 |
earch | -0.207 |
Daddy | -0.206 |
Strait | -0.195 |
WN | -0.186 |
Token | ana |
Token ID | 2271 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
gradation | +1.620 |
================================= | +1.511 |
Templ | +1.412 |
�� | +1.406 |
clot | +1.324 |
Neg logit contributions | |
ilon | -1.852 |
Daddy | -1.787 |
earch | -1.771 |
Strait | -1.708 |
WN | -1.642 |
Token | Pro |
Token ID | 1041 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
gradation | +0.849 |
================================= | +0.805 |
Templ | +0.756 |
�� | +0.741 |
clot | +0.710 |
Neg logit contributions | |
ilon | -0.769 |
earch | -0.754 |
Daddy | -0.750 |
Strait | -0.723 |
WN | -0.683 |
Token | Team |
Token ID | 4816 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
gradation | +1.268 |
================================= | +1.214 |
Templ | +1.133 |
�� | +1.125 |
clot | +1.080 |
Neg logit contributions | |
ilon | -1.018 |
Daddy | -0.991 |
earch | -0.979 |
Strait | -0.938 |
Hus | -0.886 |
Token | ) |
Token ID | 8 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
gradation | +0.239 |
================================= | +0.226 |
Templ | +0.214 |
�� | +0.207 |
clot | +0.199 |
Neg logit contributions | |
ilon | -0.225 |
earch | -0.222 |
Daddy | -0.221 |
Strait | -0.211 |
WN | -0.200 |
Token | s |
Token ID | 264 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
gradation | +0.124 |
================================= | +0.118 |
Templ | +0.113 |
�� | +0.109 |
clot | +0.106 |
Neg logit contributions | |
ilon | -0.086 |
earch | -0.085 |
Daddy | -0.084 |
Strait | -0.080 |
WN | -0.075 |
Token | Jonathan |
Token ID | 11232 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ilon | +0.039 |
earch | +0.039 |
Daddy | +0.038 |
Strait | +0.036 |
WN | +0.035 |
Neg logit contributions | |
gradation | -0.042 |
================================= | -0.040 |
Templ | -0.038 |
�� | -0.037 |
clot | -0.036 |
Token | Cant |
Token ID | 16821 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ilon | +0.148 |
earch | +0.147 |
Daddy | +0.145 |
Strait | +0.139 |
WN | +0.134 |
Neg logit contributions | |
gradation | -0.125 |
================================= | -0.118 |
Templ | -0.111 |
�� | -0.106 |
clot | -0.102 |
Token | well |
Token ID | 4053 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
gradation | +0.245 |
================================= | +0.232 |
Templ | +0.220 |
�� | +0.212 |
clot | +0.205 |
Neg logit contributions | |
ilon | -0.224 |
earch | -0.221 |
Daddy | -0.219 |
Strait | -0.209 |
WN | -0.198 |
Token | ( |
Token ID | 357 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
gradation | +0.065 |
================================= | +0.062 |
Templ | +0.059 |
�� | +0.057 |
clot | +0.055 |
Neg logit contributions | |
ilon | -0.058 |
earch | -0.057 |
Daddy | -0.057 |
Strait | -0.054 |
WN | -0.051 |
Token | Team |
Token ID | 15592 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
gradation | +0.339 |
================================= | +0.321 |
Templ | +0.305 |
�� | +0.295 |
clot | +0.286 |
Neg logit contributions | |
ilon | -0.282 |
earch | -0.279 |
Daddy | -0.278 |
Strait | -0.263 |
WN | -0.251 |
Token | Sax |
Token ID | 29242 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
gradation | +0.600 |
================================= | +0.560 |
Templ | +0.528 |
�� | +0.519 |
clot | +0.492 |
Neg logit contributions | |
ilon | -0.628 |
Daddy | -0.620 |
earch | -0.618 |
Strait | -0.595 |
WN | -0.566 |
Token | o |
Token ID | 78 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
gradation | +2.123 |
================================= | +2.013 |
Templ | +1.886 |
�� | +1.877 |
jar | +1.820 |
Neg logit contributions | |
ilon | -1.328 |
Daddy | -1.306 |
earch | -1.280 |
Strait | -1.233 |
Hus | -1.145 |
Token | Bank |
Token ID | 5018 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
gradation | +1.307 |
================================= | +1.217 |
�� | +1.136 |
Templ | +1.125 |
jar | +1.068 |
Neg logit contributions | |
ilon | -1.363 |
Daddy | -1.356 |
earch | -1.351 |
Strait | -1.302 |
Hus | -1.240 |
Token | ) |
Token ID | 8 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
gradation | +0.850 |
================================= | +0.804 |
Templ | +0.755 |
�� | +0.742 |
clot | +0.709 |
Neg logit contributions | |
ilon | -0.780 |
earch | -0.770 |
Daddy | -0.763 |
Strait | -0.733 |
WN | -0.693 |
Token | s |
Token ID | 264 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
gradation | +0.314 |
================================= | +0.299 |
Templ | +0.286 |
�� | +0.277 |
clot | +0.269 |
Neg logit contributions | |
ilon | -0.214 |
earch | -0.212 |
Daddy | -0.209 |
Strait | -0.199 |
WN | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ilon | +0.050 |
earch | +0.050 |
Daddy | +0.049 |
Strait | +0.047 |
WN | +0.044 |
Neg logit contributions | |
gradation | -0.057 |
================================= | -0.054 |
Templ | -0.051 |
�� | -0.049 |
clot | -0.048 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
gradation | +1.375 |
================================= | +1.309 |
Templ | +1.233 |
�� | +1.183 |
clot | +1.150 |
Neg logit contributions | |
earch | -1.107 |
ilon | -1.101 |
Daddy | -1.095 |
Strait | -1.051 |
invasive | -0.988 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
gradation | +1.107 |
================================= | +1.055 |
Templ | +1.004 |
�� | +0.979 |
clot | +0.931 |
Neg logit contributions | |
ilon | -0.826 |
earch | -0.821 |
Daddy | -0.810 |
Strait | -0.774 |
WN | -0.737 |
Token | : |
Token ID | 25 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
gradation | +1.654 |
================================= | +1.522 |
Templ | +1.433 |
�� | +1.413 |
jar | +1.341 |
Neg logit contributions | |
ilon | -1.433 |
Daddy | -1.400 |
earch | -1.393 |
Strait | -1.337 |
Hus | -1.288 |
Token | report |
Token ID | 989 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ilon | +0.228 |
earch | +0.225 |
Daddy | +0.223 |
Strait | +0.213 |
ktop | +0.202 |
Neg logit contributions | |
gradation | -0.259 |
================================= | -0.246 |
Templ | -0.234 |
�� | -0.225 |
clot | -0.218 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
gradation | +0.446 |
================================= | +0.421 |
Templ | +0.401 |
�� | +0.388 |
clot | +0.376 |
Neg logit contributions | |
ilon | -0.367 |
earch | -0.359 |
Daddy | -0.359 |
Strait | -0.341 |
WN | -0.324 |
Token | airline |
Token ID | 18091 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ilon | +0.009 |
earch | +0.009 |
Daddy | +0.009 |
Strait | +0.009 |
WN | +0.008 |
Neg logit contributions | |
gradation | -0.011 |
================================= | -0.010 |
Templ | -0.010 |
�� | -0.009 |
clot | -0.009 |
Token | takes |
Token ID | 2753 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
gradation | +1.683 |
================================= | +1.589 |
Templ | +1.502 |
�� | +1.470 |
clot | +1.408 |
Neg logit contributions | |
ilon | -1.494 |
earch | -1.480 |
Daddy | -1.459 |
Strait | -1.408 |
WN | -1.332 |
Token | steps |
Token ID | 4831 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
gradation | +0.235 |
================================= | +0.219 |
Templ | +0.204 |
�� | +0.194 |
jar | +0.185 |
Neg logit contributions | |
ilon | -0.332 |
earch | -0.328 |
Daddy | -0.326 |
Strait | -0.315 |
WN | -0.302 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
gradation | +0.254 |
================================= | +0.241 |
Templ | +0.230 |
�� | +0.222 |
clot | +0.214 |
Neg logit contributions | |
ilon | -0.197 |
earch | -0.194 |
Daddy | -0.193 |
Strait | -0.183 |
WN | -0.173 |
Token | open |
Token ID | 1280 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
gradation | +0.989 |
================================= | +0.932 |
Templ | +0.890 |
�� | +0.873 |
jar | +0.831 |
Neg logit contributions | |
ilon | -0.686 |
earch | -0.666 |
Daddy | -0.661 |
Strait | -0.638 |
WN | -0.595 |
Token | flights |
Token ID | 13956 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
gradation | +0.166 |
================================= | +0.157 |
Templ | +0.149 |
�� | +0.143 |
clot | +0.138 |
Neg logit contributions | |
ilon | -0.162 |
earch | -0.160 |
Daddy | -0.159 |
Strait | -0.152 |
WN | -0.144 |
Token | Gar |
Token ID | 27676 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
gradation | +0.466 |
================================= | +0.443 |
Templ | +0.423 |
�� | +0.410 |
clot | +0.398 |
Neg logit contributions | |
ilon | -0.344 |
Daddy | -0.339 |
earch | -0.339 |
Strait | -0.319 |
WN | -0.304 |
Token | min |
Token ID | 1084 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gradation | +2.082 |
================================= | +1.969 |
Templ | +1.910 |
�� | +1.895 |
clot | +1.790 |
Neg logit contributions | |
ilon | -1.444 |
Daddy | -1.393 |
earch | -1.390 |
Strait | -1.315 |
Hus | -1.247 |
Token | - |
Token ID | 12 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
gradation | +0.799 |
================================= | +0.758 |
Templ | +0.714 |
�� | +0.698 |
clot | +0.673 |
Neg logit contributions | |
ilon | -0.622 |
earch | -0.614 |
Daddy | -0.606 |
Strait | -0.582 |
WN | -0.545 |
Token | C |
Token ID | 34 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
gradation | +0.531 |
================================= | +0.498 |
Templ | +0.463 |
�� | +0.443 |
clot | +0.423 |
Neg logit contributions | |
ilon | -0.750 |
Daddy | -0.741 |
earch | -0.740 |
Strait | -0.707 |
WN | -0.686 |
Token | er |
Token ID | 263 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
gradation | +0.595 |
================================= | +0.563 |
Templ | +0.530 |
�� | +0.513 |
clot | +0.491 |
Neg logit contributions | |
ilon | -0.591 |
earch | -0.579 |
Daddy | -0.578 |
Strait | -0.546 |
WN | -0.525 |
Token | vel |
Token ID | 626 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
gradation | +0.672 |
================================= | +0.646 |
Templ | +0.619 |
�� | +0.605 |
clot | +0.589 |
Neg logit contributions | |
ilon | -0.311 |
earch | -0.302 |
Daddy | -0.300 |
Strait | -0.278 |
WN | -0.260 |
Token | o |
Token ID | 78 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
gradation | +1.906 |
================================= | +1.811 |
Templ | +1.721 |
�� | +1.693 |
clot | +1.617 |
Neg logit contributions | |
ilon | -1.240 |
Daddy | -1.232 |
earch | -1.216 |
Strait | -1.157 |
Hus | -1.088 |
Token | ) |
Token ID | 8 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
gradation | +0.613 |
================================= | +0.580 |
Templ | +0.546 |
�� | +0.533 |
clot | +0.510 |
Neg logit contributions | |
ilon | -0.560 |
earch | -0.554 |
Daddy | -0.548 |
Strait | -0.524 |
WN | -0.497 |
Token | s |
Token ID | 264 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
gradation | +0.217 |
================================= | +0.206 |
Templ | +0.197 |
�� | +0.191 |
clot | +0.185 |
Neg logit contributions | |
ilon | -0.151 |
earch | -0.149 |
Daddy | -0.148 |
Strait | -0.140 |
WN | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ilon | +0.064 |
earch | +0.064 |
Daddy | +0.063 |
Strait | +0.060 |
WN | +0.057 |
Neg logit contributions | |
gradation | -0.073 |
================================= | -0.069 |
Templ | -0.065 |
�� | -0.063 |
clot | -0.061 |
Token | t |
Token ID | 83 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
ilon | +0.095 |
earch | +0.093 |
Daddy | +0.092 |
Strait | +0.088 |
WN | +0.083 |
Neg logit contributions | |
gradation | -0.124 |
================================= | -0.118 |
Templ | -0.112 |
�� | -0.108 |
clot | -0.105 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
gradation | +1.552 |
================================= | +1.474 |
Templ | +1.390 |
�� | +1.335 |
jar | +1.299 |
Neg logit contributions | |
earch | -1.223 |
ilon | -1.212 |
Daddy | -1.210 |
Strait | -1.160 |
invasive | -1.095 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
gradation | +1.031 |
================================= | +0.982 |
Templ | +0.937 |
�� | +0.912 |
clot | +0.873 |
Neg logit contributions | |
ilon | -0.756 |
earch | -0.749 |
Daddy | -0.739 |
Strait | -0.708 |
WN | -0.669 |
Token | : |
Token ID | 25 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
gradation | +1.546 |
================================= | +1.417 |
Templ | +1.332 |
�� | +1.309 |
clot | +1.246 |
Neg logit contributions | |
ilon | -1.422 |
Daddy | -1.387 |
earch | -1.384 |
Strait | -1.328 |
WN | -1.280 |
Token | report |
Token ID | 989 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ilon | +0.435 |
earch | +0.430 |
Daddy | +0.426 |
Strait | +0.409 |
ktop | +0.388 |
Neg logit contributions | |
gradation | -0.484 |
================================= | -0.461 |
Templ | -0.437 |
�� | -0.421 |
clot | -0.407 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
gradation | +0.340 |
================================= | +0.322 |
Templ | +0.307 |
�� | +0.298 |
clot | +0.288 |
Neg logit contributions | |
ilon | -0.257 |
earch | -0.252 |
Daddy | -0.251 |
Strait | -0.238 |
WN | -0.225 |
Token | airline |
Token ID | 18091 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ilon | +0.190 |
earch | +0.187 |
Daddy | +0.185 |
Strait | +0.176 |
ktop | +0.168 |
Neg logit contributions | |
gradation | -0.223 |
================================= | -0.212 |
Templ | -0.201 |
�� | -0.194 |
clot | -0.189 |
Token | takes |
Token ID | 2753 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
gradation | +1.734 |
================================= | +1.642 |
Templ | +1.560 |
�� | +1.532 |
clot | +1.467 |
Neg logit contributions | |
ilon | -1.327 |
earch | -1.309 |
Daddy | -1.287 |
Strait | -1.236 |
WN | -1.168 |
Token | steps |
Token ID | 4831 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
gradation | +0.208 |
================================= | +0.194 |
Templ | +0.181 |
�� | +0.173 |
jar | +0.164 |
Neg logit contributions | |
ilon | -0.288 |
earch | -0.285 |
Daddy | -0.283 |
Strait | -0.273 |
WN | -0.262 |
Token | to |
Token ID | 284 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
gradation | +0.190 |
================================= | +0.181 |
Templ | +0.172 |
�� | +0.166 |
clot | +0.161 |
Neg logit contributions | |
ilon | -0.149 |
earch | -0.147 |
Daddy | -0.145 |
Strait | -0.138 |
WN | -0.130 |
Token | open |
Token ID | 1280 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
gradation | +1.377 |
================================= | +1.296 |
Templ | +1.240 |
�� | +1.220 |
jar | +1.162 |
Neg logit contributions | |
ilon | -0.893 |
earch | -0.864 |
Daddy | -0.853 |
Strait | -0.830 |
WN | -0.772 |
Token | flights |
Token ID | 13956 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
gradation | +0.462 |
================================= | +0.436 |
Templ | +0.414 |
�� | +0.400 |
clot | +0.385 |
Neg logit contributions | |
ilon | -0.417 |
earch | -0.413 |
Daddy | -0.409 |
Strait | -0.392 |
WN | -0.372 |
Token | ally |
Token ID | 12525 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ilon | +0.311 |
earch | +0.308 |
Daddy | +0.306 |
Strait | +0.290 |
ktop | +0.277 |
Neg logit contributions | |
gradation | -0.334 |
================================= | -0.316 |
Templ | -0.302 |
�� | -0.288 |
clot | -0.282 |
Token | in |
Token ID | 287 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
gradation | +0.101 |
================================= | +0.097 |
Templ | +0.092 |
�� | +0.089 |
clot | +0.086 |
Neg logit contributions | |
ilon | -0.073 |
earch | -0.072 |
Daddy | -0.072 |
Strait | -0.068 |
WN | -0.064 |
Token | charge |
Token ID | 3877 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
gradation | +0.385 |
================================= | +0.365 |
Templ | +0.345 |
�� | +0.335 |
jar | +0.322 |
Neg logit contributions | |
ilon | -0.331 |
earch | -0.328 |
Daddy | -0.325 |
Strait | -0.312 |
WN | -0.295 |
Token | of |
Token ID | 286 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
gradation | +1.355 |
================================= | +1.268 |
Templ | +1.213 |
�� | +1.186 |
clot | +1.132 |
Neg logit contributions | |
ilon | -1.045 |
Daddy | -1.036 |
earch | -1.029 |
Strait | -0.979 |
WN | -0.932 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
gradation | +1.375 |
================================= | +1.309 |
Templ | +1.233 |
�� | +1.183 |
clot | +1.150 |
Neg logit contributions | |
earch | -1.107 |
ilon | -1.101 |
Daddy | -1.095 |
Strait | -1.051 |
invasive | -0.988 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
gradation | +1.107 |
================================= | +1.055 |
Templ | +1.004 |
�� | +0.979 |
clot | +0.931 |
Neg logit contributions | |
ilon | -0.826 |
earch | -0.821 |
Daddy | -0.810 |
Strait | -0.774 |
WN | -0.737 |
Token | : |
Token ID | 25 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
gradation | +1.654 |
================================= | +1.522 |
Templ | +1.433 |
�� | +1.413 |
jar | +1.341 |
Neg logit contributions | |
ilon | -1.433 |
Daddy | -1.400 |
earch | -1.393 |
Strait | -1.337 |
Hus | -1.288 |
Token | report |
Token ID | 989 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
ilon | +0.228 |
earch | +0.225 |
Daddy | +0.223 |
Strait | +0.213 |
ktop | +0.202 |
Neg logit contributions | |
gradation | -0.259 |
================================= | -0.246 |
Templ | -0.234 |
�� | -0.225 |
clot | -0.218 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
gradation | +0.446 |
================================= | +0.421 |
Templ | +0.401 |
�� | +0.388 |
clot | +0.376 |
Neg logit contributions | |
ilon | -0.367 |
earch | -0.359 |
Daddy | -0.359 |
Strait | -0.341 |
WN | -0.324 |
Token | airline |
Token ID | 18091 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ilon | +0.009 |
earch | +0.009 |
Daddy | +0.009 |
Strait | +0.009 |
WN | +0.008 |
Neg logit contributions | |
gradation | -0.011 |
================================= | -0.010 |
Templ | -0.010 |
�� | -0.009 |
clot | -0.009 |
Token | takes |
Token ID | 2753 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
gradation | +1.683 |
================================= | +1.589 |
Templ | +1.502 |
�� | +1.470 |
clot | +1.408 |
Neg logit contributions | |
ilon | -1.494 |
earch | -1.480 |
Daddy | -1.459 |
Strait | -1.408 |
WN | -1.332 |
Token | probe |
Token ID | 12774 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
gradation | +0.467 |
================================= | +0.444 |
Templ | +0.423 |
�� | +0.407 |
clot | +0.396 |
Neg logit contributions | |
ilon | -0.370 |
earch | -0.366 |
Daddy | -0.362 |
Strait | -0.343 |
WN | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
gradation | +0.111 |
================================= | +0.106 |
Templ | +0.101 |
�� | +0.097 |
clot | +0.094 |
Neg logit contributions | |
ilon | -0.091 |
earch | -0.090 |
Daddy | -0.089 |
Strait | -0.085 |
WN | -0.080 |
Token | Ph |
Token ID | 1380 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
gradation | +0.184 |
================================= | +0.175 |
Templ | +0.166 |
�� | +0.160 |
clot | +0.155 |
Neg logit contributions | |
ilon | -0.165 |
earch | -0.163 |
Daddy | -0.162 |
Strait | -0.154 |
WN | -0.147 |
Token | obos |
Token ID | 49878 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
ilon | +0.121 |
earch | +0.120 |
Daddy | +0.119 |
Strait | +0.114 |
WN | +0.108 |
Neg logit contributions | |
gradation | -0.126 |
================================= | -0.119 |
Templ | -0.113 |
�� | -0.108 |
clot | -0.105 |
Token | - |
Token ID | 12 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
gradation | +0.386 |
================================= | +0.366 |
Templ | +0.349 |
�� | +0.336 |
clot | +0.327 |
Neg logit contributions | |
ilon | -0.311 |
earch | -0.307 |
Daddy | -0.303 |
Strait | -0.289 |
ktop | -0.273 |
Token | Gr |
Token ID | 8642 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
gradation | +0.276 |
================================= | +0.263 |
Templ | +0.251 |
�� | +0.241 |
clot | +0.235 |
Neg logit contributions | |
ilon | -0.209 |
earch | -0.205 |
Daddy | -0.204 |
Strait | -0.192 |
WN | -0.182 |
Token | unt |
Token ID | 2797 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
gradation | +0.981 |
================================= | +0.904 |
Templ | +0.812 |
�� | +0.794 |
clot | +0.724 |
Neg logit contributions | |
ilon | -2.061 |
Daddy | -2.018 |
earch | -2.006 |
Strait | -1.943 |
Hus | -1.888 |
Token | , |
Token ID | 11 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ilon | +0.080 |
earch | +0.079 |
Daddy | +0.078 |
Strait | +0.074 |
WN | +0.071 |
Neg logit contributions | |
gradation | -0.096 |
================================= | -0.091 |
Templ | -0.087 |
�� | -0.084 |
clot | -0.081 |
Token | last |
Token ID | 938 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
ilon | +0.180 |
earch | +0.178 |
Daddy | +0.176 |
Strait | +0.167 |
WN | +0.158 |
Neg logit contributions | |
gradation | -0.230 |
================================= | -0.219 |
Templ | -0.209 |
�� | -0.201 |
clot | -0.195 |
Token | year |
Token ID | 614 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
gradation | +0.030 |
================================= | +0.028 |
Templ | +0.027 |
�� | +0.025 |
clot | +0.025 |
Neg logit contributions | |
ilon | -0.032 |
earch | -0.032 |
Daddy | -0.031 |
Strait | -0.030 |
WN | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
gradation | +0.274 |
================================= | +0.259 |
Templ | +0.246 |
�� | +0.238 |
clot | +0.230 |
Neg logit contributions | |
ilon | -0.237 |
earch | -0.234 |
Daddy | -0.232 |
Strait | -0.221 |
WN | -0.209 |
Token | all |
Token ID | 477 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
gradation | +0.129 |
================================= | +0.122 |
Templ | +0.116 |
�� | +0.112 |
clot | +0.108 |
Neg logit contributions | |
ilon | -0.115 |
earch | -0.114 |
Daddy | -0.113 |
Strait | -0.108 |
WN | -0.102 |
Token | for |
Token ID | 329 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ilon | +0.359 |
earch | +0.352 |
Daddy | +0.349 |
Strait | +0.332 |
ktop | +0.314 |
Neg logit contributions | |
gradation | -0.429 |
================================= | -0.410 |
Templ | -0.390 |
�� | -0.372 |
clot | -0.364 |
Token | only |
Token ID | 691 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
gradation | +0.231 |
================================= | +0.218 |
Templ | +0.207 |
�� | +0.200 |
clot | +0.193 |
Neg logit contributions | |
ilon | -0.206 |
earch | -0.203 |
Daddy | -0.202 |
Strait | -0.193 |
WN | -0.183 |
Token | $ |
Token ID | 720 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
ilon | +0.304 |
earch | +0.301 |
Daddy | +0.298 |
Strait | +0.282 |
ktop | +0.267 |
Neg logit contributions | |
gradation | -0.381 |
================================= | -0.364 |
Templ | -0.346 |
�� | -0.333 |
clot | -0.324 |
Token | 19 |
Token ID | 1129 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ilon | +0.548 |
earch | +0.541 |
Daddy | +0.539 |
Strait | +0.520 |
ktop | +0.500 |
Neg logit contributions | |
gradation | -0.354 |
================================= | -0.331 |
Templ | -0.309 |
�� | -0.289 |
jar | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
gradation | +0.651 |
================================= | +0.616 |
Templ | +0.585 |
�� | +0.568 |
clot | +0.549 |
Neg logit contributions | |
ilon | -0.533 |
earch | -0.529 |
Daddy | -0.522 |
Strait | -0.500 |
WN | -0.475 |
Token | 99 |
Token ID | 2079 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
gradation | +1.424 |
================================= | +1.306 |
�� | +1.254 |
Templ | +1.249 |
clot | +1.167 |
Neg logit contributions | |
ilon | -1.511 |
Daddy | -1.506 |
earch | -1.488 |
Strait | -1.450 |
WN | -1.396 |
Token | ... |
Token ID | 986 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ilon | +0.114 |
earch | +0.113 |
Daddy | +0.112 |
Strait | +0.108 |
WN | +0.103 |
Neg logit contributions | |
gradation | -0.094 |
================================= | -0.089 |
Templ | -0.083 |
�� | -0.079 |
clot | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
gradation | +0.076 |
================================= | +0.072 |
Templ | +0.069 |
�� | +0.066 |
clot | +0.064 |
Neg logit contributions | |
ilon | -0.066 |
earch | -0.065 |
Daddy | -0.065 |
Strait | -0.062 |
WN | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ilon | +0.055 |
earch | +0.055 |
Daddy | +0.054 |
Strait | +0.052 |
WN | +0.049 |
Neg logit contributions | |
gradation | -0.063 |
================================= | -0.060 |
Templ | -0.057 |
�� | -0.054 |
clot | -0.053 |
Token | Because |
Token ID | 8128 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ilon | +0.071 |
earch | +0.070 |
Daddy | +0.070 |
Strait | +0.066 |
WN | +0.063 |
Neg logit contributions | |
gradation | -0.086 |
================================= | -0.081 |
Templ | -0.077 |
�� | -0.074 |
clot | -0.072 |
Token | seasons |
Token ID | 7028 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
ilon | +0.244 |
earch | +0.241 |
Daddy | +0.239 |
Strait | +0.227 |
WN | +0.216 |
Neg logit contributions | |
gradation | -0.267 |
================================= | -0.254 |
Templ | -0.240 |
�� | -0.231 |
clot | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
ilon | +0.048 |
earch | +0.048 |
Daddy | +0.047 |
Strait | +0.045 |
WN | +0.043 |
Neg logit contributions | |
gradation | -0.056 |
================================= | -0.053 |
Templ | -0.050 |
�� | -0.048 |
clot | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ilon | +0.026 |
earch | +0.025 |
Daddy | +0.025 |
Strait | +0.024 |
WN | +0.023 |
Neg logit contributions | |
gradation | -0.029 |
================================= | -0.028 |
Templ | -0.026 |
�� | -0.025 |
clot | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
gradation | +0.079 |
================================= | +0.075 |
Templ | +0.071 |
�� | +0.069 |
clot | +0.066 |
Neg logit contributions | |
ilon | -0.069 |
earch | -0.068 |
Daddy | -0.067 |
Strait | -0.064 |
WN | -0.061 |
Token | CH |
Token ID | 3398 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
gradation | +0.090 |
================================= | +0.085 |
Templ | +0.081 |
�� | +0.078 |
clot | +0.076 |
Neg logit contributions | |
ilon | -0.076 |
earch | -0.075 |
Daddy | -0.074 |
Strait | -0.071 |
WN | -0.067 |
Token | IC |
Token ID | 2149 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ilon | +0.037 |
earch | +0.036 |
Daddy | +0.036 |
Strait | +0.034 |
WN | +0.032 |
Neg logit contributions | |
gradation | -0.057 |
================================= | -0.055 |
Templ | -0.052 |
�� | -0.051 |
clot | -0.049 |
Token | AG |
Token ID | 4760 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
gradation | +1.150 |
================================= | +1.035 |
Templ | +0.978 |
�� | +0.930 |
jar | +0.877 |
Neg logit contributions | |
earch | -1.801 |
ilon | -1.797 |
Daddy | -1.786 |
Strait | -1.699 |
WN | -1.687 |
Token | O |
Token ID | 46 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
gradation | +0.271 |
================================= | +0.257 |
Templ | +0.247 |
�� | +0.240 |
clot | +0.233 |
Neg logit contributions | |
ilon | -0.159 |
earch | -0.157 |
Daddy | -0.155 |
Strait | -0.146 |
WN | -0.137 |
Token | -- |
Token ID | 1377 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ilon | +0.118 |
earch | +0.117 |
Daddy | +0.116 |
Strait | +0.110 |
WN | +0.104 |
Neg logit contributions | |
gradation | -0.138 |
================================= | -0.131 |
Templ | -0.124 |
�� | -0.120 |
clot | -0.116 |
Token | It |
Token ID | 632 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
gradation | +0.087 |
================================= | +0.082 |
Templ | +0.078 |
�� | +0.074 |
clot | +0.072 |
Neg logit contributions | |
ilon | -0.087 |
earch | -0.086 |
Daddy | -0.085 |
Strait | -0.082 |
WN | -0.078 |
Token | 's |
Token ID | 338 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
gradation | +0.165 |
================================= | +0.157 |
Templ | +0.149 |
�� | +0.144 |
clot | +0.139 |
Neg logit contributions | |
ilon | -0.141 |
earch | -0.140 |
Daddy | -0.139 |
Strait | -0.132 |
WN | -0.125 |
Token | ally |
Token ID | 12525 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ilon | +0.244 |
earch | +0.242 |
Daddy | +0.240 |
Strait | +0.229 |
WN | +0.219 |
Neg logit contributions | |
gradation | -0.235 |
================================= | -0.222 |
Templ | -0.211 |
�� | -0.201 |
clot | -0.196 |
Token | in |
Token ID | 287 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
gradation | +0.217 |
================================= | +0.207 |
Templ | +0.197 |
�� | +0.192 |
jar | +0.185 |
Neg logit contributions | |
ilon | -0.152 |
earch | -0.150 |
Daddy | -0.149 |
Strait | -0.141 |
WN | -0.133 |
Token | charge |
Token ID | 3877 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
gradation | +0.534 |
================================= | +0.507 |
Templ | +0.478 |
�� | +0.465 |
jar | +0.447 |
Neg logit contributions | |
ilon | -0.436 |
earch | -0.431 |
Daddy | -0.428 |
Strait | -0.411 |
WN | -0.387 |
Token | of |
Token ID | 286 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
gradation | +1.496 |
================================= | +1.401 |
Templ | +1.341 |
�� | +1.308 |
clot | +1.252 |
Neg logit contributions | |
ilon | -1.144 |
Daddy | -1.134 |
earch | -1.128 |
Strait | -1.070 |
WN | -1.021 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
gradation | +1.552 |
================================= | +1.474 |
Templ | +1.390 |
�� | +1.335 |
jar | +1.299 |
Neg logit contributions | |
earch | -1.223 |
ilon | -1.212 |
Daddy | -1.210 |
Strait | -1.160 |
invasive | -1.095 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
gradation | +1.031 |
================================= | +0.982 |
Templ | +0.937 |
�� | +0.912 |
clot | +0.873 |
Neg logit contributions | |
ilon | -0.756 |
earch | -0.749 |
Daddy | -0.739 |
Strait | -0.708 |
WN | -0.669 |
Token | : |
Token ID | 25 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
gradation | +1.546 |
================================= | +1.417 |
Templ | +1.332 |
�� | +1.309 |
clot | +1.246 |
Neg logit contributions | |
ilon | -1.422 |
Daddy | -1.387 |
earch | -1.384 |
Strait | -1.328 |
WN | -1.280 |
Token | report |
Token ID | 989 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ilon | +0.435 |
earch | +0.430 |
Daddy | +0.426 |
Strait | +0.409 |
ktop | +0.388 |
Neg logit contributions | |
gradation | -0.484 |
================================= | -0.461 |
Templ | -0.437 |
�� | -0.421 |
clot | -0.407 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
gradation | +0.340 |
================================= | +0.322 |
Templ | +0.307 |
�� | +0.298 |
clot | +0.288 |
Neg logit contributions | |
ilon | -0.257 |
earch | -0.252 |
Daddy | -0.251 |
Strait | -0.238 |
WN | -0.225 |
Token | airline |
Token ID | 18091 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ilon | +0.190 |
earch | +0.187 |
Daddy | +0.185 |
Strait | +0.176 |
ktop | +0.168 |
Neg logit contributions | |
gradation | -0.223 |
================================= | -0.212 |
Templ | -0.201 |
�� | -0.194 |
clot | -0.189 |
Token | takes |
Token ID | 2753 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
gradation | +1.734 |
================================= | +1.642 |
Templ | +1.560 |
�� | +1.532 |
clot | +1.467 |
Neg logit contributions | |
ilon | -1.327 |
earch | -1.309 |
Daddy | -1.287 |
Strait | -1.236 |
WN | -1.168 |
Token | Note |
Token ID | 6425 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
gradation | +1.686 |
================================= | +1.594 |
Templ | +1.559 |
�� | +1.532 |
clot | +1.480 |
Neg logit contributions | |
Daddy | -0.768 |
ilon | -0.758 |
earch | -0.756 |
Strait | -0.683 |
WN | -0.669 |
Token | : |
Token ID | 25 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ilon | +0.122 |
earch | +0.120 |
Daddy | +0.119 |
Strait | +0.113 |
ktop | +0.107 |
Neg logit contributions | |
gradation | -0.158 |
================================= | -0.150 |
Templ | -0.143 |
�� | -0.138 |
clot | -0.134 |
Token | This |
Token ID | 770 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
gradation | +1.086 |
================================= | +0.994 |
Templ | +0.936 |
�� | +0.907 |
jar | +0.878 |
Neg logit contributions | |
ilon | -1.171 |
earch | -1.150 |
Daddy | -1.150 |
Strait | -1.108 |
WN | -1.076 |
Token | article |
Token ID | 2708 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
gradation | +0.468 |
================================= | +0.444 |
Templ | +0.423 |
�� | +0.410 |
clot | +0.396 |
Neg logit contributions | |
ilon | -0.343 |
earch | -0.338 |
Daddy | -0.336 |
Strait | -0.319 |
WN | -0.301 |
Token | gives |
Token ID | 3607 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
gradation | +0.040 |
================================= | +0.037 |
Templ | +0.036 |
�� | +0.034 |
clot | +0.033 |
Neg logit contributions | |
ilon | -0.032 |
earch | -0.032 |
Daddy | -0.032 |
Strait | -0.030 |
WN | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
gradation | +0.296 |
================================= | +0.280 |
Templ | +0.265 |
�� | +0.255 |
jar | +0.247 |
Neg logit contributions | |
ilon | -0.268 |
earch | -0.264 |
Daddy | -0.263 |
Strait | -0.250 |
WN | -0.238 |
Token | views |
Token ID | 5009 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
gradation | +1.604 |
================================= | +1.501 |
Templ | +1.413 |
�� | +1.370 |
jar | +1.361 |
Neg logit contributions | |
ilon | -1.312 |
Daddy | -1.304 |
earch | -1.273 |
Strait | -1.223 |
WN | -1.178 |
Token | of |
Token ID | 286 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
gradation | +0.460 |
================================= | +0.435 |
Templ | +0.414 |
�� | +0.401 |
clot | +0.386 |
Neg logit contributions | |
ilon | -0.388 |
earch | -0.383 |
Daddy | -0.380 |
Strait | -0.361 |
WN | -0.343 |
Token | the |
Token ID | 262 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
gradation | +0.759 |
================================= | +0.717 |
Templ | +0.685 |
�� | +0.663 |
clot | +0.645 |
Neg logit contributions | |
ilon | -0.533 |
earch | -0.527 |
Daddy | -0.524 |
Strait | -0.497 |
WN | -0.468 |
Token | author |
Token ID | 1772 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
gradation | +0.542 |
================================= | +0.516 |
Templ | +0.492 |
�� | +0.477 |
clot | +0.464 |
Neg logit contributions | |
ilon | -0.375 |
earch | -0.370 |
Daddy | -0.368 |
Strait | -0.348 |
WN | -0.329 |
Token | , |
Token ID | 11 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
gradation | +0.732 |
================================= | +0.697 |
Templ | +0.669 |
�� | +0.646 |
clot | +0.628 |
Neg logit contributions | |
ilon | -0.549 |
earch | -0.541 |
Daddy | -0.539 |
Strait | -0.511 |
WN | -0.485 |
Token | TV |
Token ID | 3195 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
gradation | +0.207 |
================================= | +0.195 |
Templ | +0.185 |
�� | +0.178 |
clot | +0.171 |
Neg logit contributions | |
ilon | -0.206 |
earch | -0.204 |
Daddy | -0.203 |
Strait | -0.194 |
WN | -0.185 |
Token | news |
Token ID | 1705 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
gradation | +0.914 |
================================= | +0.872 |
Templ | +0.837 |
�� | +0.823 |
clot | +0.787 |
Neg logit contributions | |
ilon | -0.533 |
earch | -0.528 |
Daddy | -0.523 |
Strait | -0.495 |
WN | -0.466 |
Token | ! |
Token ID | 0 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
gradation | +1.313 |
================================= | +1.249 |
Templ | +1.215 |
�� | +1.195 |
clot | +1.135 |
Neg logit contributions | |
ilon | -0.834 |
Daddy | -0.817 |
earch | -0.809 |
Strait | -0.769 |
WN | -0.735 |
Token | Sign |
Token ID | 5865 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
gradation | +1.792 |
================================= | +1.708 |
Templ | +1.654 |
�� | +1.642 |
clot | +1.581 |
Neg logit contributions | |
ilon | -0.762 |
Daddy | -0.761 |
earch | -0.742 |
Strait | -0.702 |
WN | -0.649 |
Token | up |
Token ID | 510 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
gradation | +0.089 |
================================= | +0.084 |
Templ | +0.080 |
�� | +0.078 |
clot | +0.075 |
Neg logit contributions | |
ilon | -0.069 |
earch | -0.068 |
Daddy | -0.067 |
Strait | -0.064 |
WN | -0.061 |
Token | for |
Token ID | 329 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ilon | +0.243 |
earch | +0.241 |
Daddy | +0.237 |
Strait | +0.225 |
ktop | +0.214 |
Neg logit contributions | |
gradation | -0.300 |
================================= | -0.286 |
Templ | -0.272 |
�� | -0.261 |
clot | -0.254 |
Token | our |
Token ID | 674 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
gradation | +1.808 |
================================= | +1.692 |
Templ | +1.643 |
�� | +1.621 |
clot | +1.552 |
Neg logit contributions | |
Daddy | -1.067 |
ilon | -1.064 |
earch | -1.058 |
Strait | -0.998 |
Hus | -0.937 |
Token | Email |
Token ID | 9570 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
gradation | +0.329 |
================================= | +0.304 |
Templ | +0.285 |
�� | +0.271 |
clot | +0.259 |
Neg logit contributions | |
ilon | -0.476 |
Daddy | -0.471 |
earch | -0.471 |
Strait | -0.452 |
WN | -0.436 |
Token | News |
Token ID | 3000 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ilon | +0.207 |
earch | +0.203 |
Daddy | +0.200 |
Strait | +0.188 |
ktop | +0.176 |
Neg logit contributions | |
gradation | -0.358 |
================================= | -0.343 |
Templ | -0.328 |
�� | -0.317 |
jar | -0.309 |
Token | letters |
Token ID | 15653 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
gradation | +1.057 |
================================= | +0.982 |
Templ | +0.946 |
�� | +0.913 |
clot | +0.873 |
Neg logit contributions | |
Daddy | -1.029 |
ilon | -1.026 |
earch | -1.024 |
Strait | -0.975 |
WN | -0.933 |
Token | here |
Token ID | 994 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ilon | +0.234 |
earch | +0.231 |
Daddy | +0.229 |
Strait | +0.217 |
WN | +0.206 |
Neg logit contributions | |
gradation | -0.295 |
================================= | -0.281 |
Templ | -0.267 |
�� | -0.257 |
clot | -0.250 |
Token | ally |
Token ID | 12525 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilon | +0.338 |
earch | +0.336 |
Daddy | +0.334 |
Strait | +0.316 |
ktop | +0.302 |
Neg logit contributions | |
gradation | -0.364 |
================================= | -0.344 |
Templ | -0.329 |
�� | -0.313 |
clot | -0.307 |
Token | in |
Token ID | 287 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
gradation | +0.162 |
================================= | +0.155 |
Templ | +0.147 |
�� | +0.142 |
clot | +0.138 |
Neg logit contributions | |
ilon | -0.122 |
earch | -0.120 |
Daddy | -0.120 |
Strait | -0.114 |
WN | -0.107 |
Token | charge |
Token ID | 3877 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
gradation | +0.526 |
================================= | +0.499 |
Templ | +0.470 |
�� | +0.457 |
jar | +0.439 |
Neg logit contributions | |
ilon | -0.453 |
earch | -0.448 |
Daddy | -0.445 |
Strait | -0.428 |
WN | -0.403 |
Token | of |
Token ID | 286 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
gradation | +1.245 |
================================= | +1.167 |
Templ | +1.112 |
�� | +1.087 |
clot | +1.037 |
Neg logit contributions | |
ilon | -0.985 |
Daddy | -0.971 |
earch | -0.966 |
Strait | -0.920 |
WN | -0.876 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
gradation | +1.410 |
================================= | +1.343 |
Templ | +1.256 |
�� | +1.209 |
clot | +1.174 |
Neg logit contributions | |
earch | -1.170 |
ilon | -1.165 |
Daddy | -1.155 |
Strait | -1.114 |
invasive | -1.049 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
gradation | +1.182 |
================================= | +1.131 |
Templ | +1.074 |
�� | +1.050 |
jar | +0.997 |
Neg logit contributions | |
ilon | -0.855 |
earch | -0.849 |
Daddy | -0.840 |
Strait | -0.801 |
WN | -0.761 |
Token | : |
Token ID | 25 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
gradation | +1.550 |
================================= | +1.438 |
Templ | +1.348 |
�� | +1.325 |
jar | +1.265 |
Neg logit contributions | |
ilon | -1.356 |
Daddy | -1.314 |
earch | -1.311 |
Strait | -1.258 |
Hus | -1.206 |
Token | report |
Token ID | 989 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ilon | +0.152 |
earch | +0.151 |
Daddy | +0.149 |
Strait | +0.142 |
ktop | +0.135 |
Neg logit contributions | |
gradation | -0.173 |
================================= | -0.164 |
Templ | -0.156 |
�� | -0.150 |
clot | -0.145 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
gradation | +0.246 |
================================= | +0.234 |
Templ | +0.223 |
�� | +0.215 |
clot | +0.209 |
Neg logit contributions | |
ilon | -0.188 |
earch | -0.185 |
Daddy | -0.184 |
Strait | -0.174 |
WN | -0.165 |
Token | airline |
Token ID | 18091 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
gradation | +0.004 |
================================= | +0.004 |
Templ | +0.004 |
�� | +0.004 |
clot | +0.004 |
Neg logit contributions | |
ilon | -0.004 |
earch | -0.004 |
Daddy | -0.003 |
Strait | -0.003 |
WN | -0.003 |
Token | takes |
Token ID | 2753 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
gradation | +1.459 |
================================= | +1.379 |
Templ | +1.302 |
�� | +1.267 |
clot | +1.217 |
Neg logit contributions | |
ilon | -1.374 |
earch | -1.359 |
Daddy | -1.341 |
Strait | -1.293 |
WN | -1.227 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
gradation | +0.042 |
================================= | +0.040 |
Templ | +0.038 |
�� | +0.036 |
clot | +0.035 |
Neg logit contributions | |
ilon | -0.037 |
earch | -0.036 |
Daddy | -0.036 |
Strait | -0.034 |
WN | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
gradation | +0.091 |
================================= | +0.086 |
Templ | +0.081 |
�� | +0.079 |
clot | +0.076 |
Neg logit contributions | |
ilon | -0.078 |
earch | -0.078 |
Daddy | -0.077 |
Strait | -0.073 |
WN | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
gradation | +0.070 |
================================= | +0.066 |
Templ | +0.063 |
�� | +0.060 |
clot | +0.058 |
Neg logit contributions | |
ilon | -0.060 |
earch | -0.060 |
Daddy | -0.059 |
Strait | -0.056 |
WN | -0.054 |
Token | Sign |
Token ID | 11712 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ilon | +0.052 |
earch | +0.051 |
Daddy | +0.051 |
Strait | +0.048 |
WN | +0.045 |
Neg logit contributions | |
gradation | -0.082 |
================================= | -0.079 |
Templ | -0.075 |
�� | -0.073 |
clot | -0.071 |
Token | up |
Token ID | 510 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
gradation | +0.010 |
================================= | +0.009 |
Templ | +0.009 |
�� | +0.009 |
clot | +0.008 |
Neg logit contributions | |
ilon | -0.008 |
earch | -0.008 |
Daddy | -0.008 |
Strait | -0.007 |
WN | -0.007 |
Token | for |
Token ID | 329 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
gradation | +0.176 |
================================= | +0.167 |
Templ | +0.159 |
�� | +0.154 |
clot | +0.149 |
Neg logit contributions | |
ilon | -0.136 |
earch | -0.134 |
Daddy | -0.133 |
Strait | -0.126 |
WN | -0.119 |
Token | our |
Token ID | 674 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
gradation | +1.784 |
================================= | +1.708 |
Templ | +1.630 |
�� | +1.606 |
jar | +1.528 |
Neg logit contributions | |
ilon | -1.046 |
Daddy | -1.039 |
earch | -1.025 |
Strait | -0.987 |
WN | -0.919 |
Token | Wine |
Token ID | 20447 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
gradation | +0.538 |
================================= | +0.508 |
Templ | +0.481 |
�� | +0.467 |
clot | +0.449 |
Neg logit contributions | |
ilon | -0.510 |
earch | -0.503 |
Daddy | -0.502 |
Strait | -0.477 |
WN | -0.458 |
Token | Club |
Token ID | 6289 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ilon | +1.112 |
earch | +1.095 |
Daddy | +1.071 |
Strait | +1.032 |
WN | +1.007 |
Neg logit contributions | |
gradation | -0.693 |
================================= | -0.632 |
Templ | -0.598 |
�� | -0.556 |
clot | -0.537 |
Token | today |
Token ID | 1909 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilon | +0.151 |
earch | +0.149 |
Daddy | +0.147 |
Strait | +0.139 |
WN | +0.131 |
Neg logit contributions | |
gradation | -0.216 |
================================= | -0.206 |
Templ | -0.197 |
�� | -0.189 |
clot | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
gradation | +0.153 |
================================= | +0.145 |
Templ | +0.137 |
�� | +0.133 |
clot | +0.128 |
Neg logit contributions | |
ilon | -0.132 |
earch | -0.130 |
Daddy | -0.130 |
Strait | -0.123 |
WN | -0.117 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
gradation | +1.410 |
================================= | +1.343 |
Templ | +1.256 |
�� | +1.209 |
clot | +1.174 |
Neg logit contributions | |
earch | -1.170 |
ilon | -1.165 |
Daddy | -1.155 |
Strait | -1.114 |
invasive | -1.049 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
gradation | +1.182 |
================================= | +1.131 |
Templ | +1.074 |
�� | +1.050 |
jar | +0.997 |
Neg logit contributions | |
ilon | -0.855 |
earch | -0.849 |
Daddy | -0.840 |
Strait | -0.801 |
WN | -0.761 |
Token | : |
Token ID | 25 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
gradation | +1.550 |
================================= | +1.438 |
Templ | +1.348 |
�� | +1.325 |
jar | +1.265 |
Neg logit contributions | |
ilon | -1.356 |
Daddy | -1.314 |
earch | -1.311 |
Strait | -1.258 |
Hus | -1.206 |
Token | report |
Token ID | 989 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ilon | +0.152 |
earch | +0.151 |
Daddy | +0.149 |
Strait | +0.142 |
ktop | +0.135 |
Neg logit contributions | |
gradation | -0.173 |
================================= | -0.164 |
Templ | -0.156 |
�� | -0.150 |
clot | -0.145 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
gradation | +0.246 |
================================= | +0.234 |
Templ | +0.223 |
�� | +0.215 |
clot | +0.209 |
Neg logit contributions | |
ilon | -0.188 |
earch | -0.185 |
Daddy | -0.184 |
Strait | -0.174 |
WN | -0.165 |
Token | airline |
Token ID | 18091 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
gradation | +0.004 |
================================= | +0.004 |
Templ | +0.004 |
�� | +0.004 |
clot | +0.004 |
Neg logit contributions | |
ilon | -0.004 |
earch | -0.004 |
Daddy | -0.003 |
Strait | -0.003 |
WN | -0.003 |
Token | takes |
Token ID | 2753 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
gradation | +1.459 |
================================= | +1.379 |
Templ | +1.302 |
�� | +1.267 |
clot | +1.217 |
Neg logit contributions | |
ilon | -1.374 |
earch | -1.359 |
Daddy | -1.341 |
Strait | -1.293 |
WN | -1.227 |
Token | steps |
Token ID | 4831 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
gradation | +0.293 |
================================= | +0.273 |
Templ | +0.254 |
�� | +0.242 |
jar | +0.229 |
Neg logit contributions | |
ilon | -0.422 |
earch | -0.417 |
Daddy | -0.415 |
Strait | -0.401 |
WN | -0.384 |
Token | to |
Token ID | 284 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
gradation | +0.296 |
================================= | +0.280 |
Templ | +0.268 |
�� | +0.259 |
clot | +0.249 |
Neg logit contributions | |
ilon | -0.229 |
earch | -0.226 |
Daddy | -0.224 |
Strait | -0.213 |
WN | -0.200 |
Token | open |
Token ID | 1280 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
gradation | +0.901 |
================================= | +0.850 |
Templ | +0.811 |
�� | +0.796 |
jar | +0.758 |
Neg logit contributions | |
ilon | -0.618 |
earch | -0.600 |
Daddy | -0.594 |
Strait | -0.572 |
WN | -0.534 |
Token | flights |
Token ID | 13956 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
gradation | +0.040 |
================================= | +0.038 |
Templ | +0.036 |
�� | +0.035 |
clot | +0.034 |
Neg logit contributions | |
ilon | -0.039 |
earch | -0.038 |
Daddy | -0.038 |
Strait | -0.036 |
WN | -0.035 |
Token | E |
Token ID | 412 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ilon | +0.013 |
earch | +0.013 |
Daddy | +0.013 |
Strait | +0.012 |
WN | +0.012 |
Neg logit contributions | |
gradation | -0.014 |
================================= | -0.013 |
Templ | -0.012 |
�� | -0.012 |
clot | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ilon | +0.314 |
earch | +0.311 |
Daddy | +0.307 |
Strait | +0.291 |
wcsstore | +0.274 |
Neg logit contributions | |
gradation | -0.397 |
================================= | -0.379 |
Templ | -0.360 |
�� | -0.344 |
jar | -0.337 |
Token | mail |
Token ID | 4529 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ilon | +0.026 |
earch | +0.026 |
Daddy | +0.026 |
Strait | +0.025 |
WN | +0.024 |
Neg logit contributions | |
gradation | -0.020 |
================================= | -0.019 |
Templ | -0.017 |
�� | -0.017 |
clot | -0.016 |
Token | this |
Token ID | 428 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
ilon | +0.100 |
earch | +0.099 |
Daddy | +0.098 |
Strait | +0.093 |
ktop | +0.088 |
Neg logit contributions | |
gradation | -0.114 |
================================= | -0.108 |
Templ | -0.103 |
�� | -0.099 |
clot | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
gradation | +0.372 |
================================= | +0.352 |
Templ | +0.336 |
�� | +0.327 |
clot | +0.314 |
Neg logit contributions | |
ilon | -0.285 |
earch | -0.281 |
Daddy | -0.279 |
Strait | -0.264 |
WN | -0.250 |
Token | a |
Token ID | 257 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
gradation | +0.366 |
================================= | +0.348 |
Templ | +0.332 |
�� | +0.321 |
jar | +0.310 |
Neg logit contributions | |
ilon | -0.277 |
earch | -0.273 |
Daddy | -0.270 |
Strait | -0.257 |
WN | -0.243 |
Token | friend |
Token ID | 1545 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
gradation | +1.798 |
================================= | +1.694 |
Templ | +1.641 |
�� | +1.600 |
jar | +1.539 |
Neg logit contributions | |
ilon | -1.038 |
Daddy | -1.019 |
earch | -1.008 |
Strait | -0.952 |
WN | -0.898 |
Token | Print |
Token ID | 12578 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ilon | +0.550 |
earch | +0.546 |
Daddy | +0.536 |
Strait | +0.512 |
ktop | +0.493 |
Neg logit contributions | |
gradation | -0.580 |
================================= | -0.556 |
Templ | -0.525 |
�� | -0.496 |
clot | -0.486 |
Token | able |
Token ID | 540 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
gradation | +1.434 |
================================= | +1.327 |
Templ | +1.286 |
�� | +1.250 |
clot | +1.209 |
Neg logit contributions | |
ilon | -1.022 |
Daddy | -1.003 |
earch | -1.003 |
Strait | -0.939 |
Hus | -0.902 |
Token | version |
Token ID | 2196 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
gradation | +0.176 |
================================= | +0.167 |
Templ | +0.159 |
�� | +0.154 |
clot | +0.149 |
Neg logit contributions | |
ilon | -0.134 |
earch | -0.131 |
Daddy | -0.131 |
Strait | -0.124 |
WN | -0.117 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ilon | +0.301 |
earch | +0.297 |
Daddy | +0.293 |
Strait | +0.276 |
WN | +0.259 |
Neg logit contributions | |
gradation | -0.497 |
================================= | -0.479 |
Templ | -0.456 |
�� | -0.439 |
clot | -0.430 |
Token | ker |
Token ID | 41927 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
gradation | +0.224 |
================================= | +0.211 |
Templ | +0.199 |
�� | +0.192 |
clot | +0.183 |
Neg logit contributions | |
ilon | -0.243 |
earch | -0.240 |
Daddy | -0.239 |
Strait | -0.229 |
WN | -0.218 |
Token | at |
Token ID | 265 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
gradation | +0.478 |
================================= | +0.459 |
Templ | +0.443 |
�� | +0.432 |
clot | +0.419 |
Neg logit contributions | |
ilon | -0.210 |
earch | -0.205 |
Daddy | -0.203 |
Strait | -0.187 |
ktop | -0.172 |
Token | otic |
Token ID | 6210 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
gradation | +0.439 |
================================= | +0.415 |
Templ | +0.394 |
�� | +0.380 |
clot | +0.364 |
Neg logit contributions | |
ilon | -0.429 |
earch | -0.422 |
Daddy | -0.420 |
Strait | -0.401 |
ktop | -0.381 |
Token | plugs |
Token ID | 37008 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ilon | +0.108 |
earch | +0.107 |
Daddy | +0.106 |
Strait | +0.101 |
WN | +0.096 |
Neg logit contributions | |
gradation | -0.110 |
================================= | -0.104 |
Templ | -0.098 |
�� | -0.094 |
clot | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
gradation | +0.156 |
================================= | +0.148 |
Templ | +0.141 |
�� | +0.136 |
clot | +0.132 |
Neg logit contributions | |
ilon | -0.122 |
earch | -0.120 |
Daddy | -0.120 |
Strait | -0.114 |
WN | -0.107 |
Token | mim |
Token ID | 17007 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
gradation | +0.385 |
================================= | +0.354 |
Templ | +0.328 |
�� | +0.313 |
jar | +0.293 |
Neg logit contributions | |
ilon | -0.646 |
earch | -0.638 |
Daddy | -0.637 |
Strait | -0.613 |
WN | -0.591 |
Token | icking |
Token ID | 7958 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
gradation | +1.520 |
================================= | +1.431 |
Templ | +1.378 |
�� | +1.349 |
clot | +1.272 |
Neg logit contributions | |
ilon | -1.323 |
earch | -1.278 |
Daddy | -1.278 |
Strait | -1.206 |
WN | -1.162 |
Token | the |
Token ID | 262 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ilon | +0.025 |
earch | +0.024 |
Daddy | +0.024 |
Strait | +0.023 |
WN | +0.021 |
Neg logit contributions | |
gradation | -0.033 |
================================= | -0.031 |
Templ | -0.030 |
�� | -0.029 |
clot | -0.028 |
Token | sp |
Token ID | 599 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
gradation | +0.253 |
================================= | +0.240 |
Templ | +0.228 |
�� | +0.221 |
clot | +0.212 |
Neg logit contributions | |
ilon | -0.206 |
earch | -0.203 |
Daddy | -0.201 |
Strait | -0.192 |
WN | -0.181 |
Token | ines |
Token ID | 1127 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
gradation | +0.446 |
================================= | +0.409 |
Templ | +0.382 |
�� | +0.364 |
clot | +0.337 |
Neg logit contributions | |
ilon | -0.814 |
earch | -0.806 |
Daddy | -0.799 |
Strait | -0.771 |
ktop | -0.745 |
Token | on |
Token ID | 319 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
ilon | +0.111 |
earch | +0.110 |
Daddy | +0.109 |
Strait | +0.103 |
WN | +0.098 |
Neg logit contributions | |
gradation | -0.123 |
================================= | -0.117 |
Templ | -0.111 |
�� | -0.106 |
clot | -0.103 |
Token | taxes |
Token ID | 5704 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
gradation | +1.458 |
================================= | +1.389 |
Templ | +1.332 |
�� | +1.284 |
clot | +1.240 |
Neg logit contributions | |
ilon | -0.873 |
earch | -0.870 |
Daddy | -0.870 |
Strait | -0.798 |
WN | -0.755 |
Token | ' |
Token ID | 6 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
gradation | +1.072 |
================================= | +1.008 |
Templ | +0.980 |
�� | +0.950 |
clot | +0.910 |
Neg logit contributions | |
ilon | -0.729 |
Daddy | -0.717 |
earch | -0.714 |
Strait | -0.678 |
Hus | -0.636 |
Token | Former |
Token ID | 14466 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gradation | +0.664 |
================================= | +0.618 |
Templ | +0.591 |
�� | +0.568 |
clot | +0.544 |
Neg logit contributions | |
ilon | -0.692 |
earch | -0.686 |
Daddy | -0.679 |
Strait | -0.652 |
WN | -0.628 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
gradation | +0.753 |
================================= | +0.711 |
Templ | +0.676 |
�� | +0.649 |
jar | +0.626 |
Neg logit contributions | |
ilon | -0.665 |
Daddy | -0.654 |
earch | -0.647 |
Strait | -0.609 |
WN | -0.591 |
Token | campaign |
Token ID | 1923 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
gradation | +1.009 |
================================= | +0.954 |
Templ | +0.918 |
�� | +0.886 |
jar | +0.865 |
Neg logit contributions | |
ilon | -0.564 |
Daddy | -0.549 |
earch | -0.547 |
Strait | -0.509 |
WN | -0.479 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
gradation | +0.306 |
================================= | +0.290 |
Templ | +0.275 |
�� | +0.266 |
clot | +0.256 |
Neg logit contributions | |
ilon | -0.276 |
earch | -0.272 |
Daddy | -0.271 |
Strait | -0.258 |
WN | -0.245 |
Token | : |
Token ID | 25 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
gradation | +1.636 |
================================= | +1.565 |
Templ | +1.498 |
�� | +1.450 |
clot | +1.394 |
Neg logit contributions | |
ilon | -1.137 |
earch | -1.126 |
Daddy | -1.124 |
Strait | -1.069 |
WN | -0.999 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
gradation | +0.826 |
================================= | +0.781 |
Templ | +0.736 |
�� | +0.718 |
clot | +0.693 |
Neg logit contributions | |
ilon | -0.743 |
earch | -0.730 |
Daddy | -0.729 |
Strait | -0.696 |
WN | -0.663 |
Token | staff |
Token ID | 3085 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
gradation | +1.339 |
================================= | +1.293 |
Templ | +1.210 |
�� | +1.199 |
clot | +1.138 |
Neg logit contributions | |
ilon | -1.119 |
earch | -1.082 |
Daddy | -1.079 |
Strait | -1.029 |
invasive | -0.976 |
Token | are |
Token ID | 389 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
gradation | +0.741 |
================================= | +0.703 |
Templ | +0.670 |
�� | +0.639 |
clot | +0.623 |
Neg logit contributions | |
ilon | -0.594 |
earch | -0.586 |
Daddy | -0.578 |
Strait | -0.552 |
WN | -0.521 |
Token | ' |
Token ID | 705 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
gradation | +0.469 |
================================= | +0.434 |
Templ | +0.405 |
�� | +0.381 |
jar | +0.370 |
Neg logit contributions | |
ilon | -0.661 |
earch | -0.657 |
Daddy | -0.652 |
Strait | -0.627 |
LCS | -0.599 |
Token | Ric |
Token ID | 15868 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
gradation | +0.193 |
================================= | +0.183 |
Templ | +0.174 |
�� | +0.168 |
clot | +0.163 |
Neg logit contributions | |
ilon | -0.165 |
earch | -0.163 |
Daddy | -0.162 |
Strait | -0.154 |
WN | -0.146 |
Token | her |
Token ID | 372 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ilon | +0.282 |
earch | +0.275 |
Daddy | +0.273 |
Strait | +0.249 |
ktop | +0.228 |
Neg logit contributions | |
gradation | -0.796 |
================================= | -0.766 |
Templ | -0.739 |
�� | -0.714 |
jar | -0.707 |
Token | t |
Token ID | 83 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ilon | +0.232 |
earch | +0.230 |
Daddy | +0.227 |
Strait | +0.216 |
ktop | +0.204 |
Neg logit contributions | |
gradation | -0.298 |
================================= | -0.283 |
Templ | -0.270 |
�� | -0.259 |
jar | -0.252 |
Token | and |
Token ID | 290 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
ilon | +0.665 |
earch | +0.661 |
Daddy | +0.648 |
Strait | +0.615 |
ktop | +0.593 |
Neg logit contributions | |
gradation | -0.785 |
================================= | -0.750 |
Templ | -0.710 |
�� | -0.674 |
clot | -0.658 |
Token | David |
Token ID | 3271 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ilon | +1.811 |
earch | +1.804 |
Daddy | +1.795 |
Strait | +1.701 |
wcsstore | +1.677 |
Neg logit contributions | |
gradation | -1.495 |
================================= | -1.426 |
Templ | -1.346 |
jar | -1.242 |
�� | -1.234 |
Token | Gordon |
Token ID | 11646 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ilon | +0.091 |
earch | +0.090 |
Daddy | +0.090 |
Strait | +0.086 |
ktop | +0.082 |
Neg logit contributions | |
gradation | -0.074 |
================================= | -0.069 |
Templ | -0.065 |
�� | -0.062 |
clot | -0.059 |
Token | ( |
Token ID | 357 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
ilon | +1.933 |
Daddy | +1.909 |
earch | +1.904 |
ktop | +1.800 |
Strait | +1.794 |
Neg logit contributions | |
gradation | -1.798 |
================================= | -1.765 |
Templ | -1.673 |
jar | -1.508 |
clot | -1.507 |
Token | IS |
Token ID | 1797 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
ilon | +0.303 |
earch | +0.299 |
Daddy | +0.295 |
Strait | +0.279 |
ktop | +0.261 |
Neg logit contributions | |
gradation | -0.568 |
================================= | -0.544 |
Templ | -0.522 |
�� | -0.505 |
jar | -0.493 |
Token | I |
Token ID | 40 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ilon | +0.349 |
earch | +0.346 |
Daddy | +0.343 |
Strait | +0.326 |
ktop | +0.307 |
Neg logit contributions | |
gradation | -0.489 |
================================= | -0.466 |
Templ | -0.443 |
�� | -0.427 |
jar | -0.416 |
Token | Books |
Token ID | 13661 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ilon | +0.629 |
earch | +0.621 |
Daddy | +0.618 |
Strait | +0.592 |
ktop | +0.575 |
Neg logit contributions | |
gradation | -0.458 |
================================= | -0.434 |
Templ | -0.406 |
�� | -0.382 |
clot | -0.367 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ilon | +0.717 |
earch | +0.708 |
Daddy | +0.701 |
Strait | +0.662 |
ktop | +0.643 |
Neg logit contributions | |
gradation | -0.828 |
================================= | -0.792 |
Templ | -0.748 |
�� | -0.711 |
clot | -0.692 |
Token | " |
Token ID | 366 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
ilon | +0.067 |
earch | +0.067 |
Daddy | +0.066 |
Strait | +0.063 |
WN | +0.060 |
Neg logit contributions | |
gradation | -0.074 |
================================= | -0.070 |
Templ | -0.067 |
�� | -0.064 |
clot | -0.062 |
Token | One |
Token ID | 3198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ilon | +0.251 |
earch | +0.248 |
Daddy | +0.245 |
Strait | +0.234 |
ktop | +0.222 |
Neg logit contributions | |
gradation | -0.299 |
================================= | -0.284 |
Templ | -0.270 |
�� | -0.259 |
clot | -0.251 |
Token | Fle |
Token ID | 12005 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ilon | +0.890 |
earch | +0.886 |
Daddy | +0.867 |
Strait | +0.819 |
ktop | +0.786 |
Neg logit contributions | |
gradation | -1.227 |
================================= | -1.178 |
Templ | -1.127 |
�� | -1.072 |
clot | -1.051 |
Token | w |
Token ID | 86 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
gradation | +0.178 |
================================= | +0.171 |
Templ | +0.164 |
�� | +0.159 |
clot | +0.155 |
Neg logit contributions | |
ilon | -0.095 |
earch | -0.093 |
Daddy | -0.092 |
Strait | -0.086 |
WN | -0.080 |
Token | Over |
Token ID | 3827 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ilon | +0.145 |
earch | +0.144 |
Daddy | +0.142 |
Strait | +0.136 |
WN | +0.129 |
Neg logit contributions | |
gradation | -0.160 |
================================= | -0.152 |
Templ | -0.144 |
�� | -0.138 |
clot | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
gradation | +0.087 |
================================= | +0.083 |
Templ | +0.079 |
�� | +0.076 |
clot | +0.074 |
Neg logit contributions | |
ilon | -0.065 |
earch | -0.064 |
Daddy | -0.064 |
Strait | -0.060 |
WN | -0.057 |
Token | C |
Token ID | 327 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
earch | +1.477 |
ilon | +1.421 |
Daddy | +1.370 |
ktop | +1.314 |
Strait | +1.271 |
Neg logit contributions | |
gradation | -2.148 |
================================= | -2.095 |
Templ | -2.026 |
�� | -1.919 |
』 | -1.883 |
Token | uck |
Token ID | 1347 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ilon | +0.370 |
earch | +0.366 |
Daddy | +0.364 |
Strait | +0.346 |
ktop | +0.333 |
Neg logit contributions | |
gradation | -0.379 |
================================= | -0.360 |
Templ | -0.340 |
�� | -0.325 |
jar | -0.317 |
Token | oo |
Token ID | 2238 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
gradation | +0.405 |
================================= | +0.385 |
Templ | +0.369 |
�� | +0.358 |
clot | +0.346 |
Neg logit contributions | |
ilon | -0.269 |
earch | -0.264 |
Daddy | -0.263 |
Strait | -0.249 |
WN | -0.232 |
Token | 's |
Token ID | 338 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ilon | +0.441 |
earch | +0.438 |
Daddy | +0.432 |
Strait | +0.407 |
ktop | +0.392 |
Neg logit contributions | |
gradation | -0.534 |
================================= | -0.509 |
Templ | -0.483 |
�� | -0.463 |
clot | -0.453 |
Token | Nest |
Token ID | 21420 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ilon | +1.055 |
earch | +1.043 |
Daddy | +1.011 |
Strait | +0.939 |
ktop | +0.915 |
Neg logit contributions | |
gradation | -1.749 |
================================= | -1.719 |
Templ | -1.640 |
�� | -1.560 |
jar | -1.537 |
Token | � |
Token ID | 247 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
gradation | +0.072 |
================================= | +0.069 |
Templ | +0.066 |
�� | +0.063 |
clot | +0.062 |
Neg logit contributions | |
ilon | -0.052 |
earch | -0.052 |
Daddy | -0.051 |
Strait | -0.048 |
WN | -0.046 |
Token | s |
Token ID | 82 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
gradation | +0.119 |
================================= | +0.113 |
Templ | +0.108 |
�� | +0.104 |
clot | +0.101 |
Neg logit contributions | |
ilon | -0.088 |
earch | -0.087 |
Daddy | -0.086 |
Strait | -0.082 |
WN | -0.077 |
Token | been |
Token ID | 587 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
gradation | +0.172 |
================================= | +0.163 |
Templ | +0.155 |
�� | +0.150 |
clot | +0.145 |
Neg logit contributions | |
ilon | -0.150 |
earch | -0.149 |
Daddy | -0.147 |
Strait | -0.140 |
WN | -0.133 |
Token | Nikol |
Token ID | 48127 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
gradation | +0.153 |
================================= | +0.145 |
Templ | +0.138 |
�� | +0.133 |
clot | +0.129 |
Neg logit contributions | |
ilon | -0.123 |
earch | -0.121 |
Daddy | -0.120 |
Strait | -0.114 |
WN | -0.108 |
Token | aj |
Token ID | 1228 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
gradation | +0.064 |
================================= | +0.061 |
Templ | +0.058 |
�� | +0.056 |
clot | +0.055 |
Neg logit contributions | |
ilon | -0.045 |
earch | -0.044 |
Daddy | -0.044 |
Strait | -0.042 |
WN | -0.039 |
Token | Eh |
Token ID | 31480 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ilon | +0.424 |
earch | +0.421 |
Daddy | +0.414 |
Strait | +0.393 |
ktop | +0.375 |
Neg logit contributions | |
gradation | -0.488 |
================================= | -0.462 |
Templ | -0.442 |
�� | -0.423 |
jar | -0.412 |
Token | lers |
Token ID | 8116 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
ilon | +1.347 |
earch | +1.311 |
Daddy | +1.290 |
Strait | +1.198 |
wcsstore | +1.159 |
Neg logit contributions | |
gradation | -2.253 |
================================= | -2.187 |
Templ | -2.075 |
�� | -2.000 |
jar | -1.966 |
Token | and |
Token ID | 290 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
gradation | +0.035 |
================================= | +0.033 |
Templ | +0.031 |
�� | +0.030 |
clot | +0.029 |
Neg logit contributions | |
ilon | -0.028 |
earch | -0.028 |
Daddy | -0.028 |
Strait | -0.026 |
WN | -0.025 |
Token | Patri |
Token ID | 9606 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
gradation | +0.051 |
================================= | +0.048 |
Templ | +0.045 |
�� | +0.043 |
clot | +0.042 |
Neg logit contributions | |
ilon | -0.049 |
earch | -0.049 |
Daddy | -0.048 |
Strait | -0.046 |
WN | -0.044 |
Token | k |
Token ID | 74 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
gradation | +0.609 |
================================= | +0.578 |
Templ | +0.555 |
�� | +0.539 |
clot | +0.525 |
Neg logit contributions | |
ilon | -0.365 |
earch | -0.356 |
Daddy | -0.356 |
Strait | -0.339 |
WN | -0.314 |
Token | L |
Token ID | 406 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ilon | +0.136 |
earch | +0.134 |
Daddy | +0.132 |
Strait | +0.125 |
ktop | +0.118 |
Neg logit contributions | |
gradation | -0.201 |
================================= | -0.192 |
Templ | -0.184 |
�� | -0.177 |
clot | -0.172 |
Token | here |
Token ID | 994 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
gradation | +0.169 |
================================= | +0.161 |
Templ | +0.153 |
�� | +0.149 |
clot | +0.143 |
Neg logit contributions | |
ilon | -0.129 |
earch | -0.127 |
Daddy | -0.126 |
Strait | -0.120 |
WN | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
earch | +0.811 |
ilon | +0.809 |
Daddy | +0.800 |
Strait | +0.769 |
ktop | +0.732 |
Neg logit contributions | |
gradation | -0.863 |
================================= | -0.822 |
Templ | -0.771 |
�� | -0.737 |
jar | -0.720 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
gradation | +0.069 |
================================= | +0.065 |
Templ | +0.062 |
�� | +0.060 |
clot | +0.058 |
Neg logit contributions | |
ilon | -0.059 |
earch | -0.059 |
Daddy | -0.058 |
Strait | -0.056 |
WN | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
gradation | +0.143 |
================================= | +0.135 |
Templ | +0.129 |
�� | +0.124 |
clot | +0.120 |
Neg logit contributions | |
ilon | -0.123 |
earch | -0.122 |
Daddy | -0.121 |
Strait | -0.115 |
WN | -0.109 |
Token | Read |
Token ID | 5569 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
gradation | +0.370 |
================================= | +0.349 |
Templ | +0.332 |
�� | +0.323 |
clot | +0.312 |
Neg logit contributions | |
ilon | -0.322 |
Daddy | -0.317 |
earch | -0.316 |
Strait | -0.299 |
WN | -0.286 |
Token | more |
Token ID | 517 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ilon | +0.705 |
earch | +0.703 |
Daddy | +0.693 |
Strait | +0.658 |
ktop | +0.631 |
Neg logit contributions | |
gradation | -0.775 |
================================= | -0.737 |
Templ | -0.706 |
�� | -0.668 |
clot | -0.651 |
Token | by |
Token ID | 416 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ilon | +1.879 |
earch | +1.839 |
Daddy | +1.813 |
Strait | +1.743 |
ktop | +1.720 |
Neg logit contributions | |
gradation | -1.702 |
================================= | -1.671 |
Templ | -1.590 |
�� | -1.446 |
jar | -1.441 |
Token | Justin |
Token ID | 10799 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
ilon | +0.708 |
Daddy | +0.702 |
earch | +0.701 |
Strait | +0.661 |
ktop | +0.631 |
Neg logit contributions | |
gradation | -0.932 |
================================= | -0.893 |
Templ | -0.847 |
�� | -0.804 |
clot | -0.794 |
Token | R |
Token ID | 371 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ilon | +0.262 |
earch | +0.260 |
Daddy | +0.258 |
Strait | +0.247 |
ktop | +0.238 |
Neg logit contributions | |
gradation | -0.213 |
================================= | -0.201 |
Templ | -0.189 |
�� | -0.179 |
clot | -0.173 |
Token | aim |
Token ID | 1385 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ilon | +0.201 |
earch | +0.199 |
Daddy | +0.197 |
Strait | +0.183 |
wcsstore | +0.171 |
Neg logit contributions | |
gradation | -0.384 |
================================= | -0.368 |
Templ | -0.353 |
�� | -0.342 |
clot | -0.334 |
Token | ondo |
Token ID | 22311 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
gradation | +1.199 |
================================= | +1.132 |
Templ | +1.079 |
�� | +1.041 |
clot | +1.019 |
Neg logit contributions | |
ilon | -1.097 |
earch | -1.075 |
Daddy | -1.065 |
Strait | -1.017 |
WN | -0.965 |
Token | with |
Token ID | 351 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
ilon | +0.218 |
earch | +0.215 |
Daddy | +0.214 |
Strait | +0.202 |
WN | +0.191 |
Neg logit contributions | |
gradation | -0.292 |
================================= | -0.278 |
Templ | -0.266 |
�� | -0.256 |
clot | -0.249 |
Token | point |
Token ID | 966 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
gradation | +0.051 |
================================= | +0.049 |
Templ | +0.046 |
�� | +0.045 |
clot | +0.043 |
Neg logit contributions | |
ilon | -0.042 |
earch | -0.042 |
Daddy | -0.042 |
Strait | -0.039 |
WN | -0.037 |
Token | guard |
Token ID | 4860 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
gradation | +0.109 |
================================= | +0.102 |
Templ | +0.095 |
�� | +0.091 |
clot | +0.087 |
Neg logit contributions | |
ilon | -0.143 |
earch | -0.141 |
Daddy | -0.141 |
Strait | -0.135 |
WN | -0.130 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ilon | +0.272 |
earch | +0.269 |
Daddy | +0.266 |
Strait | +0.253 |
WN | +0.241 |
Neg logit contributions | |
gradation | -0.296 |
================================= | -0.281 |
Templ | -0.267 |
�� | -0.255 |
clot | -0.248 |
Token | o |
Token ID | 78 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
gradation | +0.145 |
================================= | +0.138 |
Templ | +0.131 |
�� | +0.127 |
clot | +0.123 |
Neg logit contributions | |
ilon | -0.111 |
earch | -0.110 |
Daddy | -0.109 |
Strait | -0.104 |
WN | -0.098 |
Token | U |
Token ID | 471 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ilon | +0.356 |
earch | +0.353 |
Daddy | +0.348 |
Strait | +0.331 |
wcsstore | +0.316 |
Neg logit contributions | |
gradation | -0.412 |
================================= | -0.392 |
Templ | -0.373 |
�� | -0.356 |
clot | -0.346 |
Token | dri |
Token ID | 7553 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ilon | +1.303 |
earch | +1.276 |
Daddy | +1.273 |
Strait | +1.195 |
wcsstore | +1.179 |
Neg logit contributions | |
gradation | -2.060 |
================================= | -1.989 |
Templ | -1.878 |
jar | -1.821 |
�� | -1.813 |
Token | h |
Token ID | 71 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ilon | +0.905 |
Daddy | +0.896 |
earch | +0.893 |
Strait | +0.855 |
wcsstore | +0.826 |
Neg logit contributions | |
gradation | -0.817 |
================================= | -0.772 |
Templ | -0.734 |
�� | -0.690 |
jar | -0.682 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ilon | +0.271 |
earch | +0.268 |
Daddy | +0.265 |
Strait | +0.252 |
WN | +0.239 |
Neg logit contributions | |
gradation | -0.330 |
================================= | -0.314 |
Templ | -0.298 |
�� | -0.287 |
clot | -0.279 |
Token | according |
Token ID | 1864 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ilon | +0.281 |
earch | +0.278 |
Daddy | +0.276 |
Strait | +0.262 |
WN | +0.248 |
Neg logit contributions | |
gradation | -0.330 |
================================= | -0.313 |
Templ | -0.298 |
�� | -0.286 |
clot | -0.278 |
Token | to |
Token ID | 284 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ilon | +0.170 |
earch | +0.168 |
Daddy | +0.167 |
Strait | +0.158 |
WN | +0.150 |
Neg logit contributions | |
gradation | -0.211 |
================================= | -0.201 |
Templ | -0.191 |
�� | -0.184 |
clot | -0.179 |
Token | birth |
Token ID | 4082 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
gradation | +0.359 |
================================= | +0.341 |
Templ | +0.321 |
�� | +0.309 |
clot | +0.298 |
Neg logit contributions | |
ilon | -0.330 |
earch | -0.325 |
Daddy | -0.323 |
Strait | -0.308 |
WN | -0.293 |
Token | rate |
Token ID | 2494 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ilon | +0.377 |
earch | +0.372 |
Daddy | +0.370 |
Strait | +0.355 |
WN | +0.340 |
Neg logit contributions | |
gradation | -0.301 |
================================= | -0.282 |
Templ | -0.265 |
�� | -0.253 |
clot | -0.244 |
Token | , |
Token ID | 11 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
gradation | +0.297 |
================================= | +0.281 |
Templ | +0.268 |
�� | +0.258 |
clot | +0.251 |
Neg logit contributions | |
ilon | -0.231 |
earch | -0.227 |
Daddy | -0.226 |
Strait | -0.214 |
WN | -0.203 |
Token | America |
Token ID | 2253 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ilon | +0.529 |
earch | +0.526 |
Daddy | +0.522 |
Strait | +0.494 |
wcsstore | +0.479 |
Neg logit contributions | |
gradation | -0.539 |
================================= | -0.510 |
Templ | -0.482 |
�� | -0.466 |
clot | -0.452 |
Token | needs |
Token ID | 2476 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
ilon | +0.286 |
earch | +0.284 |
Daddy | +0.280 |
Strait | +0.267 |
WN | +0.253 |
Neg logit contributions | |
gradation | -0.344 |
================================= | -0.328 |
Templ | -0.312 |
�� | -0.299 |
clot | -0.291 |
Token | future |
Token ID | 2003 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
gradation | +0.647 |
================================= | +0.618 |
Templ | +0.589 |
�� | +0.564 |
clot | +0.548 |
Neg logit contributions | |
ilon | -0.498 |
earch | -0.490 |
Daddy | -0.487 |
Strait | -0.460 |
WN | -0.438 |
Token | migrants |
Token ID | 12783 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ilon | +1.562 |
earch | +1.550 |
Daddy | +1.527 |
Strait | +1.465 |
wcsstore | +1.400 |
Neg logit contributions | |
gradation | -1.810 |
================================= | -1.717 |
Templ | -1.641 |
�� | -1.586 |
clot | -1.559 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
gradation | +0.827 |
================================= | +0.771 |
Templ | +0.739 |
�� | +0.718 |
jar | +0.692 |
Neg logit contributions | |
ilon | -0.658 |
earch | -0.651 |
Daddy | -0.645 |
Strait | -0.613 |
Hus | -0.578 |
Token | ways |
Token ID | 2842 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
gradation | +0.129 |
================================= | +0.122 |
Templ | +0.116 |
�� | +0.111 |
clot | +0.108 |
Neg logit contributions | |
ilon | -0.115 |
earch | -0.113 |
Daddy | -0.112 |
Strait | -0.107 |
WN | -0.102 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
ilon | +0.470 |
earch | +0.468 |
Daddy | +0.463 |
Strait | +0.439 |
ktop | +0.422 |
Neg logit contributions | |
gradation | -0.566 |
================================= | -0.540 |
Templ | -0.512 |
�� | -0.492 |
clot | -0.480 |
Token | looms |
Token ID | 46234 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
gradation | +0.550 |
================================= | +0.523 |
Templ | +0.500 |
�� | +0.483 |
clot | +0.468 |
Neg logit contributions | |
ilon | -0.379 |
earch | -0.373 |
Daddy | -0.372 |
Strait | -0.349 |
WN | -0.331 |
Token | 2000 |
Token ID | 4751 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ilon | +0.248 |
earch | +0.246 |
Daddy | +0.244 |
Strait | +0.234 |
ktop | +0.225 |
Neg logit contributions | |
gradation | -0.198 |
================================= | -0.186 |
Templ | -0.175 |
�� | -0.165 |
clot | -0.160 |
Token | ), |
Token ID | 828 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
earch | +1.008 |
ilon | +0.999 |
Daddy | +0.987 |
Strait | +0.939 |
ktop | +0.907 |
Neg logit contributions | |
gradation | -0.999 |
================================= | -0.940 |
Templ | -0.891 |
�� | -0.844 |
jar | -0.834 |
Token | my |
Token ID | 616 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ilon | +0.530 |
earch | +0.524 |
Daddy | +0.517 |
Strait | +0.491 |
ktop | +0.471 |
Neg logit contributions | |
gradation | -0.631 |
================================= | -0.601 |
Templ | -0.574 |
�� | -0.544 |
clot | -0.533 |
Token | biography |
Token ID | 26444 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
earch | +0.825 |
ilon | +0.820 |
Daddy | +0.811 |
Strait | +0.780 |
ktop | +0.755 |
Neg logit contributions | |
gradation | -0.756 |
================================= | -0.714 |
Templ | -0.673 |
�� | -0.636 |
clot | -0.629 |
Token | of |
Token ID | 286 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
ilon | +0.541 |
earch | +0.536 |
Daddy | +0.532 |
Strait | +0.506 |
ktop | +0.485 |
Neg logit contributions | |
gradation | -0.588 |
================================= | -0.560 |
Templ | -0.534 |
�� | -0.508 |
clot | -0.494 |
Token | the |
Token ID | 262 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ilon | +0.392 |
earch | +0.388 |
Daddy | +0.384 |
Strait | +0.364 |
ktop | +0.348 |
Neg logit contributions | |
gradation | -0.499 |
================================= | -0.474 |
Templ | -0.453 |
�� | -0.435 |
jar | -0.424 |
Token | great |
Token ID | 1049 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
ilon | +1.570 |
earch | +1.559 |
Daddy | +1.554 |
Strait | +1.467 |
ktop | +1.461 |
Neg logit contributions | |
gradation | -1.764 |
================================= | -1.697 |
Templ | -1.597 |
�� | -1.514 |
clot | -1.494 |
Token | libertarian |
Token ID | 19466 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
ilon | +0.607 |
earch | +0.602 |
Daddy | +0.592 |
Strait | +0.570 |
ktop | +0.550 |
Neg logit contributions | |
gradation | -0.560 |
================================= | -0.532 |
Templ | -0.497 |
�� | -0.476 |
clot | -0.466 |
Token | thinker |
Token ID | 45206 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
ilon | +0.412 |
earch | +0.409 |
Daddy | +0.403 |
Strait | +0.386 |
WN | +0.368 |
Neg logit contributions | |
gradation | -0.441 |
================================= | -0.420 |
Templ | -0.395 |
�� | -0.377 |
clot | -0.369 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ilon | +0.499 |
earch | +0.499 |
Daddy | +0.492 |
Strait | +0.468 |
ktop | +0.452 |
Neg logit contributions | |
gradation | -0.597 |
================================= | -0.572 |
Templ | -0.542 |
�� | -0.516 |
jar | -0.506 |
Token | here |
Token ID | 994 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
gradation | +0.169 |
================================= | +0.161 |
Templ | +0.153 |
�� | +0.149 |
clot | +0.143 |
Neg logit contributions | |
ilon | -0.129 |
earch | -0.127 |
Daddy | -0.126 |
Strait | -0.120 |
WN | -0.113 |
Token | by |
Token ID | 416 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ilon | +1.530 |
earch | +1.496 |
Daddy | +1.487 |
Strait | +1.412 |
ktop | +1.356 |
Neg logit contributions | |
gradation | -1.453 |
================================= | -1.398 |
Templ | -1.359 |
�� | -1.241 |
clot | -1.230 |
Token | Scott |
Token ID | 4746 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ilon | +0.864 |
Daddy | +0.860 |
earch | +0.857 |
Strait | +0.813 |
ktop | +0.780 |
Neg logit contributions | |
gradation | -0.899 |
================================= | -0.852 |
Templ | -0.810 |
�� | -0.767 |
clot | -0.751 |
Token | Ric |
Token ID | 15868 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
gradation | +0.193 |
================================= | +0.183 |
Templ | +0.174 |
�� | +0.168 |
clot | +0.163 |
Neg logit contributions | |
ilon | -0.165 |
earch | -0.163 |
Daddy | -0.162 |
Strait | -0.154 |
WN | -0.146 |
Token | her |
Token ID | 372 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ilon | +0.282 |
earch | +0.275 |
Daddy | +0.273 |
Strait | +0.249 |
ktop | +0.228 |
Neg logit contributions | |
gradation | -0.796 |
================================= | -0.766 |
Templ | -0.739 |
�� | -0.714 |
jar | -0.707 |
Token | t |
Token ID | 83 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ilon | +0.232 |
earch | +0.230 |
Daddy | +0.227 |
Strait | +0.216 |
ktop | +0.204 |
Neg logit contributions | |
gradation | -0.298 |
================================= | -0.283 |
Templ | -0.270 |
�� | -0.259 |
jar | -0.252 |
Token | and |
Token ID | 290 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
ilon | +0.665 |
earch | +0.661 |
Daddy | +0.648 |
Strait | +0.615 |
ktop | +0.593 |
Neg logit contributions | |
gradation | -0.785 |
================================= | -0.750 |
Templ | -0.710 |
�� | -0.674 |
clot | -0.658 |
Token | David |
Token ID | 3271 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ilon | +1.811 |
earch | +1.804 |
Daddy | +1.795 |
Strait | +1.701 |
wcsstore | +1.677 |
Neg logit contributions | |
gradation | -1.495 |
================================= | -1.426 |
Templ | -1.346 |
jar | -1.242 |
�� | -1.234 |
Token | Gordon |
Token ID | 11646 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ilon | +0.091 |
earch | +0.090 |
Daddy | +0.090 |
Strait | +0.086 |
ktop | +0.082 |
Neg logit contributions | |
gradation | -0.074 |
================================= | -0.069 |
Templ | -0.065 |
�� | -0.062 |
clot | -0.059 |
Token | ( |
Token ID | 357 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
ilon | +1.933 |
Daddy | +1.909 |
earch | +1.904 |
ktop | +1.800 |
Strait | +1.794 |
Neg logit contributions | |
gradation | -1.798 |
================================= | -1.765 |
Templ | -1.673 |
jar | -1.508 |
clot | -1.507 |
Token | IS |
Token ID | 1797 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
ilon | +0.303 |
earch | +0.299 |
Daddy | +0.295 |
Strait | +0.279 |
ktop | +0.261 |
Neg logit contributions | |
gradation | -0.568 |
================================= | -0.544 |
Templ | -0.522 |
�� | -0.505 |
jar | -0.493 |
Token | I |
Token ID | 40 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ilon | +0.349 |
earch | +0.346 |
Daddy | +0.343 |
Strait | +0.326 |
ktop | +0.307 |
Neg logit contributions | |
gradation | -0.489 |
================================= | -0.466 |
Templ | -0.443 |
�� | -0.427 |
jar | -0.416 |
Token | that |
Token ID | 326 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
ilon | +0.085 |
earch | +0.084 |
Daddy | +0.083 |
Strait | +0.079 |
WN | +0.075 |
Neg logit contributions | |
gradation | -0.106 |
================================= | -0.100 |
Templ | -0.096 |
�� | -0.092 |
clot | -0.089 |
Token | Georg |
Token ID | 6850 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ilon | +0.002 |
earch | +0.002 |
Daddy | +0.002 |
Strait | +0.002 |
WN | +0.002 |
Neg logit contributions | |
gradation | -0.002 |
================================= | -0.002 |
Templ | -0.002 |
�� | -0.002 |
clot | -0.002 |
Token | es |
Token ID | 274 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
gradation | +0.402 |
================================= | +0.380 |
Templ | +0.359 |
�� | +0.347 |
clot | +0.335 |
Neg logit contributions | |
ilon | -0.374 |
earch | -0.370 |
Daddy | -0.366 |
Strait | -0.350 |
WN | -0.332 |
Token | Mé |
Token ID | 43579 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
gradation | +0.527 |
================================= | +0.496 |
Templ | +0.470 |
�� | +0.457 |
clot | +0.439 |
Neg logit contributions | |
ilon | -0.473 |
earch | -0.467 |
Daddy | -0.463 |
Strait | -0.444 |
ktop | -0.421 |
Token | li |
Token ID | 4528 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
ilon | +0.173 |
earch | +0.172 |
Daddy | +0.170 |
Strait | +0.160 |
WN | +0.150 |
Neg logit contributions | |
gradation | -0.279 |
================================= | -0.266 |
Templ | -0.255 |
�� | -0.247 |
clot | -0.240 |
Token | è |
Token ID | 14064 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ilon | +0.141 |
earch | +0.137 |
Daddy | +0.135 |
Strait | +0.122 |
ktop | +0.108 |
Neg logit contributions | |
gradation | -0.488 |
================================= | -0.471 |
Templ | -0.454 |
�� | -0.443 |
jar | -0.435 |
Token | s |
Token ID | 82 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
earch | +1.530 |
ilon | +1.494 |
Daddy | +1.474 |
Strait | +1.386 |
ktop | +1.353 |
Neg logit contributions | |
gradation | -1.756 |
================================= | -1.697 |
Templ | -1.594 |
jar | -1.530 |
�� | -1.506 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
gradation | +0.033 |
================================= | +0.031 |
Templ | +0.030 |
�� | +0.029 |
clot | +0.028 |
Neg logit contributions | |
ilon | -0.027 |
earch | -0.027 |
Daddy | -0.027 |
Strait | -0.025 |
WN | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
ilon | +0.130 |
earch | +0.129 |
Daddy | +0.128 |
Strait | +0.121 |
WN | +0.115 |
Neg logit contributions | |
gradation | -0.167 |
================================= | -0.159 |
Templ | -0.152 |
�� | -0.146 |
clot | -0.142 |
Token | early |
Token ID | 1903 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ilon | +0.237 |
earch | +0.234 |
Daddy | +0.232 |
Strait | +0.221 |
WN | +0.209 |
Neg logit contributions | |
gradation | -0.280 |
================================= | -0.266 |
Templ | -0.253 |
�� | -0.243 |
clot | -0.236 |
Token | French |
Token ID | 4141 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
gradation | +0.014 |
================================= | +0.014 |
Templ | +0.013 |
�� | +0.013 |
clot | +0.012 |
Neg logit contributions | |
ilon | -0.013 |
earch | -0.012 |
Daddy | -0.012 |
Strait | -0.012 |
WN | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ilon | +0.456 |
earch | +0.454 |
Daddy | +0.450 |
Strait | +0.428 |
ktop | +0.409 |
Neg logit contributions | |
gradation | -0.499 |
================================= | -0.477 |
Templ | -0.450 |
�� | -0.431 |
clot | -0.418 |
Token | Carey |
Token ID | 31612 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ilon | +0.230 |
earch | +0.227 |
Daddy | +0.224 |
Strait | +0.207 |
ktop | +0.195 |
Neg logit contributions | |
gradation | -0.448 |
================================= | -0.431 |
Templ | -0.414 |
�� | -0.400 |
clot | -0.390 |
Token | , |
Token ID | 11 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
earch | +0.887 |
ilon | +0.886 |
Daddy | +0.882 |
Strait | +0.828 |
ktop | +0.800 |
Neg logit contributions | |
gradation | -1.030 |
================================= | -0.987 |
Templ | -0.943 |
�� | -0.877 |
jar | -0.872 |
Token | a |
Token ID | 257 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
gradation | +0.600 |
================================= | +0.569 |
Templ | +0.540 |
�� | +0.525 |
clot | +0.510 |
Neg logit contributions | |
ilon | -0.449 |
earch | -0.442 |
Daddy | -0.438 |
Strait | -0.415 |
LCS | -0.391 |
Token | Fore |
Token ID | 4558 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
gradation | +0.475 |
================================= | +0.456 |
Templ | +0.437 |
�� | +0.429 |
clot | +0.418 |
Neg logit contributions | |
ilon | -0.191 |
earch | -0.188 |
Daddy | -0.185 |
Strait | -0.171 |
WN | -0.157 |
Token | word |
Token ID | 4775 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ilon | +0.392 |
earch | +0.383 |
Daddy | +0.381 |
Strait | +0.362 |
ktop | +0.343 |
Neg logit contributions | |
gradation | -0.547 |
================================= | -0.519 |
Templ | -0.496 |
�� | -0.479 |
clot | -0.468 |
Token | by |
Token ID | 416 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ilon | +1.651 |
earch | +1.644 |
Daddy | +1.621 |
Strait | +1.536 |
ktop | +1.506 |
Neg logit contributions | |
gradation | -1.588 |
================================= | -1.523 |
Templ | -1.441 |
�� | -1.363 |
clot | -1.329 |
Token | Patrick |
Token ID | 9925 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
Daddy | +0.997 |
earch | +0.989 |
ilon | +0.985 |
Strait | +0.910 |
wcsstore | +0.886 |
Neg logit contributions | |
gradation | -1.498 |
================================= | -1.448 |
Templ | -1.390 |
�� | -1.310 |
jar | -1.298 |
Token | J |
Token ID | 449 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
gradation | +0.037 |
================================= | +0.035 |
Templ | +0.034 |
�� | +0.032 |
clot | +0.031 |
Neg logit contributions | |
ilon | -0.035 |
earch | -0.034 |
Daddy | -0.034 |
Strait | -0.033 |
WN | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ilon | +0.098 |
earch | +0.096 |
Daddy | +0.096 |
Strait | +0.091 |
ktop | +0.087 |
Neg logit contributions | |
gradation | -0.110 |
================================= | -0.104 |
Templ | -0.099 |
�� | -0.095 |
clot | -0.092 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ilon | +0.308 |
earch | +0.306 |
Daddy | +0.302 |
Strait | +0.290 |
ktop | +0.280 |
Neg logit contributions | |
gradation | -0.247 |
================================= | -0.232 |
Templ | -0.218 |
�� | -0.206 |
jar | -0.199 |
Token | note |
Token ID | 3465 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ilon | +0.087 |
earch | +0.086 |
Daddy | +0.085 |
Strait | +0.081 |
ktop | +0.076 |
Neg logit contributions | |
gradation | -0.133 |
================================= | -0.127 |
Templ | -0.122 |
�� | -0.118 |
clot | -0.115 |
Token | that |
Token ID | 326 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ilon | +0.073 |
earch | +0.072 |
Daddy | +0.071 |
Strait | +0.068 |
ktop | +0.064 |
Neg logit contributions | |
gradation | -0.093 |
================================= | -0.088 |
Templ | -0.084 |
�� | -0.081 |
clot | -0.078 |
Token | my |
Token ID | 616 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
ilon | +0.123 |
earch | +0.122 |
Daddy | +0.121 |
Strait | +0.115 |
ktop | +0.109 |
Neg logit contributions | |
gradation | -0.154 |
================================= | -0.146 |
Templ | -0.139 |
�� | -0.134 |
clot | -0.130 |
Token | tweets |
Token ID | 12665 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
gradation | +0.407 |
================================= | +0.383 |
Templ | +0.366 |
�� | +0.353 |
clot | +0.342 |
Neg logit contributions | |
ilon | -0.329 |
earch | -0.325 |
Daddy | -0.322 |
Strait | -0.306 |
WN | -0.290 |
Token | are |
Token ID | 389 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ilon | +0.292 |
earch | +0.289 |
Daddy | +0.287 |
Strait | +0.273 |
WN | +0.258 |
Neg logit contributions | |
gradation | -0.334 |
================================= | -0.317 |
Templ | -0.301 |
�� | -0.289 |
clot | -0.281 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
gradation | +0.123 |
================================= | +0.115 |
Templ | +0.108 |
�� | +0.104 |
clot | +0.100 |
Neg logit contributions | |
ilon | -0.150 |
earch | -0.148 |
Daddy | -0.147 |
Strait | -0.141 |
WN | -0.135 |
Token | deliberately |
Token ID | 14593 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
earch | +1.433 |
ilon | +1.422 |
Daddy | +1.388 |
Strait | +1.314 |
ktop | +1.297 |
Neg logit contributions | |
gradation | -1.813 |
================================= | -1.749 |
Templ | -1.651 |
�� | -1.591 |
clot | -1.546 |
Token | provocative |
Token ID | 28695 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ilon | +0.386 |
earch | +0.379 |
Daddy | +0.375 |
Strait | +0.350 |
ktop | +0.322 |
Neg logit contributions | |
gradation | -0.797 |
================================= | -0.772 |
Templ | -0.740 |
�� | -0.711 |
clot | -0.701 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ilon | +0.811 |
earch | +0.809 |
Daddy | +0.794 |
Strait | +0.752 |
WN | +0.721 |
Neg logit contributions | |
gradation | -0.920 |
================================= | -0.879 |
Templ | -0.830 |
�� | -0.789 |
jar | -0.782 |
Token | often |
Token ID | 1690 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ilon | +0.876 |
earch | +0.869 |
Daddy | +0.861 |
Strait | +0.829 |
WN | +0.796 |
Neg logit contributions | |
gradation | -0.623 |
================================= | -0.584 |
Templ | -0.542 |
�� | -0.514 |
clot | -0.500 |
Token | made |
Token ID | 925 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ilon | +1.148 |
earch | +1.142 |
Daddy | +1.128 |
Strait | +1.086 |
ktop | +1.037 |
Neg logit contributions | |
gradation | -1.009 |
================================= | -0.977 |
Templ | -0.910 |
�� | -0.852 |
clot | -0.842 |
Token | as |
Token ID | 355 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
gradation | +0.220 |
================================= | +0.209 |
Templ | +0.199 |
�� | +0.192 |
clot | +0.186 |
Neg logit contributions | |
ilon | -0.169 |
earch | -0.167 |
Daddy | -0.165 |
Strait | -0.157 |
WN | -0.148 |
Token | Goldman |
Token ID | 18740 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
gradation | +0.316 |
================================= | +0.299 |
Templ | +0.283 |
�� | +0.273 |
clot | +0.264 |
Neg logit contributions | |
ilon | -0.280 |
earch | -0.276 |
Daddy | -0.274 |
Strait | -0.261 |
WN | -0.248 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
gradation | +0.151 |
================================= | +0.143 |
Templ | +0.136 |
�� | +0.131 |
clot | +0.127 |
Neg logit contributions | |
ilon | -0.127 |
earch | -0.126 |
Daddy | -0.125 |
Strait | -0.119 |
WN | -0.113 |
Token | to |
Token ID | 284 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
gradation | +0.150 |
================================= | +0.142 |
Templ | +0.135 |
�� | +0.131 |
clot | +0.126 |
Neg logit contributions | |
ilon | -0.120 |
earch | -0.118 |
Daddy | -0.117 |
Strait | -0.111 |
WN | -0.105 |
Token | j |
Token ID | 474 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ilon | +0.031 |
earch | +0.030 |
Daddy | +0.030 |
Strait | +0.029 |
WN | +0.027 |
Neg logit contributions | |
gradation | -0.032 |
================================= | -0.030 |
Templ | -0.028 |
�� | -0.027 |
clot | -0.026 |
Token | ett |
Token ID | 3087 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ilon | +0.403 |
earch | +0.398 |
Daddy | +0.396 |
Strait | +0.376 |
WN | +0.358 |
Neg logit contributions | |
gradation | -0.462 |
================================= | -0.439 |
Templ | -0.416 |
�� | -0.400 |
clot | -0.391 |
Token | ison |
Token ID | 1653 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Daddy | +1.092 |
ilon | +1.084 |
earch | +1.074 |
Strait | +1.018 |
ktop | +0.963 |
Neg logit contributions | |
gradation | -2.001 |
================================= | -1.929 |
Templ | -1.817 |
clot | -1.764 |
jar | -1.741 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
gradation | +0.196 |
================================= | +0.186 |
Templ | +0.177 |
�� | +0.170 |
clot | +0.165 |
Neg logit contributions | |
ilon | -0.159 |
earch | -0.157 |
Daddy | -0.156 |
Strait | -0.148 |
WN | -0.140 |
Token | billions |
Token ID | 13188 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ilon | +0.125 |
earch | +0.123 |
Daddy | +0.122 |
Strait | +0.116 |
WN | +0.110 |
Neg logit contributions | |
gradation | -0.163 |
================================= | -0.155 |
Templ | -0.148 |
�� | -0.142 |
clot | -0.138 |
Token | in |
Token ID | 287 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
ilon | +0.186 |
earch | +0.184 |
Daddy | +0.182 |
Strait | +0.173 |
WN | +0.164 |
Neg logit contributions | |
gradation | -0.218 |
================================= | -0.207 |
Templ | -0.197 |
�� | -0.189 |
clot | -0.184 |
Token | sub |
Token ID | 850 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ilon | +0.040 |
earch | +0.039 |
Daddy | +0.039 |
Strait | +0.037 |
WN | +0.035 |
Neg logit contributions | |
gradation | -0.048 |
================================= | -0.046 |
Templ | -0.043 |
�� | -0.042 |
clot | -0.041 |
Token | House |
Token ID | 18102 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
gradation | +0.228 |
================================= | +0.217 |
Templ | +0.206 |
�� | +0.199 |
clot | +0.193 |
Neg logit contributions | |
ilon | -0.182 |
earch | -0.180 |
Daddy | -0.179 |
Strait | -0.169 |
WN | -0.160 |
Token | committee |
Token ID | 5583 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ilon | +0.117 |
earch | +0.116 |
Daddy | +0.115 |
Strait | +0.110 |
WN | +0.105 |
Neg logit contributions | |
gradation | -0.117 |
================================= | -0.111 |
Templ | -0.105 |
�� | -0.101 |
clot | -0.097 |
Token | believes |
Token ID | 5804 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
gradation | +0.389 |
================================= | +0.369 |
Templ | +0.351 |
�� | +0.336 |
clot | +0.327 |
Neg logit contributions | |
ilon | -0.323 |
earch | -0.320 |
Daddy | -0.317 |
Strait | -0.302 |
WN | -0.285 |
Token | it |
Token ID | 340 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
gradation | +0.551 |
================================= | +0.526 |
Templ | +0.501 |
�� | +0.482 |
clot | +0.466 |
Neg logit contributions | |
ilon | -0.415 |
earch | -0.412 |
Daddy | -0.406 |
Strait | -0.387 |
WN | -0.364 |
Token | has |
Token ID | 468 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gradation | +0.270 |
================================= | +0.257 |
Templ | +0.244 |
�� | +0.235 |
clot | +0.227 |
Neg logit contributions | |
ilon | -0.229 |
earch | -0.226 |
Daddy | -0.225 |
Strait | -0.215 |
WN | -0.202 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
gradation | +1.048 |
================================= | +0.988 |
Templ | +0.927 |
�� | +0.901 |
jar | +0.854 |
Neg logit contributions | |
ilon | -1.060 |
earch | -1.058 |
Daddy | -1.049 |
Strait | -1.011 |
Hus | -0.960 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ilon | +1.461 |
earch | +1.452 |
Daddy | +1.443 |
Strait | +1.389 |
ktop | +1.343 |
Neg logit contributions | |
gradation | -1.569 |
================================= | -1.520 |
Templ | -1.450 |
clot | -1.409 |
�� | -1.366 |
Token | requested |
Token ID | 9167 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
gradation | +1.190 |
================================= | +1.127 |
Templ | +1.062 |
�� | +1.038 |
clot | +0.992 |
Neg logit contributions | |
ilon | -0.875 |
Daddy | -0.861 |
earch | -0.849 |
Strait | -0.814 |
WN | -0.769 |
Token | putting |
Token ID | 5137 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
gradation | +0.599 |
================================= | +0.564 |
Templ | +0.533 |
�� | +0.518 |
jar | +0.496 |
Neg logit contributions | |
ilon | -0.509 |
earch | -0.501 |
Daddy | -0.499 |
Strait | -0.475 |
WN | -0.447 |
Token | ally |
Token ID | 12525 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilon | +0.338 |
earch | +0.336 |
Daddy | +0.334 |
Strait | +0.316 |
ktop | +0.302 |
Neg logit contributions | |
gradation | -0.364 |
================================= | -0.344 |
Templ | -0.329 |
�� | -0.313 |
clot | -0.307 |
Token | in |
Token ID | 287 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
gradation | +0.162 |
================================= | +0.155 |
Templ | +0.147 |
�� | +0.142 |
clot | +0.138 |
Neg logit contributions | |
ilon | -0.122 |
earch | -0.120 |
Daddy | -0.120 |
Strait | -0.114 |
WN | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ilon | +0.098 |
earch | +0.096 |
Daddy | +0.096 |
Strait | +0.091 |
ktop | +0.087 |
Neg logit contributions | |
gradation | -0.110 |
================================= | -0.104 |
Templ | -0.099 |
�� | -0.095 |
clot | -0.092 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ilon | +0.308 |
earch | +0.306 |
Daddy | +0.302 |
Strait | +0.290 |
ktop | +0.280 |
Neg logit contributions | |
gradation | -0.247 |
================================= | -0.232 |
Templ | -0.218 |
�� | -0.206 |
jar | -0.199 |
Token | , |
Token ID | 11 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
earch | +0.821 |
ilon | +0.820 |
Daddy | +0.798 |
Strait | +0.761 |
wcsstore | +0.738 |
Neg logit contributions | |
gradation | -0.951 |
================================= | -0.907 |
Templ | -0.870 |
jar | -0.809 |
�� | -0.808 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ilon | +0.630 |
earch | +0.623 |
Daddy | +0.616 |
Strait | +0.590 |
ktop | +0.562 |
Neg logit contributions | |
gradation | -0.749 |
================================= | -0.715 |
Templ | -0.681 |
�� | -0.646 |
clot | -0.631 |
Token | critical |
Token ID | 4688 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ilon | +0.574 |
earch | +0.562 |
Daddy | +0.561 |
Strait | +0.528 |
ktop | +0.498 |
Neg logit contributions | |
gradation | -0.888 |
================================= | -0.849 |
Templ | -0.814 |
�� | -0.779 |
clot | -0.767 |
Token | essays |
Token ID | 27126 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ilon | +0.219 |
earch | +0.216 |
Daddy | +0.214 |
Strait | +0.202 |
ktop | +0.193 |
Neg logit contributions | |
gradation | -0.283 |
================================= | -0.270 |
Templ | -0.257 |
�� | -0.247 |
clot | -0.241 |
Token | by |
Token ID | 416 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ilon | +1.530 |
earch | +1.496 |
Daddy | +1.487 |
Strait | +1.412 |
ktop | +1.356 |
Neg logit contributions | |
gradation | -1.453 |
================================= | -1.398 |
Templ | -1.359 |
�� | -1.241 |
clot | -1.230 |
Token | Scott |
Token ID | 4746 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ilon | +0.864 |
Daddy | +0.860 |
earch | +0.857 |
Strait | +0.813 |
ktop | +0.780 |
Neg logit contributions | |
gradation | -0.899 |
================================= | -0.852 |
Templ | -0.810 |
�� | -0.767 |
clot | -0.751 |
Token | Ric |
Token ID | 15868 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
gradation | +0.193 |
================================= | +0.183 |
Templ | +0.174 |
�� | +0.168 |
clot | +0.163 |
Neg logit contributions | |
ilon | -0.165 |
earch | -0.163 |
Daddy | -0.162 |
Strait | -0.154 |
WN | -0.146 |
Token | her |
Token ID | 372 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ilon | +0.282 |
earch | +0.275 |
Daddy | +0.273 |
Strait | +0.249 |
ktop | +0.228 |
Neg logit contributions | |
gradation | -0.796 |
================================= | -0.766 |
Templ | -0.739 |
�� | -0.714 |
jar | -0.707 |
Token | t |
Token ID | 83 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ilon | +0.232 |
earch | +0.230 |
Daddy | +0.227 |
Strait | +0.216 |
ktop | +0.204 |
Neg logit contributions | |
gradation | -0.298 |
================================= | -0.283 |
Templ | -0.270 |
�� | -0.259 |
jar | -0.252 |
Token | House |
Token ID | 18102 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
gradation | +0.154 |
================================= | +0.147 |
Templ | +0.140 |
�� | +0.135 |
clot | +0.131 |
Neg logit contributions | |
ilon | -0.122 |
earch | -0.121 |
Daddy | -0.120 |
Strait | -0.114 |
WN | -0.108 |
Token | committee |
Token ID | 5583 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
ilon | +0.142 |
earch | +0.140 |
Daddy | +0.139 |
Strait | +0.133 |
WN | +0.126 |
Neg logit contributions | |
gradation | -0.143 |
================================= | -0.135 |
Templ | -0.128 |
�� | -0.123 |
clot | -0.119 |
Token | believes |
Token ID | 5804 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
gradation | +0.527 |
================================= | +0.499 |
Templ | +0.477 |
�� | +0.454 |
jar | +0.442 |
Neg logit contributions | |
ilon | -0.431 |
earch | -0.429 |
Daddy | -0.424 |
Strait | -0.404 |
WN | -0.380 |
Token | it |
Token ID | 340 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
gradation | +0.385 |
================================= | +0.366 |
Templ | +0.350 |
�� | +0.336 |
clot | +0.326 |
Neg logit contributions | |
ilon | -0.296 |
earch | -0.294 |
Daddy | -0.290 |
Strait | -0.277 |
WN | -0.261 |
Token | has |
Token ID | 468 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
gradation | +0.227 |
================================= | +0.216 |
Templ | +0.205 |
�� | +0.198 |
clot | +0.191 |
Neg logit contributions | |
ilon | -0.188 |
earch | -0.186 |
Daddy | -0.185 |
Strait | -0.177 |
WN | -0.166 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
gradation | +0.886 |
================================= | +0.831 |
Templ | +0.782 |
�� | +0.759 |
jar | +0.722 |
Neg logit contributions | |
ilon | -0.898 |
earch | -0.896 |
Daddy | -0.887 |
Strait | -0.855 |
Hus | -0.811 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ilon | +1.419 |
earch | +1.408 |
Daddy | +1.399 |
Strait | +1.340 |
ktop | +1.303 |
Neg logit contributions | |
gradation | -1.505 |
================================= | -1.470 |
Templ | -1.395 |
clot | -1.352 |
�� | -1.314 |
Token | requested |
Token ID | 9167 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
gradation | +1.331 |
================================= | +1.260 |
Templ | +1.188 |
�� | +1.167 |
clot | +1.108 |
Neg logit contributions | |
ilon | -0.991 |
Daddy | -0.983 |
earch | -0.959 |
Strait | -0.924 |
WN | -0.876 |
Token | putting |
Token ID | 5137 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
gradation | +0.719 |
================================= | +0.677 |
Templ | +0.641 |
�� | +0.623 |
jar | +0.597 |
Neg logit contributions | |
ilon | -0.586 |
earch | -0.578 |
Daddy | -0.577 |
Strait | -0.548 |
LCS | -0.516 |
Token | ally |
Token ID | 12525 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ilon | +0.311 |
earch | +0.308 |
Daddy | +0.306 |
Strait | +0.290 |
ktop | +0.277 |
Neg logit contributions | |
gradation | -0.334 |
================================= | -0.316 |
Templ | -0.302 |
�� | -0.288 |
clot | -0.282 |
Token | in |
Token ID | 287 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
gradation | +0.101 |
================================= | +0.097 |
Templ | +0.092 |
�� | +0.089 |
clot | +0.086 |
Neg logit contributions | |
ilon | -0.073 |
earch | -0.072 |
Daddy | -0.072 |
Strait | -0.068 |
WN | -0.064 |
Token | Trump |
Token ID | 1301 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
gradation | +0.377 |
================================= | +0.357 |
Templ | +0.338 |
�� | +0.328 |
clot | +0.316 |
Neg logit contributions | |
ilon | -0.319 |
Daddy | -0.314 |
earch | -0.314 |
Strait | -0.297 |
WN | -0.282 |
Token | urges |
Token ID | 28804 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
gradation | +0.476 |
================================= | +0.452 |
Templ | +0.428 |
�� | +0.414 |
clot | +0.398 |
Neg logit contributions | |
ilon | -0.416 |
Daddy | -0.410 |
earch | -0.410 |
Strait | -0.389 |
WN | -0.370 |
Token | North |
Token ID | 2258 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
gradation | +0.672 |
================================= | +0.638 |
Templ | +0.605 |
�� | +0.584 |
jar | +0.564 |
Neg logit contributions | |
ilon | -0.543 |
earch | -0.535 |
Daddy | -0.533 |
Strait | -0.509 |
WN | -0.479 |
Token | Korea |
Token ID | 4969 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
gradation | +0.608 |
================================= | +0.572 |
Templ | +0.544 |
�� | +0.521 |
clot | +0.502 |
Neg logit contributions | |
ilon | -0.614 |
earch | -0.605 |
Daddy | -0.605 |
Strait | -0.575 |
LCS | -0.549 |
Token | to |
Token ID | 284 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
gradation | +0.074 |
================================= | +0.070 |
Templ | +0.067 |
�� | +0.064 |
clot | +0.062 |
Neg logit contributions | |
ilon | -0.058 |
earch | -0.057 |
Daddy | -0.057 |
Strait | -0.054 |
WN | -0.051 |
Token | den |
Token ID | 2853 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
gradation | +0.036 |
================================= | +0.035 |
Templ | +0.033 |
�� | +0.032 |
clot | +0.031 |
Neg logit contributions | |
ilon | -0.030 |
earch | -0.029 |
Daddy | -0.029 |
Strait | -0.027 |
WN | -0.026 |
Token | uclear |
Token ID | 4016 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ilon | +1.187 |
earch | +1.159 |
Daddy | +1.157 |
Strait | +1.091 |
wcsstore | +1.036 |
Neg logit contributions | |
gradation | -1.735 |
================================= | -1.675 |
Templ | -1.594 |
clot | -1.523 |
jar | -1.521 |
Token | ize |
Token ID | 1096 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ilon | +0.061 |
earch | +0.060 |
Daddy | +0.059 |
Strait | +0.056 |
WN | +0.052 |
Neg logit contributions | |
gradation | -0.102 |
================================= | -0.097 |
Templ | -0.093 |
�� | -0.090 |
clot | -0.088 |
Token | ahead |
Token ID | 4058 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
gradation | +0.576 |
================================= | +0.541 |
Templ | +0.519 |
�� | +0.503 |
clot | +0.487 |
Neg logit contributions | |
ilon | -0.420 |
earch | -0.413 |
Daddy | -0.412 |
Strait | -0.394 |
WN | -0.371 |
Token | of |
Token ID | 286 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
gradation | +0.158 |
================================= | +0.149 |
Templ | +0.142 |
�� | +0.137 |
clot | +0.132 |
Neg logit contributions | |
ilon | -0.136 |
earch | -0.134 |
Daddy | -0.133 |
Strait | -0.127 |
WN | -0.120 |
Token | summit |
Token ID | 14237 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
gradation | +1.008 |
================================= | +0.932 |
Templ | +0.887 |
�� | +0.849 |
jar | +0.826 |
Neg logit contributions | |
ilon | -1.106 |
Daddy | -1.096 |
earch | -1.095 |
Strait | -1.049 |
LCS | -1.008 |
Token | valuable |
Token ID | 8119 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ilon | +0.632 |
earch | +0.631 |
Daddy | +0.617 |
Strait | +0.586 |
wcsstore | +0.557 |
Neg logit contributions | |
gradation | -0.870 |
================================= | -0.836 |
Templ | -0.800 |
�� | -0.762 |
clot | -0.749 |
Token | , |
Token ID | 11 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ilon | +0.675 |
earch | +0.670 |
Daddy | +0.653 |
Strait | +0.622 |
ktop | +0.599 |
Neg logit contributions | |
gradation | -0.784 |
================================= | -0.746 |
Templ | -0.705 |
�� | -0.678 |
jar | -0.665 |
Token | local |
Token ID | 1957 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
gradation | +0.466 |
================================= | +0.440 |
Templ | +0.416 |
�� | +0.400 |
clot | +0.384 |
Neg logit contributions | |
ilon | -0.470 |
earch | -0.464 |
Daddy | -0.462 |
Strait | -0.444 |
WN | -0.424 |
Token | independent |
Token ID | 4795 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
gradation | +0.516 |
================================= | +0.492 |
Templ | +0.471 |
�� | +0.457 |
clot | +0.443 |
Neg logit contributions | |
ilon | -0.316 |
earch | -0.312 |
Daddy | -0.310 |
Strait | -0.292 |
WN | -0.275 |
Token | journalism |
Token ID | 14033 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
ilon | +0.041 |
earch | +0.040 |
Daddy | +0.040 |
Strait | +0.038 |
WN | +0.035 |
Neg logit contributions | |
gradation | -0.063 |
================================= | -0.060 |
Templ | -0.058 |
�� | -0.056 |
clot | -0.054 |
Token | in |
Token ID | 287 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ilon | +0.476 |
earch | +0.469 |
Daddy | +0.467 |
Strait | +0.441 |
ktop | +0.419 |
Neg logit contributions | |
gradation | -0.582 |
================================= | -0.554 |
Templ | -0.526 |
�� | -0.503 |
clot | -0.493 |
Token | South |
Token ID | 2520 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
earch | +1.275 |
ilon | +1.245 |
Daddy | +1.225 |
Strait | +1.119 |
ktop | +1.113 |
Neg logit contributions | |
gradation | -1.686 |
================================= | -1.598 |
Templ | -1.526 |
�� | -1.455 |
jar | -1.454 |
Token | Australia |
Token ID | 4505 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
gradation | +0.181 |
================================= | +0.171 |
Templ | +0.163 |
�� | +0.158 |
clot | +0.153 |
Neg logit contributions | |
ilon | -0.142 |
earch | -0.140 |
Daddy | -0.139 |
Strait | -0.132 |
WN | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ilon | +0.061 |
earch | +0.061 |
Daddy | +0.060 |
Strait | +0.057 |
WN | +0.054 |
Neg logit contributions | |
gradation | -0.070 |
================================= | -0.066 |
Templ | -0.063 |
�� | -0.060 |
clot | -0.058 |
Token | As |
Token ID | 1081 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
ilon | +0.611 |
earch | +0.605 |
Daddy | +0.598 |
Strait | +0.570 |
ktop | +0.549 |
Neg logit contributions | |
gradation | -0.583 |
================================= | -0.553 |
Templ | -0.522 |
�� | -0.490 |
jar | -0.485 |
Token | a |
Token ID | 257 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ilon | +0.532 |
earch | +0.522 |
Daddy | +0.520 |
Strait | +0.493 |
wcsstore | +0.470 |
Neg logit contributions | |
gradation | -0.639 |
================================= | -0.604 |
Templ | -0.575 |
�� | -0.553 |
jar | -0.539 |
Token | House |
Token ID | 18102 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
gradation | +0.222 |
================================= | +0.211 |
Templ | +0.201 |
�� | +0.194 |
clot | +0.188 |
Neg logit contributions | |
ilon | -0.174 |
earch | -0.172 |
Daddy | -0.171 |
Strait | -0.162 |
WN | -0.153 |
Token | committee |
Token ID | 5583 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
ilon | +0.012 |
earch | +0.011 |
Daddy | +0.011 |
Strait | +0.011 |
WN | +0.010 |
Neg logit contributions | |
gradation | -0.012 |
================================= | -0.011 |
Templ | -0.011 |
�� | -0.010 |
clot | -0.010 |
Token | believes |
Token ID | 5804 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
gradation | +0.579 |
================================= | +0.548 |
Templ | +0.525 |
�� | +0.497 |
jar | +0.485 |
Neg logit contributions | |
ilon | -0.470 |
earch | -0.468 |
Daddy | -0.463 |
Strait | -0.441 |
WN | -0.415 |
Token | it |
Token ID | 340 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
gradation | +0.553 |
================================= | +0.526 |
Templ | +0.501 |
�� | +0.481 |
clot | +0.465 |
Neg logit contributions | |
ilon | -0.431 |
earch | -0.428 |
Daddy | -0.422 |
Strait | -0.401 |
WN | -0.379 |
Token | has |
Token ID | 468 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
gradation | +0.170 |
================================= | +0.162 |
Templ | +0.154 |
�� | +0.148 |
clot | +0.143 |
Neg logit contributions | |
ilon | -0.144 |
earch | -0.142 |
Daddy | -0.141 |
Strait | -0.135 |
WN | -0.127 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
gradation | +1.104 |
================================= | +1.035 |
Templ | +0.977 |
�� | +0.945 |
jar | +0.900 |
Neg logit contributions | |
ilon | -1.091 |
earch | -1.089 |
Daddy | -1.078 |
Strait | -1.038 |
Hus | -0.987 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ilon | +1.358 |
earch | +1.345 |
Daddy | +1.344 |
Strait | +1.282 |
ktop | +1.241 |
Neg logit contributions | |
gradation | -1.513 |
================================= | -1.472 |
Templ | -1.403 |
clot | -1.363 |
�� | -1.323 |
Token | requested |
Token ID | 9167 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
gradation | +1.461 |
================================= | +1.380 |
Templ | +1.300 |
�� | +1.280 |
jar | +1.214 |
Neg logit contributions | |
ilon | -1.123 |
Daddy | -1.109 |
earch | -1.081 |
Strait | -1.047 |
WN | -0.990 |
Token | putting |
Token ID | 5137 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
gradation | +0.726 |
================================= | +0.682 |
Templ | +0.647 |
�� | +0.629 |
jar | +0.603 |
Neg logit contributions | |
ilon | -0.592 |
earch | -0.583 |
Daddy | -0.582 |
Strait | -0.553 |
LCS | -0.522 |
Token | ally |
Token ID | 12525 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ilon | +0.244 |
earch | +0.242 |
Daddy | +0.240 |
Strait | +0.229 |
WN | +0.219 |
Neg logit contributions | |
gradation | -0.235 |
================================= | -0.222 |
Templ | -0.211 |
�� | -0.201 |
clot | -0.196 |
Token | in |
Token ID | 287 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
gradation | +0.217 |
================================= | +0.207 |
Templ | +0.197 |
�� | +0.192 |
jar | +0.185 |
Neg logit contributions | |
ilon | -0.152 |
earch | -0.150 |
Daddy | -0.149 |
Strait | -0.141 |
WN | -0.133 |
Token | ep |
Token ID | 538 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ilon | +0.251 |
earch | +0.249 |
Daddy | +0.247 |
Strait | +0.236 |
wcsstore | +0.225 |
Neg logit contributions | |
gradation | -0.246 |
================================= | -0.232 |
Templ | -0.220 |
�� | -0.210 |
clot | -0.204 |
Token | HBO |
Token ID | 18804 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
ilon | +0.089 |
earch | +0.088 |
Daddy | +0.087 |
Strait | +0.083 |
WN | +0.079 |
Neg logit contributions | |
gradation | -0.098 |
================================= | -0.093 |
Templ | -0.088 |
�� | -0.085 |
clot | -0.082 |
Token | Jim |
Token ID | 5395 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
ilon | +0.271 |
earch | +0.268 |
Daddy | +0.265 |
Strait | +0.252 |
ktop | +0.241 |
Neg logit contributions | |
gradation | -0.296 |
================================= | -0.281 |
Templ | -0.267 |
�� | -0.255 |
clot | -0.248 |
Token | Parsons |
Token ID | 35925 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
ilon | +0.611 |
earch | +0.605 |
Daddy | +0.597 |
Strait | +0.570 |
ktop | +0.549 |
Neg logit contributions | |
gradation | -0.564 |
================================= | -0.532 |
Templ | -0.503 |
�� | -0.474 |
clot | -0.462 |
Token | The |
Token ID | 383 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ilon | +0.176 |
earch | +0.174 |
Daddy | +0.172 |
Strait | +0.164 |
WN | +0.156 |
Neg logit contributions | |
gradation | -0.192 |
================================= | -0.182 |
Templ | -0.173 |
�� | -0.166 |
clot | -0.161 |
Token | Big |
Token ID | 4403 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ilon | +0.652 |
earch | +0.643 |
Daddy | +0.630 |
Strait | +0.595 |
ktop | +0.574 |
Neg logit contributions | |
gradation | -0.850 |
================================= | -0.819 |
Templ | -0.782 |
�� | -0.743 |
jar | -0.728 |
Token | Bang |
Token ID | 9801 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
earch | +0.896 |
ilon | +0.893 |
Daddy | +0.843 |
Strait | +0.782 |
ktop | +0.747 |
Neg logit contributions | |
gradation | -2.005 |
================================= | -1.948 |
Templ | -1.855 |
�� | -1.786 |
clot | -1.753 |
Token | Theory |
Token ID | 17003 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ilon | +0.412 |
earch | +0.410 |
Daddy | +0.403 |
Strait | +0.384 |
ktop | +0.367 |
Neg logit contributions | |
gradation | -0.507 |
================================= | -0.484 |
Templ | -0.459 |
�� | -0.443 |
clot | -0.429 |
Token | CBS |
Token ID | 11133 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
ilon | +0.183 |
earch | +0.181 |
Daddy | +0.179 |
Strait | +0.170 |
ktop | +0.162 |
Neg logit contributions | |
gradation | -0.204 |
================================= | -0.194 |
Templ | -0.185 |
�� | -0.177 |
clot | -0.172 |
Token | Amy |
Token ID | 14235 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
gradation | +0.031 |
================================= | +0.030 |
Templ | +0.028 |
�� | +0.027 |
clot | +0.026 |
Neg logit contributions | |
ilon | -0.029 |
earch | -0.029 |
Daddy | -0.028 |
Strait | -0.027 |
WN | -0.026 |
Token | Poe |
Token ID | 34815 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
gradation | +0.178 |
================================= | +0.166 |
Templ | +0.154 |
�� | +0.147 |
clot | +0.141 |
Neg logit contributions | |
ilon | -0.263 |
earch | -0.260 |
Daddy | -0.259 |
Strait | -0.250 |
WN | -0.239 |
Token | The |
Token ID | 383 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ilon | +0.138 |
earch | +0.136 |
Daddy | +0.135 |
Strait | +0.129 |
WN | +0.122 |
Neg logit contributions | |
gradation | -0.155 |
================================= | -0.147 |
Templ | -0.139 |
�� | -0.134 |
clot | -0.130 |
Token | Bh |
Token ID | 16581 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ilon | +0.365 |
earch | +0.361 |
Daddy | +0.357 |
Strait | +0.339 |
ktop | +0.323 |
Neg logit contributions | |
gradation | -0.416 |
================================= | -0.395 |
Templ | -0.376 |
�� | -0.360 |
clot | -0.350 |
Token | ag |
Token ID | 363 |
Feature activation | -3.23e-03 |
Pos logit contributions | |
ilon | +0.091 |
earch | +0.090 |
Daddy | +0.089 |
Strait | +0.083 |
WN | +0.078 |
Neg logit contributions | |
gradation | -0.161 |
================================= | -0.154 |
Templ | -0.147 |
�� | -0.142 |
clot | -0.139 |
Token | av |
Token ID | 615 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
ilon | +0.003 |
earch | +0.003 |
Daddy | +0.003 |
Strait | +0.002 |
WN | +0.002 |
Neg logit contributions | |
gradation | -0.002 |
================================= | -0.002 |
Templ | -0.002 |
�� | -0.002 |
clot | -0.002 |
Token | ad |
Token ID | 324 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
gradation | +0.053 |
================================= | +0.051 |
Templ | +0.049 |
�� | +0.048 |
clot | +0.047 |
Neg logit contributions | |
ilon | -0.018 |
earch | -0.017 |
Daddy | -0.017 |
Strait | -0.016 |
WN | -0.014 |
Token | G |
Token ID | 402 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ilon | +0.225 |
earch | +0.223 |
Daddy | +0.221 |
Strait | +0.212 |
ktop | +0.202 |
Neg logit contributions | |
gradation | -0.208 |
================================= | -0.196 |
Templ | -0.184 |
�� | -0.176 |
clot | -0.170 |
Token | ita |
Token ID | 5350 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ilon | +1.324 |
Daddy | +1.296 |
earch | +1.276 |
Strait | +1.219 |
wcsstore | +1.219 |
Neg logit contributions | |
gradation | -1.552 |
================================= | -1.480 |
Templ | -1.386 |
�� | -1.323 |
jar | -1.319 |
Token |
|
Token ID | 198 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
gradation | +0.013 |
================================= | +0.012 |
Templ | +0.011 |
�� | +0.011 |
clot | +0.011 |
Neg logit contributions | |
ilon | -0.011 |
earch | -0.011 |
Daddy | -0.011 |
Strait | -0.010 |
WN | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
gradation | +0.041 |
================================= | +0.039 |
Templ | +0.037 |
�� | +0.036 |
clot | +0.034 |
Neg logit contributions | |
ilon | -0.036 |
earch | -0.035 |
Daddy | -0.035 |
Strait | -0.033 |
WN | -0.032 |
Token | - |
Token ID | 12 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
gradation | +0.044 |
================================= | +0.041 |
Templ | +0.039 |
�� | +0.038 |
clot | +0.037 |
Neg logit contributions | |
ilon | -0.037 |
earch | -0.036 |
Daddy | -0.036 |
Strait | -0.034 |
WN | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
gradation | +0.089 |
================================= | +0.084 |
Templ | +0.080 |
�� | +0.077 |
clot | +0.075 |
Neg logit contributions | |
ilon | -0.074 |
earch | -0.073 |
Daddy | -0.073 |
Strait | -0.069 |
WN | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ilon | +0.322 |
earch | +0.320 |
Daddy | +0.316 |
Strait | +0.301 |
ktop | +0.287 |
Neg logit contributions | |
gradation | -0.357 |
================================= | -0.340 |
Templ | -0.322 |
�� | -0.307 |
jar | -0.300 |
Token | Ram |
Token ID | 7431 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
ilon | +0.277 |
earch | +0.275 |
Daddy | +0.272 |
Strait | +0.259 |
WN | +0.247 |
Neg logit contributions | |
gradation | -0.295 |
================================= | -0.280 |
Templ | -0.265 |
�� | -0.254 |
clot | -0.246 |
Token | í |
Token ID | 8836 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ilon | +0.035 |
earch | +0.034 |
Daddy | +0.034 |
Strait | +0.032 |
WN | +0.030 |
Neg logit contributions | |
gradation | -0.052 |
================================= | -0.049 |
Templ | -0.047 |
�� | -0.045 |
clot | -0.044 |
Token | rez |
Token ID | 21107 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ilon | +0.114 |
earch | +0.113 |
Daddy | +0.112 |
Strait | +0.107 |
WN | +0.102 |
Neg logit contributions | |
gradation | -0.115 |
================================= | -0.108 |
Templ | -0.102 |
�� | -0.098 |
clot | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
ilon | +0.271 |
earch | +0.268 |
Daddy | +0.265 |
Strait | +0.252 |
WN | +0.239 |
Neg logit contributions | |
gradation | -0.336 |
================================= | -0.319 |
Templ | -0.304 |
�� | -0.292 |
clot | -0.284 |
Token | PD |
Token ID | 14340 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
gradation | +0.055 |
================================= | +0.053 |
Templ | +0.050 |
�� | +0.048 |
clot | +0.047 |
Neg logit contributions | |
ilon | -0.044 |
earch | -0.044 |
Daddy | -0.043 |
Strait | -0.041 |
WN | -0.039 |
Token | V |
Token ID | 53 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
gradation | +0.785 |
================================= | +0.730 |
Templ | +0.687 |
�� | +0.662 |
clot | +0.628 |
Neg logit contributions | |
ilon | -1.050 |
earch | -1.030 |
Daddy | -1.030 |
Strait | -0.989 |
WN | -0.958 |
Token | SA |
Token ID | 4090 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
gradation | +0.452 |
================================= | +0.429 |
Templ | +0.410 |
�� | +0.399 |
clot | +0.385 |
Neg logit contributions | |
ilon | -0.328 |
earch | -0.323 |
Daddy | -0.321 |
Strait | -0.303 |
WN | -0.288 |
Token | has |
Token ID | 468 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
gradation | +0.162 |
================================= | +0.153 |
Templ | +0.145 |
�� | +0.140 |
clot | +0.136 |
Neg logit contributions | |
ilon | -0.142 |
earch | -0.140 |
Daddy | -0.139 |
Strait | -0.132 |
WN | -0.125 |
Token | not |
Token ID | 407 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
gradation | +0.272 |
================================= | +0.257 |
Templ | +0.243 |
�� | +0.235 |
clot | +0.226 |
Neg logit contributions | |
ilon | -0.256 |
earch | -0.253 |
Daddy | -0.251 |
Strait | -0.240 |
WN | -0.228 |
Token | thri |
Token ID | 19531 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
gradation | +0.030 |
================================= | +0.029 |
Templ | +0.027 |
�� | +0.026 |
clot | +0.025 |
Neg logit contributions | |
ilon | -0.029 |
earch | -0.028 |
Daddy | -0.028 |
Strait | -0.027 |
WN | -0.025 |
Token | time |
Token ID | 640 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
gradation | +0.102 |
================================= | +0.097 |
Templ | +0.092 |
�� | +0.089 |
clot | +0.086 |
Neg logit contributions | |
ilon | -0.081 |
earch | -0.080 |
Daddy | -0.079 |
Strait | -0.075 |
WN | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ilon | +0.105 |
earch | +0.103 |
Daddy | +0.103 |
Strait | +0.098 |
WN | +0.093 |
Neg logit contributions | |
gradation | -0.118 |
================================= | -0.112 |
Templ | -0.106 |
�� | -0.102 |
clot | -0.099 |
Token | You |
Token ID | 921 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
gradation | +0.271 |
================================= | +0.255 |
Templ | +0.243 |
�� | +0.234 |
clot | +0.226 |
Neg logit contributions | |
ilon | -0.252 |
earch | -0.250 |
Daddy | -0.248 |
Strait | -0.237 |
WN | -0.225 |
Token | agree |
Token ID | 4236 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
gradation | +0.324 |
================================= | +0.308 |
Templ | +0.295 |
�� | +0.285 |
clot | +0.276 |
Neg logit contributions | |
ilon | -0.231 |
earch | -0.227 |
Daddy | -0.224 |
Strait | -0.213 |
WN | -0.201 |
Token | to |
Token ID | 284 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
gradation | +0.126 |
================================= | +0.119 |
Templ | +0.114 |
�� | +0.110 |
clot | +0.106 |
Neg logit contributions | |
ilon | -0.099 |
earch | -0.098 |
Daddy | -0.097 |
Strait | -0.092 |
WN | -0.087 |
Token | receive |
Token ID | 3328 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
gradation | +0.682 |
================================= | +0.632 |
Templ | +0.596 |
�� | +0.579 |
jar | +0.540 |
Neg logit contributions | |
ilon | -0.883 |
earch | -0.874 |
Daddy | -0.866 |
Strait | -0.837 |
WN | -0.805 |
Token | occasional |
Token ID | 12209 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
gradation | +0.968 |
================================= | +0.915 |
Templ | +0.869 |
�� | +0.849 |
clot | +0.805 |
Neg logit contributions | |
ilon | -0.852 |
earch | -0.842 |
Daddy | -0.836 |
Strait | -0.800 |
WN | -0.766 |
Token | updates |
Token ID | 5992 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
gradation | +0.427 |
================================= | +0.405 |
Templ | +0.387 |
�� | +0.375 |
clot | +0.363 |
Neg logit contributions | |
ilon | -0.307 |
earch | -0.302 |
Daddy | -0.299 |
Strait | -0.284 |
WN | -0.269 |
Token | and |
Token ID | 290 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
gradation | +0.249 |
================================= | +0.237 |
Templ | +0.226 |
�� | +0.218 |
clot | +0.211 |
Neg logit contributions | |
ilon | -0.193 |
earch | -0.190 |
Daddy | -0.189 |
Strait | -0.179 |
WN | -0.169 |
Token | special |
Token ID | 2041 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
gradation | +0.517 |
================================= | +0.489 |
Templ | +0.465 |
�� | +0.450 |
jar | +0.432 |
Neg logit contributions | |
ilon | -0.461 |
earch | -0.455 |
Daddy | -0.452 |
Strait | -0.432 |
WN | -0.410 |
Token | offers |
Token ID | 4394 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
ilon | +0.135 |
earch | +0.133 |
Daddy | +0.132 |
Strait | +0.126 |
WN | +0.120 |
Neg logit contributions | |
gradation | -0.149 |
================================= | -0.141 |
Templ | -0.134 |
�� | -0.129 |
clot | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
gradation | +0.042 |
================================= | +0.040 |
Templ | +0.038 |
�� | +0.036 |
clot | +0.035 |
Neg logit contributions | |
ilon | -0.037 |
earch | -0.036 |
Daddy | -0.036 |
Strait | -0.034 |
WN | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
gradation | +0.091 |
================================= | +0.086 |
Templ | +0.081 |
�� | +0.079 |
clot | +0.076 |
Neg logit contributions | |
ilon | -0.078 |
earch | -0.078 |
Daddy | -0.077 |
Strait | -0.073 |
WN | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
gradation | +0.070 |
================================= | +0.066 |
Templ | +0.063 |
�� | +0.060 |
clot | +0.058 |
Neg logit contributions | |
ilon | -0.060 |
earch | -0.060 |
Daddy | -0.059 |
Strait | -0.056 |
WN | -0.054 |
Token | Sign |
Token ID | 11712 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
ilon | +0.052 |
earch | +0.051 |
Daddy | +0.051 |
Strait | +0.048 |
WN | +0.045 |
Neg logit contributions | |
gradation | -0.082 |
================================= | -0.079 |
Templ | -0.075 |
�� | -0.073 |
clot | -0.071 |
Token | up |
Token ID | 510 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
gradation | +0.010 |
================================= | +0.009 |
Templ | +0.009 |
�� | +0.009 |
clot | +0.008 |
Neg logit contributions | |
ilon | -0.008 |
earch | -0.008 |
Daddy | -0.008 |
Strait | -0.007 |
WN | -0.007 |
Token | for |
Token ID | 329 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
gradation | +0.176 |
================================= | +0.167 |
Templ | +0.159 |
�� | +0.154 |
clot | +0.149 |
Neg logit contributions | |
ilon | -0.136 |
earch | -0.134 |
Daddy | -0.133 |
Strait | -0.126 |
WN | -0.119 |
Token | our |
Token ID | 674 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
gradation | +1.784 |
================================= | +1.708 |
Templ | +1.630 |
�� | +1.606 |
jar | +1.528 |
Neg logit contributions | |
ilon | -1.046 |
Daddy | -1.039 |
earch | -1.025 |
Strait | -0.987 |
WN | -0.919 |
Token | Wine |
Token ID | 20447 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
gradation | +0.538 |
================================= | +0.508 |
Templ | +0.481 |
�� | +0.467 |
clot | +0.449 |
Neg logit contributions | |
ilon | -0.510 |
earch | -0.503 |
Daddy | -0.502 |
Strait | -0.477 |
WN | -0.458 |
Token | Club |
Token ID | 6289 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ilon | +1.112 |
earch | +1.095 |
Daddy | +1.071 |
Strait | +1.032 |
WN | +1.007 |
Neg logit contributions | |
gradation | -0.693 |
================================= | -0.632 |
Templ | -0.598 |
�� | -0.556 |
clot | -0.537 |
Token | today |
Token ID | 1909 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilon | +0.151 |
earch | +0.149 |
Daddy | +0.147 |
Strait | +0.139 |
WN | +0.131 |
Neg logit contributions | |
gradation | -0.216 |
================================= | -0.206 |
Templ | -0.197 |
�� | -0.189 |
clot | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
gradation | +0.153 |
================================= | +0.145 |
Templ | +0.137 |
�� | +0.133 |
clot | +0.128 |
Neg logit contributions | |
ilon | -0.132 |
earch | -0.130 |
Daddy | -0.130 |
Strait | -0.123 |
WN | -0.117 |
Token | taxes |
Token ID | 5704 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
gradation | +1.387 |
================================= | +1.320 |
Templ | +1.265 |
�� | +1.221 |
clot | +1.178 |
Neg logit contributions | |
ilon | -0.840 |
earch | -0.835 |
Daddy | -0.835 |
Strait | -0.767 |
WN | -0.725 |
Token | ' |
Token ID | 6 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
gradation | +1.164 |
================================= | +1.094 |
Templ | +1.065 |
�� | +1.031 |
clot | +0.988 |
Neg logit contributions | |
ilon | -0.781 |
Daddy | -0.768 |
earch | -0.764 |
Strait | -0.727 |
Hus | -0.684 |
Token | Former |
Token ID | 14466 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
gradation | +0.603 |
================================= | +0.563 |
Templ | +0.539 |
�� | +0.517 |
clot | +0.495 |
Neg logit contributions | |
ilon | -0.626 |
earch | -0.620 |
Daddy | -0.614 |
Strait | -0.589 |
WN | -0.567 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
gradation | +0.817 |
================================= | +0.772 |
Templ | +0.734 |
�� | +0.705 |
jar | +0.680 |
Neg logit contributions | |
ilon | -0.706 |
Daddy | -0.696 |
earch | -0.686 |
Strait | -0.646 |
WN | -0.628 |
Token | campaign |
Token ID | 1923 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
gradation | +0.697 |
================================= | +0.663 |
Templ | +0.638 |
�� | +0.618 |
jar | +0.602 |
Neg logit contributions | |
ilon | -0.348 |
earch | -0.339 |
Daddy | -0.339 |
Strait | -0.313 |
WN | -0.292 |
Token | spokesman |
Token ID | 6523 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
gradation | +0.356 |
================================= | +0.337 |
Templ | +0.320 |
�� | +0.310 |
clot | +0.298 |
Neg logit contributions | |
ilon | -0.314 |
earch | -0.309 |
Daddy | -0.308 |
Strait | -0.293 |
WN | -0.279 |
Token | : |
Token ID | 25 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
gradation | +1.573 |
================================= | +1.504 |
Templ | +1.444 |
�� | +1.395 |
clot | +1.342 |
Neg logit contributions | |
ilon | -1.074 |
earch | -1.067 |
Daddy | -1.064 |
Strait | -1.009 |
WN | -0.944 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
gradation | +0.783 |
================================= | +0.740 |
Templ | +0.698 |
�� | +0.680 |
clot | +0.656 |
Neg logit contributions | |
ilon | -0.707 |
earch | -0.694 |
Daddy | -0.694 |
Strait | -0.662 |
wcsstore | -0.632 |
Token | staff |
Token ID | 3085 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
gradation | +1.274 |
================================= | +1.229 |
Templ | +1.153 |
�� | +1.139 |
clot | +1.083 |
Neg logit contributions | |
ilon | -1.063 |
earch | -1.027 |
Daddy | -1.026 |
Strait | -0.978 |
wcsstore | -0.928 |
Token | are |
Token ID | 389 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
gradation | +0.778 |
================================= | +0.739 |
Templ | +0.706 |
�� | +0.674 |
clot | +0.656 |
Neg logit contributions | |
ilon | -0.594 |
earch | -0.586 |
Daddy | -0.578 |
Strait | -0.552 |
WN | -0.519 |
Token | ' |
Token ID | 705 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
gradation | +0.463 |
================================= | +0.429 |
Templ | +0.400 |
�� | +0.376 |
jar | +0.365 |
Neg logit contributions | |
ilon | -0.661 |
earch | -0.656 |
Daddy | -0.651 |
Strait | -0.627 |
LCS | -0.599 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ilon | +0.336 |
earch | +0.333 |
Daddy | +0.330 |
Strait | +0.313 |
WN | +0.296 |
Neg logit contributions | |
gradation | -0.412 |
================================= | -0.391 |
Templ | -0.373 |
�� | -0.358 |
clot | -0.349 |
Token | disease |
Token ID | 4369 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ilon | +0.264 |
earch | +0.261 |
Daddy | +0.258 |
Strait | +0.245 |
WN | +0.233 |
Neg logit contributions | |
gradation | -0.305 |
================================= | -0.289 |
Templ | -0.275 |
�� | -0.264 |
clot | -0.257 |
Token | become |
Token ID | 1716 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
gradation | +0.116 |
================================= | +0.109 |
Templ | +0.104 |
�� | +0.100 |
clot | +0.096 |
Neg logit contributions | |
ilon | -0.107 |
earch | -0.105 |
Daddy | -0.104 |
Strait | -0.100 |
WN | -0.095 |
Token | apparent |
Token ID | 4156 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
ilon | +0.066 |
earch | +0.065 |
Daddy | +0.064 |
Strait | +0.061 |
WN | +0.058 |
Neg logit contributions | |
gradation | -0.083 |
================================= | -0.078 |
Templ | -0.075 |
�� | -0.072 |
clot | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
gradation | +0.046 |
================================= | +0.043 |
Templ | +0.041 |
�� | +0.040 |
clot | +0.038 |
Neg logit contributions | |
ilon | -0.040 |
earch | -0.039 |
Daddy | -0.039 |
Strait | -0.037 |
WN | -0.035 |
Token | Skin |
Token ID | 17847 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ilon | +0.071 |
earch | +0.070 |
Daddy | +0.070 |
Strait | +0.066 |
WN | +0.063 |
Neg logit contributions | |
gradation | -0.073 |
================================= | -0.069 |
Templ | -0.066 |
�� | -0.063 |
clot | -0.061 |
Token | disc |
Token ID | 1221 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
gradation | +1.022 |
================================= | +0.970 |
Templ | +0.920 |
�� | +0.892 |
clot | +0.852 |
Neg logit contributions | |
ilon | -0.873 |
earch | -0.860 |
Daddy | -0.853 |
Strait | -0.817 |
WN | -0.773 |
Token | ol |
Token ID | 349 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
gradation | +0.710 |
================================= | +0.684 |
Templ | +0.655 |
�� | +0.637 |
clot | +0.618 |
Neg logit contributions | |
ilon | -0.371 |
earch | -0.364 |
Daddy | -0.360 |
Strait | -0.336 |
WN | -0.312 |
Token | oration |
Token ID | 6944 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
gradation | +0.658 |
================================= | +0.614 |
Templ | +0.567 |
�� | +0.542 |
clot | +0.503 |
Neg logit contributions | |
ilon | -1.145 |
earch | -1.134 |
Daddy | -1.123 |
Strait | -1.082 |
ktop | -1.048 |
Token | and |
Token ID | 290 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
gradation | +0.274 |
================================= | +0.260 |
Templ | +0.247 |
�� | +0.239 |
clot | +0.231 |
Neg logit contributions | |
ilon | -0.232 |
earch | -0.229 |
Daddy | -0.227 |
Strait | -0.217 |
WN | -0.205 |
Token | darker |
Token ID | 18646 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
gradation | +0.381 |
================================= | +0.360 |
Templ | +0.341 |
�� | +0.329 |
jar | +0.316 |
Neg logit contributions | |
ilon | -0.363 |
earch | -0.358 |
Daddy | -0.356 |
Strait | -0.340 |
WN | -0.323 |
Token | hip |
Token ID | 1056 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ilon | +0.359 |
earch | +0.355 |
Daddy | +0.352 |
Strait | +0.335 |
WN | +0.318 |
Neg logit contributions | |
gradation | -0.420 |
================================= | -0.399 |
Templ | -0.379 |
�� | -0.364 |
clot | -0.355 |
Token | � |
Token ID | 447 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ilon | +0.393 |
earch | +0.389 |
Daddy | +0.385 |
Strait | +0.366 |
ktop | +0.347 |
Neg logit contributions | |
gradation | -0.470 |
================================= | -0.447 |
Templ | -0.425 |
�� | -0.409 |
clot | -0.398 |
Token | � |
Token ID | 251 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
gradation | +0.185 |
================================= | +0.175 |
Templ | +0.166 |
�� | +0.160 |
clot | +0.155 |
Neg logit contributions | |
ilon | -0.158 |
earch | -0.157 |
Daddy | -0.155 |
Strait | -0.148 |
WN | -0.140 |
Token | stitch |
Token ID | 24695 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
ilon | +0.251 |
earch | +0.249 |
Daddy | +0.246 |
Strait | +0.234 |
WN | +0.222 |
Neg logit contributions | |
gradation | -0.300 |
================================= | -0.285 |
Templ | -0.271 |
�� | -0.261 |
clot | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
ilon | +0.424 |
earch | +0.420 |
Daddy | +0.415 |
Strait | +0.395 |
ktop | +0.375 |
Neg logit contributions | |
gradation | -0.495 |
================================= | -0.471 |
Templ | -0.447 |
�� | -0.429 |
clot | -0.419 |
Token | Next |
Token ID | 7406 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
ilon | +0.064 |
earch | +0.063 |
Daddy | +0.062 |
Strait | +0.060 |
WN | +0.057 |
Neg logit contributions | |
gradation | -0.066 |
================================= | -0.062 |
Templ | -0.059 |
�� | -0.057 |
clot | -0.055 |
Token | show |
Token ID | 905 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ilon | +0.030 |
earch | +0.030 |
Daddy | +0.030 |
Strait | +0.028 |
WN | +0.027 |
Neg logit contributions | |
gradation | -0.038 |
================================= | -0.036 |
Templ | -0.034 |
�� | -0.033 |
clot | -0.032 |
Token | them |
Token ID | 606 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
gradation | +0.223 |
================================= | +0.210 |
Templ | +0.199 |
�� | +0.192 |
clot | +0.185 |
Neg logit contributions | |
ilon | -0.208 |
earch | -0.206 |
Daddy | -0.205 |
Strait | -0.195 |
WN | -0.185 |
Token | how |
Token ID | 703 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ilon | +0.148 |
earch | +0.147 |
Daddy | +0.145 |
Strait | +0.139 |
WN | +0.132 |
Neg logit contributions | |
gradation | -0.168 |
================================= | -0.159 |
Templ | -0.151 |
�� | -0.145 |
clot | -0.141 |
Token | they |
Token ID | 484 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ilon | +0.206 |
earch | +0.204 |
Daddy | +0.202 |
Strait | +0.191 |
WN | +0.182 |
Neg logit contributions | |
gradation | -0.257 |
================================= | -0.244 |
Templ | -0.233 |
�� | -0.224 |
clot | -0.218 |
Token | can |
Token ID | 460 |
Feature activation | +6.31e-03 |
Pos logit contributions | |
ilon | +0.079 |
earch | +0.078 |
Daddy | +0.077 |
Strait | +0.073 |
WN | +0.070 |
Neg logit contributions | |
gradation | -0.087 |
================================= | -0.082 |
Templ | -0.078 |
�� | -0.075 |
clot | -0.073 |
Token | of |
Token ID | 286 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ilon | +0.309 |
earch | +0.305 |
Daddy | +0.303 |
Strait | +0.289 |
WN | +0.274 |
Neg logit contributions | |
gradation | -0.356 |
================================= | -0.339 |
Templ | -0.322 |
�� | -0.309 |
clot | -0.300 |
Token | talent |
Token ID | 7401 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ilon | +0.142 |
earch | +0.140 |
Daddy | +0.139 |
Strait | +0.132 |
WN | +0.125 |
Neg logit contributions | |
gradation | -0.169 |
================================= | -0.160 |
Templ | -0.153 |
�� | -0.147 |
clot | -0.143 |
Token | out |
Token ID | 503 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
ilon | +0.189 |
earch | +0.187 |
Daddy | +0.185 |
Strait | +0.176 |
WN | +0.166 |
Neg logit contributions | |
gradation | -0.235 |
================================= | -0.223 |
Templ | -0.213 |
�� | -0.204 |
clot | -0.199 |
Token | there |
Token ID | 612 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ilon | +0.314 |
earch | +0.309 |
Daddy | +0.307 |
Strait | +0.289 |
WN | +0.269 |
Neg logit contributions | |
gradation | -0.528 |
================================= | -0.505 |
Templ | -0.483 |
�� | -0.467 |
clot | -0.456 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ilon | +0.072 |
earch | +0.071 |
Daddy | +0.071 |
Strait | +0.067 |
WN | +0.064 |
Neg logit contributions | |
gradation | -0.091 |
================================= | -0.087 |
Templ | -0.082 |
�� | -0.079 |
clot | -0.077 |
Token | I |
Token ID | 314 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
gradation | +0.020 |
================================= | +0.019 |
Templ | +0.018 |
�� | +0.018 |
clot | +0.017 |
Neg logit contributions | |
ilon | -0.020 |
earch | -0.019 |
Daddy | -0.019 |
Strait | -0.018 |
WN | -0.017 |
Token | think |
Token ID | 892 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
gradation | +0.100 |
================================= | +0.094 |
Templ | +0.089 |
�� | +0.086 |
clot | +0.083 |
Neg logit contributions | |
ilon | -0.095 |
earch | -0.094 |
Daddy | -0.094 |
Strait | -0.089 |
WN | -0.085 |
Token | it |
Token ID | 340 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ilon | +0.008 |
earch | +0.008 |
Daddy | +0.008 |
Strait | +0.007 |
WN | +0.007 |
Neg logit contributions | |
gradation | -0.010 |
================================= | -0.009 |
Templ | -0.009 |
�� | -0.009 |
clot | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ilon | +0.013 |
earch | +0.013 |
Daddy | +0.012 |
Strait | +0.012 |
WN | +0.011 |
Neg logit contributions | |
gradation | -0.014 |
================================= | -0.013 |
Templ | -0.013 |
�� | -0.012 |
clot | -0.012 |
Token | part |
Token ID | 636 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ilon | +0.068 |
earch | +0.067 |
Daddy | +0.066 |
Strait | +0.063 |
WN | +0.060 |
Neg logit contributions | |
gradation | -0.077 |
================================= | -0.073 |
Templ | -0.069 |
�� | -0.067 |
clot | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ilon | +0.110 |
earch | +0.109 |
Daddy | +0.108 |
Strait | +0.103 |
WN | +0.097 |
Neg logit contributions | |
gradation | -0.125 |
================================= | -0.119 |
Templ | -0.113 |
�� | -0.109 |
clot | -0.105 |
Token | wrap |
Token ID | 14441 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
gradation | +0.084 |
================================= | +0.079 |
Templ | +0.075 |
�� | +0.072 |
clot | +0.070 |
Neg logit contributions | |
ilon | -0.075 |
earch | -0.075 |
Daddy | -0.074 |
Strait | -0.070 |
WN | -0.067 |
Token | up |
Token ID | 510 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
gradation | +0.027 |
================================= | +0.026 |
Templ | +0.025 |
�� | +0.024 |
clot | +0.023 |
Neg logit contributions | |
ilon | -0.021 |
earch | -0.021 |
Daddy | -0.020 |
Strait | -0.019 |
WN | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
gradation | +0.037 |
================================= | +0.036 |
Templ | +0.034 |
�� | +0.033 |
clot | +0.032 |
Neg logit contributions | |
ilon | -0.030 |
earch | -0.030 |
Daddy | -0.029 |
Strait | -0.028 |
WN | -0.026 |
Token | giant |
Token ID | 6175 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
gradation | +0.275 |
================================= | +0.261 |
Templ | +0.248 |
�� | +0.239 |
clot | +0.231 |
Neg logit contributions | |
ilon | -0.240 |
earch | -0.237 |
Daddy | -0.236 |
Strait | -0.225 |
WN | -0.213 |
Token | signs |
Token ID | 5895 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
gradation | +0.094 |
================================= | +0.089 |
Templ | +0.084 |
�� | +0.081 |
clot | +0.079 |
Neg logit contributions | |
ilon | -0.078 |
earch | -0.077 |
Daddy | -0.077 |
Strait | -0.073 |
WN | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
ilon | +0.108 |
earch | +0.107 |
Daddy | +0.106 |
Strait | +0.101 |
WN | +0.096 |
Neg logit contributions | |
gradation | -0.134 |
================================= | -0.127 |
Templ | -0.121 |
�� | -0.116 |
clot | -0.113 |
Token | we |
Token ID | 356 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
gradation | +0.054 |
================================= | +0.051 |
Templ | +0.049 |
�� | +0.047 |
clot | +0.045 |
Neg logit contributions | |
ilon | -0.050 |
earch | -0.050 |
Daddy | -0.049 |
Strait | -0.047 |
WN | -0.045 |
Token | head |
Token ID | 1182 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
gradation | +0.025 |
================================= | +0.023 |
Templ | +0.022 |
�� | +0.021 |
clot | +0.021 |
Neg logit contributions | |
ilon | -0.022 |
earch | -0.022 |
Daddy | -0.022 |
Strait | -0.021 |
WN | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ilon | +0.135 |
earch | +0.133 |
Daddy | +0.132 |
Strait | +0.125 |
WN | +0.119 |
Neg logit contributions | |
gradation | -0.168 |
================================= | -0.159 |
Templ | -0.152 |
�� | -0.146 |
clot | -0.142 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
gradation | +0.209 |
================================= | +0.198 |
Templ | +0.189 |
�� | +0.182 |
clot | +0.177 |
Neg logit contributions | |
ilon | -0.160 |
earch | -0.158 |
Daddy | -0.157 |
Strait | -0.149 |
WN | -0.140 |
Token | bar |
Token ID | 2318 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
gradation | +0.289 |
================================= | +0.273 |
Templ | +0.258 |
�� | +0.249 |
clot | +0.240 |
Neg logit contributions | |
ilon | -0.274 |
earch | -0.271 |
Daddy | -0.269 |
Strait | -0.257 |
WN | -0.244 |
Token | ively |
Token ID | 2280 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
gradation | +0.042 |
================================= | +0.040 |
Templ | +0.038 |
�� | +0.036 |
clot | +0.035 |
Neg logit contributions | |
ilon | -0.034 |
earch | -0.033 |
Daddy | -0.033 |
Strait | -0.031 |
WN | -0.030 |
Token | abuse |
Token ID | 5076 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
gradation | +0.142 |
================================= | +0.135 |
Templ | +0.127 |
�� | +0.122 |
clot | +0.118 |
Neg logit contributions | |
ilon | -0.139 |
earch | -0.138 |
Daddy | -0.137 |
Strait | -0.131 |
WN | -0.124 |
Token | popular |
Token ID | 2968 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
gradation | +0.023 |
================================= | +0.021 |
Templ | +0.020 |
�� | +0.020 |
clot | +0.019 |
Neg logit contributions | |
ilon | -0.019 |
earch | -0.019 |
Daddy | -0.019 |
Strait | -0.018 |
WN | -0.017 |
Token | rave |
Token ID | 46242 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
gradation | +0.124 |
================================= | +0.117 |
Templ | +0.112 |
�� | +0.108 |
clot | +0.104 |
Neg logit contributions | |
ilon | -0.100 |
earch | -0.099 |
Daddy | -0.098 |
Strait | -0.093 |
WN | -0.088 |
Token | drugs |
Token ID | 5010 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
ilon | +0.096 |
earch | +0.095 |
Daddy | +0.095 |
Strait | +0.090 |
WN | +0.085 |
Neg logit contributions | |
gradation | -0.111 |
================================= | -0.105 |
Templ | -0.100 |
�� | -0.096 |
clot | -0.093 |
Token | come |
Token ID | 1282 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ilon | +0.039 |
earch | +0.038 |
Daddy | +0.038 |
Strait | +0.036 |
WN | +0.034 |
Neg logit contributions | |
gradation | -0.047 |
================================= | -0.044 |
Templ | -0.042 |
�� | -0.041 |
clot | -0.039 |
Token | off |
Token ID | 572 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
gradation | +0.237 |
================================= | +0.225 |
Templ | +0.213 |
�� | +0.206 |
clot | +0.200 |
Neg logit contributions | |
ilon | -0.192 |
earch | -0.190 |
Daddy | -0.188 |
Strait | -0.179 |
WN | -0.170 |
Token | their |
Token ID | 511 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
gradation | +0.077 |
================================= | +0.073 |
Templ | +0.070 |
�� | +0.067 |
clot | +0.065 |
Neg logit contributions | |
ilon | -0.062 |
earch | -0.061 |
Daddy | -0.061 |
Strait | -0.058 |
WN | -0.055 |
Token | cr |
Token ID | 1067 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
gradation | +0.209 |
================================= | +0.198 |
Templ | +0.188 |
�� | +0.181 |
clot | +0.175 |
Neg logit contributions | |
ilon | -0.179 |
earch | -0.177 |
Daddy | -0.175 |
Strait | -0.167 |
WN | -0.158 |
Token | utch |
Token ID | 7140 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ilon | +0.381 |
earch | +0.376 |
Daddy | +0.373 |
Strait | +0.357 |
ktop | +0.340 |
Neg logit contributions | |
gradation | -0.398 |
================================= | -0.376 |
Templ | -0.356 |
�� | -0.340 |
clot | -0.330 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
gradation | +0.088 |
================================= | +0.084 |
Templ | +0.080 |
�� | +0.077 |
clot | +0.074 |
Neg logit contributions | |
ilon | -0.076 |
earch | -0.075 |
Daddy | -0.074 |
Strait | -0.071 |
WN | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
gradation | +0.132 |
================================= | +0.125 |
Templ | +0.118 |
�� | +0.114 |
clot | +0.111 |
Neg logit contributions | |
ilon | -0.114 |
earch | -0.112 |
Daddy | -0.112 |
Strait | -0.106 |
WN | -0.101 |
Token | Man |
Token ID | 1869 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
gradation | +0.043 |
================================= | +0.040 |
Templ | +0.038 |
�� | +0.037 |
clot | +0.036 |
Neg logit contributions | |
ilon | -0.035 |
earch | -0.035 |
Daddy | -0.034 |
Strait | -0.033 |
WN | -0.031 |
Token | gh |
Token ID | 456 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ilon | +0.107 |
earch | +0.106 |
Daddy | +0.105 |
Strait | +0.100 |
WN | +0.095 |
Neg logit contributions | |
gradation | -0.121 |
================================= | -0.114 |
Templ | -0.109 |
�� | -0.104 |
clot | -0.101 |
Token | ud |
Token ID | 463 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ilon | +0.085 |
earch | +0.084 |
Daddy | +0.084 |
Strait | +0.079 |
WN | +0.075 |
Neg logit contributions | |
gradation | -0.112 |
================================= | -0.107 |
Templ | -0.101 |
�� | -0.098 |
clot | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
ilon | +0.065 |
earch | +0.065 |
Daddy | +0.064 |
Strait | +0.061 |
WN | +0.057 |
Neg logit contributions | |
gradation | -0.089 |
================================= | -0.084 |
Templ | -0.080 |
�� | -0.078 |
clot | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
gradation | +0.045 |
================================= | +0.043 |
Templ | +0.041 |
�� | +0.039 |
clot | +0.038 |
Neg logit contributions | |
ilon | -0.042 |
earch | -0.042 |
Daddy | -0.041 |
Strait | -0.039 |
WN | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
ilon | +0.020 |
earch | +0.020 |
Daddy | +0.019 |
Strait | +0.018 |
WN | +0.018 |
Neg logit contributions | |
gradation | -0.023 |
================================= | -0.021 |
Templ | -0.020 |
�� | -0.020 |
clot | -0.019 |
Token | One |
Token ID | 3198 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
gradation | +0.043 |
================================= | +0.041 |
Templ | +0.039 |
�� | +0.037 |
clot | +0.036 |
Neg logit contributions | |
ilon | -0.036 |
earch | -0.035 |
Daddy | -0.035 |
Strait | -0.033 |
WN | -0.032 |
Token | finds |
Token ID | 7228 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ilon | +0.104 |
earch | +0.102 |
Daddy | +0.101 |
Strait | +0.097 |
WN | +0.092 |
Neg logit contributions | |
gradation | -0.120 |
================================= | -0.114 |
Templ | -0.108 |
�� | -0.104 |
clot | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ilon | +0.091 |
earch | +0.090 |
Daddy | +0.089 |
Strait | +0.085 |
WN | +0.080 |
Neg logit contributions | |
gradation | -0.109 |
================================= | -0.104 |
Templ | -0.098 |
�� | -0.095 |
clot | -0.092 |
Token | number |
Token ID | 1271 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ilon | +0.089 |
earch | +0.088 |
Daddy | +0.087 |
Strait | +0.083 |
WN | +0.079 |
Neg logit contributions | |
gradation | -0.102 |
================================= | -0.097 |
Templ | -0.092 |
�� | -0.089 |
clot | -0.086 |
Token | settled |
Token ID | 10282 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ilon | +0.075 |
earch | +0.074 |
Daddy | +0.073 |
Strait | +0.070 |
WN | +0.066 |
Neg logit contributions | |
gradation | -0.089 |
================================= | -0.085 |
Templ | -0.080 |
�� | -0.077 |
clot | -0.075 |
Token | [ |
Token ID | 685 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
ilon | +0.115 |
earch | +0.113 |
Daddy | +0.112 |
Strait | +0.107 |
WN | +0.101 |
Neg logit contributions | |
gradation | -0.144 |
================================= | -0.136 |
Templ | -0.130 |
�� | -0.125 |
clot | -0.122 |
Token | in |
Token ID | 259 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
gradation | +0.061 |
================================= | +0.058 |
Templ | +0.055 |
�� | +0.053 |
clot | +0.052 |
Neg logit contributions | |
ilon | -0.043 |
earch | -0.042 |
Daddy | -0.042 |
Strait | -0.039 |
WN | -0.037 |
Token | Chicago |
Token ID | 4842 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
gradation | +0.307 |
================================= | +0.291 |
Templ | +0.276 |
�� | +0.266 |
clot | +0.257 |
Neg logit contributions | |
ilon | -0.277 |
earch | -0.274 |
Daddy | -0.271 |
Strait | -0.259 |
WN | -0.246 |
Token | ] |
Token ID | 60 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
gradation | +0.240 |
================================= | +0.225 |
Templ | +0.211 |
�� | +0.202 |
clot | +0.194 |
Neg logit contributions | |
ilon | -0.302 |
earch | -0.299 |
Daddy | -0.297 |
Strait | -0.286 |
WN | -0.273 |
Token | and |
Token ID | 290 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
gradation | +0.114 |
================================= | +0.108 |
Templ | +0.103 |
�� | +0.100 |
clot | +0.097 |
Neg logit contributions | |
ilon | -0.091 |
earch | -0.090 |
Daddy | -0.089 |
Strait | -0.085 |
WN | -0.080 |
Token | organized |
Token ID | 8389 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
ilon | +0.175 |
earch | +0.173 |
Daddy | +0.171 |
Strait | +0.163 |
WN | +0.155 |
Neg logit contributions | |
gradation | -0.194 |
================================= | -0.184 |
Templ | -0.175 |
�� | -0.168 |
clot | -0.163 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ilon | +0.040 |
earch | +0.040 |
Daddy | +0.039 |
Strait | +0.037 |
WN | +0.035 |
Neg logit contributions | |
gradation | -0.049 |
================================= | -0.047 |
Templ | -0.044 |
�� | -0.043 |
clot | -0.041 |
Token | so |
Token ID | 523 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ilon | +0.070 |
earch | +0.069 |
Daddy | +0.068 |
Strait | +0.065 |
WN | +0.061 |
Neg logit contributions | |
gradation | -0.085 |
================================= | -0.081 |
Templ | -0.077 |
�� | -0.074 |
clot | -0.072 |
Token | maybe |
Token ID | 3863 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
gradation | +0.104 |
================================= | +0.098 |
Templ | +0.094 |
�� | +0.090 |
clot | +0.087 |
Neg logit contributions | |
ilon | -0.086 |
earch | -0.085 |
Daddy | -0.084 |
Strait | -0.080 |
WN | -0.076 |
Token | that |
Token ID | 326 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
gradation | +0.216 |
================================= | +0.205 |
Templ | +0.195 |
�� | +0.188 |
clot | +0.182 |
Neg logit contributions | |
ilon | -0.175 |
earch | -0.173 |
Daddy | -0.171 |
Strait | -0.163 |
WN | -0.154 |
Token | Arctic |
Token ID | 15723 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
gradation | +0.145 |
================================= | +0.138 |
Templ | +0.131 |
�� | +0.126 |
clot | +0.122 |
Neg logit contributions | |
ilon | -0.124 |
earch | -0.123 |
Daddy | -0.121 |
Strait | -0.116 |
WN | -0.110 |
Token | where |
Token ID | 810 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ilon | +0.169 |
earch | +0.167 |
Daddy | +0.166 |
Strait | +0.157 |
WN | +0.149 |
Neg logit contributions | |
gradation | -0.212 |
================================= | -0.202 |
Templ | -0.192 |
�� | -0.185 |
clot | -0.180 |
Token | operating |
Token ID | 5361 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
ilon | +0.112 |
earch | +0.111 |
Daddy | +0.110 |
Strait | +0.104 |
WN | +0.099 |
Neg logit contributions | |
gradation | -0.139 |
================================= | -0.132 |
Templ | -0.125 |
�� | -0.121 |
clot | -0.117 |
Token | conditions |
Token ID | 3403 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
gradation | +0.076 |
================================= | +0.072 |
Templ | +0.069 |
�� | +0.066 |
clot | +0.064 |
Neg logit contributions | |
ilon | -0.061 |
earch | -0.060 |
Daddy | -0.060 |
Strait | -0.057 |
WN | -0.054 |
Token | are |
Token ID | 389 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ilon | +0.392 |
earch | +0.387 |
Daddy | +0.385 |
Strait | +0.366 |
WN | +0.348 |
Neg logit contributions | |
gradation | -0.442 |
================================= | -0.419 |
Templ | -0.397 |
�� | -0.380 |
clot | -0.371 |
Token | beyond |
Token ID | 3675 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ilon | +0.386 |
earch | +0.381 |
Daddy | +0.379 |
Strait | +0.358 |
WN | +0.341 |
Neg logit contributions | |
gradation | -0.476 |
================================= | -0.452 |
Templ | -0.430 |
�� | -0.413 |
clot | -0.403 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
ilon | +0.184 |
earch | +0.181 |
Daddy | +0.180 |
Strait | +0.171 |
WN | +0.162 |
Neg logit contributions | |
gradation | -0.231 |
================================= | -0.219 |
Templ | -0.209 |
�� | -0.201 |
clot | -0.196 |
Token | capability |
Token ID | 12971 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ilon | +0.240 |
earch | +0.236 |
Daddy | +0.235 |
Strait | +0.221 |
WN | +0.209 |
Neg logit contributions | |
gradation | -0.332 |
================================= | -0.316 |
Templ | -0.301 |
�� | -0.291 |
clot | -0.283 |
Token | of |
Token ID | 286 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
ilon | +0.416 |
earch | +0.411 |
Daddy | +0.409 |
Strait | +0.388 |
WN | +0.369 |
Neg logit contributions | |
gradation | -0.467 |
================================= | -0.442 |
Templ | -0.420 |
�� | -0.404 |
clot | -0.391 |
Token | conventional |
Token ID | 10224 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ilon | +0.297 |
earch | +0.293 |
Daddy | +0.291 |
Strait | +0.275 |
WN | +0.262 |
Neg logit contributions | |
gradation | -0.359 |
================================= | -0.341 |
Templ | -0.325 |
�� | -0.312 |
clot | -0.304 |
Token | ice |
Token ID | 4771 |
Feature activation | -7.96e-03 |
Pos logit contributions | |
ilon | +0.204 |
earch | +0.202 |
Daddy | +0.200 |
Strait | +0.189 |
WN | +0.179 |
Neg logit contributions | |
gradation | -0.275 |
================================= | -0.262 |
Templ | -0.250 |
�� | -0.241 |
clot | -0.235 |
Token | do |
Token ID | 466 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
gradation | +0.053 |
================================= | +0.051 |
Templ | +0.048 |
�� | +0.046 |
clot | +0.045 |
Neg logit contributions | |
ilon | -0.046 |
earch | -0.045 |
Daddy | -0.045 |
Strait | -0.043 |
WN | -0.041 |
Token | believe |
Token ID | 1975 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
gradation | +0.046 |
================================= | +0.044 |
Templ | +0.042 |
�� | +0.040 |
clot | +0.039 |
Neg logit contributions | |
ilon | -0.039 |
earch | -0.038 |
Daddy | -0.038 |
Strait | -0.036 |
WN | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
gradation | +0.173 |
================================= | +0.164 |
Templ | +0.156 |
�� | +0.151 |
clot | +0.146 |
Neg logit contributions | |
ilon | -0.133 |
earch | -0.131 |
Daddy | -0.130 |
Strait | -0.123 |
WN | -0.116 |
Token | what |
Token ID | 644 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
gradation | +0.288 |
================================= | +0.273 |
Templ | +0.260 |
�� | +0.251 |
clot | +0.243 |
Neg logit contributions | |
ilon | -0.223 |
earch | -0.220 |
Daddy | -0.218 |
Strait | -0.208 |
WN | -0.195 |
Token | America |
Token ID | 2253 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
gradation | +0.018 |
================================= | +0.017 |
Templ | +0.016 |
�� | +0.016 |
clot | +0.015 |
Neg logit contributions | |
ilon | -0.016 |
earch | -0.016 |
Daddy | -0.016 |
Strait | -0.015 |
WN | -0.014 |
Token | ought |
Token ID | 10783 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ilon | +0.070 |
earch | +0.069 |
Daddy | +0.069 |
Strait | +0.065 |
WN | +0.062 |
Neg logit contributions | |
gradation | -0.074 |
================================= | -0.070 |
Templ | -0.067 |
�� | -0.064 |
clot | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
ilon | +0.070 |
earch | +0.069 |
Daddy | +0.069 |
Strait | +0.065 |
WN | +0.062 |
Neg logit contributions | |
gradation | -0.088 |
================================= | -0.083 |
Templ | -0.079 |
�� | -0.076 |
clot | -0.074 |
Token | do |
Token ID | 466 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
gradation | +0.018 |
================================= | +0.017 |
Templ | +0.016 |
�� | +0.015 |
clot | +0.015 |
Neg logit contributions | |
ilon | -0.020 |
earch | -0.020 |
Daddy | -0.020 |
Strait | -0.019 |
WN | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ilon | +0.150 |
earch | +0.149 |
Daddy | +0.147 |
Strait | +0.140 |
WN | +0.133 |
Neg logit contributions | |
gradation | -0.185 |
================================= | -0.176 |
Templ | -0.167 |
�� | -0.161 |
clot | -0.157 |
Token | immediately |
Token ID | 3393 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
gradation | +0.107 |
================================= | +0.102 |
Templ | +0.097 |
�� | +0.093 |
clot | +0.090 |
Neg logit contributions | |
ilon | -0.093 |
earch | -0.092 |
Daddy | -0.091 |
Strait | -0.087 |
WN | -0.082 |
Token | establish |
Token ID | 4474 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
gradation | +0.031 |
================================= | +0.029 |
Templ | +0.028 |
�� | +0.027 |
clot | +0.026 |
Neg logit contributions | |
ilon | -0.029 |
earch | -0.029 |
Daddy | -0.028 |
Strait | -0.027 |
WN | -0.026 |
Token | stem |
Token ID | 10717 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
ilon | +0.193 |
earch | +0.191 |
Daddy | +0.190 |
Strait | +0.181 |
WN | +0.172 |
Neg logit contributions | |
gradation | -0.196 |
================================= | -0.186 |
Templ | -0.175 |
�� | -0.168 |
clot | -0.163 |
Token | from |
Token ID | 422 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
gradation | +0.025 |
================================= | +0.023 |
Templ | +0.022 |
�� | +0.021 |
clot | +0.021 |
Neg logit contributions | |
ilon | -0.021 |
earch | -0.021 |
Daddy | -0.021 |
Strait | -0.020 |
WN | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
ilon | +0.048 |
earch | +0.047 |
Daddy | +0.047 |
Strait | +0.044 |
WN | +0.042 |
Neg logit contributions | |
gradation | -0.059 |
================================= | -0.056 |
Templ | -0.054 |
�� | -0.052 |
clot | -0.050 |
Token | presence |
Token ID | 4931 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ilon | +0.031 |
earch | +0.031 |
Daddy | +0.030 |
Strait | +0.029 |
WN | +0.028 |
Neg logit contributions | |
gradation | -0.034 |
================================= | -0.032 |
Templ | -0.030 |
�� | -0.029 |
clot | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
ilon | +0.144 |
earch | +0.142 |
Daddy | +0.141 |
Strait | +0.134 |
WN | +0.127 |
Neg logit contributions | |
gradation | -0.164 |
================================= | -0.155 |
Templ | -0.148 |
�� | -0.142 |
clot | -0.138 |
Token | Fowler |
Token ID | 33693 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
gradation | +0.038 |
================================= | +0.036 |
Templ | +0.034 |
�� | +0.033 |
clot | +0.032 |
Neg logit contributions | |
ilon | -0.031 |
earch | -0.030 |
Daddy | -0.030 |
Strait | -0.029 |
WN | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ilon | +0.102 |
earch | +0.100 |
Daddy | +0.100 |
Strait | +0.095 |
WN | +0.090 |
Neg logit contributions | |
gradation | -0.123 |
================================= | -0.116 |
Templ | -0.111 |
�� | -0.107 |
clot | -0.104 |
Token | who |
Token ID | 508 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
ilon | +0.146 |
earch | +0.144 |
Daddy | +0.143 |
Strait | +0.136 |
WN | +0.129 |
Neg logit contributions | |
gradation | -0.174 |
================================= | -0.166 |
Templ | -0.157 |
�� | -0.151 |
clot | -0.147 |
Token | has |
Token ID | 468 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ilon | +0.038 |
earch | +0.037 |
Daddy | +0.037 |
Strait | +0.035 |
WN | +0.033 |
Neg logit contributions | |
gradation | -0.042 |
================================= | -0.040 |
Templ | -0.038 |
�� | -0.037 |
clot | -0.036 |
Token | said |
Token ID | 531 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
gradation | +0.155 |
================================= | +0.147 |
Templ | +0.139 |
�� | +0.134 |
clot | +0.129 |
Neg logit contributions | |
ilon | -0.142 |
earch | -0.141 |
Daddy | -0.140 |
Strait | -0.133 |
WN | -0.127 |
Token | all |
Token ID | 477 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
gradation | +0.132 |
================================= | +0.125 |
Templ | +0.119 |
�� | +0.115 |
clot | +0.111 |
Neg logit contributions | |
ilon | -0.115 |
earch | -0.114 |
Daddy | -0.113 |
Strait | -0.108 |
WN | -0.102 |
Token | routinely |
Token ID | 16231 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
ilon | +0.163 |
earch | +0.161 |
Daddy | +0.160 |
Strait | +0.152 |
WN | +0.144 |
Neg logit contributions | |
gradation | -0.189 |
================================= | -0.179 |
Templ | -0.170 |
�� | -0.164 |
clot | -0.159 |
Token | delayed |
Token ID | 11038 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
gradation | +0.063 |
================================= | +0.060 |
Templ | +0.057 |
�� | +0.055 |
clot | +0.053 |
Neg logit contributions | |
ilon | -0.053 |
earch | -0.053 |
Daddy | -0.052 |
Strait | -0.050 |
WN | -0.047 |
Token | by |
Token ID | 416 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
gradation | +0.048 |
================================= | +0.046 |
Templ | +0.044 |
�� | +0.042 |
clot | +0.041 |
Neg logit contributions | |
ilon | -0.040 |
earch | -0.040 |
Daddy | -0.039 |
Strait | -0.037 |
WN | -0.035 |
Token | private |
Token ID | 2839 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
gradation | +0.081 |
================================= | +0.077 |
Templ | +0.073 |
�� | +0.071 |
clot | +0.068 |
Neg logit contributions | |
ilon | -0.067 |
earch | -0.067 |
Daddy | -0.066 |
Strait | -0.063 |
WN | -0.059 |
Token | automobile |
Token ID | 27930 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ilon | +0.132 |
earch | +0.131 |
Daddy | +0.130 |
Strait | +0.124 |
WN | +0.118 |
Neg logit contributions | |
gradation | -0.137 |
================================= | -0.130 |
Templ | -0.123 |
�� | -0.118 |
clot | -0.114 |
Token | drivers |
Token ID | 6643 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ilon | +0.205 |
earch | +0.203 |
Daddy | +0.201 |
Strait | +0.190 |
WN | +0.181 |
Neg logit contributions | |
gradation | -0.253 |
================================= | -0.240 |
Templ | -0.229 |
�� | -0.220 |
clot | -0.214 |
Token | blocking |
Token ID | 12013 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ilon | +0.101 |
earch | +0.100 |
Daddy | +0.099 |
Strait | +0.094 |
WN | +0.089 |
Neg logit contributions | |
gradation | -0.121 |
================================= | -0.115 |
Templ | -0.110 |
�� | -0.105 |
clot | -0.102 |
Token | boarding |
Token ID | 25523 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ilon | +0.021 |
earch | +0.021 |
Daddy | +0.021 |
Strait | +0.020 |
WN | +0.019 |
Neg logit contributions | |
gradation | -0.026 |
================================= | -0.025 |
Templ | -0.024 |
�� | -0.023 |
clot | -0.022 |
Token | islands |
Token ID | 14807 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
gradation | +0.257 |
================================= | +0.244 |
Templ | +0.231 |
�� | +0.223 |
clot | +0.216 |
Neg logit contributions | |
ilon | -0.226 |
earch | -0.223 |
Daddy | -0.221 |
Strait | -0.212 |
WN | -0.200 |
Token | and |
Token ID | 290 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
gradation | +0.024 |
================================= | +0.022 |
Templ | +0.021 |
�� | +0.021 |
clot | +0.020 |
Neg logit contributions | |
ilon | -0.019 |
earch | -0.019 |
Daddy | -0.019 |
Strait | -0.018 |
WN | -0.017 |
Token | waiting |
Token ID | 4953 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ilon | +0.032 |
earch | +0.032 |
Daddy | +0.032 |
Strait | +0.030 |
WN | +0.029 |
Neg logit contributions | |
gradation | -0.038 |
================================= | -0.036 |
Templ | -0.034 |
�� | -0.033 |
clot | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
gradation | +0.082 |
================================= | +0.078 |
Templ | +0.074 |
�� | +0.072 |
clot | +0.069 |
Neg logit contributions | |
ilon | -0.071 |
earch | -0.070 |
Daddy | -0.070 |
Strait | -0.067 |
WN | -0.063 |
Token | St |
Token ID | 1273 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gradation | +0.238 |
================================= | +0.225 |
Templ | +0.213 |
�� | +0.204 |
clot | +0.197 |
Neg logit contributions | |
ilon | -0.241 |
earch | -0.237 |
Daddy | -0.237 |
Strait | -0.226 |
WN | -0.215 |
Token | umble |
Token ID | 10344 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
gradation | +0.769 |
================================= | +0.693 |
Templ | +0.645 |
�� | +0.630 |
clot | +0.583 |
Neg logit contributions | |
ilon | -1.345 |
earch | -1.326 |
Daddy | -1.326 |
Strait | -1.271 |
WN | -1.233 |
Token | Upon |
Token ID | 23792 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
ilon | +0.255 |
earch | +0.252 |
Daddy | +0.247 |
Strait | +0.236 |
ktop | +0.221 |
Neg logit contributions | |
gradation | -0.376 |
================================= | -0.360 |
Templ | -0.343 |
�� | -0.330 |
clot | -0.323 |
Token | What |
Token ID | 1867 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
ilon | +0.398 |
earch | +0.396 |
Daddy | +0.390 |
Strait | +0.375 |
ktop | +0.360 |
Neg logit contributions | |
gradation | -0.330 |
================================= | -0.313 |
Templ | -0.293 |
�� | -0.278 |
clot | -0.270 |
Token | are |
Token ID | 389 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ilon | +0.211 |
earch | +0.209 |
Daddy | +0.207 |
Strait | +0.198 |
ktop | +0.187 |
Neg logit contributions | |
gradation | -0.243 |
================================= | -0.231 |
Templ | -0.220 |
�� | -0.211 |
clot | -0.205 |
Token | these |
Token ID | 777 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ilon | +1.178 |
earch | +1.156 |
Daddy | +1.134 |
Strait | +1.093 |
ktop | +1.042 |
Neg logit contributions | |
gradation | -1.363 |
================================= | -1.313 |
Templ | -1.253 |
clot | -1.183 |
�� | -1.183 |
Token | ? |
Token ID | 30 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ilon | +1.100 |
earch | +1.088 |
Daddy | +1.072 |
Strait | +1.044 |
ktop | +1.003 |
Neg logit contributions | |
gradation | -0.814 |
================================= | -0.778 |
Templ | -0.722 |
�� | -0.675 |
clot | -0.666 |
Token | E |
Token ID | 412 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ilon | +0.013 |
earch | +0.013 |
Daddy | +0.013 |
Strait | +0.012 |
WN | +0.012 |
Neg logit contributions | |
gradation | -0.014 |
================================= | -0.013 |
Templ | -0.012 |
�� | -0.012 |
clot | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ilon | +0.314 |
earch | +0.311 |
Daddy | +0.307 |
Strait | +0.291 |
wcsstore | +0.274 |
Neg logit contributions | |
gradation | -0.397 |
================================= | -0.379 |
Templ | -0.360 |
�� | -0.344 |
jar | -0.337 |
Token | mail |
Token ID | 4529 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ilon | +0.026 |
earch | +0.026 |
Daddy | +0.026 |
Strait | +0.025 |
WN | +0.024 |
Neg logit contributions | |
gradation | -0.020 |
================================= | -0.019 |
Templ | -0.017 |
�� | -0.017 |
clot | -0.016 |
Token | House |
Token ID | 18102 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
gradation | +0.228 |
================================= | +0.217 |
Templ | +0.206 |
�� | +0.199 |
clot | +0.193 |
Neg logit contributions | |
ilon | -0.182 |
earch | -0.180 |
Daddy | -0.179 |
Strait | -0.169 |
WN | -0.160 |
Token | committee |
Token ID | 5583 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ilon | +0.117 |
earch | +0.116 |
Daddy | +0.115 |
Strait | +0.110 |
WN | +0.105 |
Neg logit contributions | |
gradation | -0.117 |
================================= | -0.111 |
Templ | -0.105 |
�� | -0.101 |
clot | -0.097 |
Token | believes |
Token ID | 5804 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
gradation | +0.389 |
================================= | +0.369 |
Templ | +0.351 |
�� | +0.336 |
clot | +0.327 |
Neg logit contributions | |
ilon | -0.323 |
earch | -0.320 |
Daddy | -0.317 |
Strait | -0.302 |
WN | -0.285 |
Token | it |
Token ID | 340 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
gradation | +0.551 |
================================= | +0.526 |
Templ | +0.501 |
�� | +0.482 |
clot | +0.466 |
Neg logit contributions | |
ilon | -0.415 |
earch | -0.412 |
Daddy | -0.406 |
Strait | -0.387 |
WN | -0.364 |
Token | has |
Token ID | 468 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gradation | +0.270 |
================================= | +0.257 |
Templ | +0.244 |
�� | +0.235 |
clot | +0.227 |
Neg logit contributions | |
ilon | -0.229 |
earch | -0.226 |
Daddy | -0.225 |
Strait | -0.215 |
WN | -0.202 |
Token | evidence |
Token ID | 2370 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
gradation | +1.048 |
================================= | +0.988 |
Templ | +0.927 |
�� | +0.901 |
jar | +0.854 |
Neg logit contributions | |
ilon | -1.060 |
earch | -1.058 |
Daddy | -1.049 |
Strait | -1.011 |
Hus | -0.960 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ilon | +1.461 |
earch | +1.452 |
Daddy | +1.443 |
Strait | +1.389 |
ktop | +1.343 |
Neg logit contributions | |
gradation | -1.569 |
================================= | -1.520 |
Templ | -1.450 |
clot | -1.409 |
�� | -1.366 |
Token | requested |
Token ID | 9167 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
gradation | +1.190 |
================================= | +1.127 |
Templ | +1.062 |
�� | +1.038 |
clot | +0.992 |
Neg logit contributions | |
ilon | -0.875 |
Daddy | -0.861 |
earch | -0.849 |
Strait | -0.814 |
WN | -0.769 |
Token | putting |
Token ID | 5137 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
gradation | +0.599 |
================================= | +0.564 |
Templ | +0.533 |
�� | +0.518 |
jar | +0.496 |
Neg logit contributions | |
ilon | -0.509 |
earch | -0.501 |
Daddy | -0.499 |
Strait | -0.475 |
WN | -0.447 |
Token | ally |
Token ID | 12525 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilon | +0.338 |
earch | +0.336 |
Daddy | +0.334 |
Strait | +0.316 |
ktop | +0.302 |
Neg logit contributions | |
gradation | -0.364 |
================================= | -0.344 |
Templ | -0.329 |
�� | -0.313 |
clot | -0.307 |
Token | in |
Token ID | 287 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
gradation | +0.162 |
================================= | +0.155 |
Templ | +0.147 |
�� | +0.142 |
clot | +0.138 |
Neg logit contributions | |
ilon | -0.122 |
earch | -0.120 |
Daddy | -0.120 |
Strait | -0.114 |
WN | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
gradation | +0.085 |
================================= | +0.080 |
Templ | +0.076 |
�� | +0.073 |
clot | +0.071 |
Neg logit contributions | |
ilon | -0.073 |
earch | -0.072 |
Daddy | -0.072 |
Strait | -0.068 |
WN | -0.065 |
Token | St |
Token ID | 1273 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
gradation | +0.160 |
================================= | +0.151 |
Templ | +0.143 |
�� | +0.137 |
clot | +0.133 |
Neg logit contributions | |
ilon | -0.164 |
earch | -0.161 |
Daddy | -0.161 |
Strait | -0.153 |
WN | -0.146 |
Token | umble |
Token ID | 10344 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
gradation | +0.837 |
================================= | +0.754 |
Templ | +0.703 |
�� | +0.689 |
clot | +0.636 |
Neg logit contributions | |
ilon | -1.452 |
Daddy | -1.435 |
earch | -1.434 |
Strait | -1.372 |
WN | -1.331 |
Token | Upon |
Token ID | 23792 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ilon | +0.178 |
earch | +0.176 |
Daddy | +0.173 |
Strait | +0.164 |
ktop | +0.154 |
Neg logit contributions | |
gradation | -0.265 |
================================= | -0.253 |
Templ | -0.242 |
�� | -0.233 |
clot | -0.228 |
Token | What |
Token ID | 1867 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
ilon | +0.490 |
earch | +0.489 |
Daddy | +0.480 |
Strait | +0.462 |
ktop | +0.444 |
Neg logit contributions | |
gradation | -0.403 |
================================= | -0.382 |
Templ | -0.358 |
�� | -0.340 |
clot | -0.330 |
Token | are |
Token ID | 389 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ilon | +0.063 |
earch | +0.062 |
Daddy | +0.062 |
Strait | +0.059 |
WN | +0.056 |
Neg logit contributions | |
gradation | -0.073 |
================================= | -0.070 |
Templ | -0.066 |
�� | -0.064 |
clot | -0.062 |
Token | these |
Token ID | 777 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ilon | +0.929 |
earch | +0.912 |
Daddy | +0.895 |
Strait | +0.862 |
ktop | +0.819 |
Neg logit contributions | |
gradation | -1.106 |
================================= | -1.066 |
Templ | -1.014 |
�� | -0.964 |
clot | -0.956 |
Token | ? |
Token ID | 30 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ilon | +0.990 |
earch | +0.984 |
Daddy | +0.968 |
Strait | +0.939 |
ktop | +0.904 |
Neg logit contributions | |
gradation | -0.739 |
================================= | -0.707 |
Templ | -0.656 |
�� | -0.615 |
clot | -0.604 |
Token | E |
Token ID | 412 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ilon | +0.089 |
earch | +0.088 |
Daddy | +0.087 |
Strait | +0.083 |
WN | +0.079 |
Neg logit contributions | |
gradation | -0.091 |
================================= | -0.086 |
Templ | -0.082 |
�� | -0.078 |
clot | -0.076 |
Token | - |
Token ID | 12 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ilon | +0.382 |
earch | +0.378 |
Daddy | +0.373 |
Strait | +0.354 |
wcsstore | +0.334 |
Neg logit contributions | |
gradation | -0.480 |
================================= | -0.458 |
Templ | -0.434 |
�� | -0.415 |
clot | -0.407 |
Token | mail |
Token ID | 4529 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ilon | +0.107 |
earch | +0.106 |
Daddy | +0.105 |
Strait | +0.101 |
ktop | +0.097 |
Neg logit contributions | |
gradation | -0.080 |
================================= | -0.075 |
Templ | -0.070 |
�� | -0.067 |
clot | -0.064 |
Token | into |
Token ID | 656 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ilon | +0.234 |
earch | +0.231 |
Daddy | +0.229 |
Strait | +0.217 |
WN | +0.206 |
Neg logit contributions | |
gradation | -0.282 |
================================= | -0.267 |
Templ | -0.254 |
�� | -0.244 |
clot | -0.238 |
Token | an |
Token ID | 281 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ilon | +0.070 |
earch | +0.070 |
Daddy | +0.069 |
Strait | +0.065 |
WN | +0.062 |
Neg logit contributions | |
gradation | -0.088 |
================================= | -0.084 |
Templ | -0.080 |
�� | -0.077 |
clot | -0.074 |
Token | all |
Token ID | 477 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
ilon | +0.162 |
earch | +0.159 |
Daddy | +0.158 |
Strait | +0.150 |
WN | +0.142 |
Neg logit contributions | |
gradation | -0.212 |
================================= | -0.201 |
Templ | -0.192 |
�� | -0.185 |
clot | -0.180 |
Token | - |
Token ID | 12 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ilon | +0.337 |
earch | +0.331 |
Daddy | +0.329 |
Strait | +0.312 |
WN | +0.295 |
Neg logit contributions | |
gradation | -0.431 |
================================= | -0.410 |
Templ | -0.390 |
�� | -0.376 |
clot | -0.366 |
Token | new |
Token ID | 3605 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ilon | +0.351 |
earch | +0.347 |
Daddy | +0.344 |
Strait | +0.331 |
WN | +0.316 |
Neg logit contributions | |
gradation | -0.286 |
================================= | -0.268 |
Templ | -0.252 |
�� | -0.240 |
clot | -0.232 |
Token | Ter |
Token ID | 3813 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ilon | +0.271 |
earch | +0.267 |
Daddy | +0.265 |
Strait | +0.251 |
WN | +0.238 |
Neg logit contributions | |
gradation | -0.353 |
================================= | -0.336 |
Templ | -0.320 |
�� | -0.308 |
clot | -0.300 |
Token | rain |
Token ID | 3201 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
ilon | +1.036 |
earch | +1.026 |
Daddy | +1.015 |
Strait | +0.977 |
WN | +0.940 |
Neg logit contributions | |
gradation | -0.970 |
================================= | -0.910 |
Templ | -0.854 |
�� | -0.809 |
jar | -0.797 |
Token | Management |
Token ID | 8549 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ilon | +0.428 |
earch | +0.420 |
Daddy | +0.417 |
Strait | +0.396 |
WN | +0.375 |
Neg logit contributions | |
gradation | -0.551 |
================================= | -0.524 |
Templ | -0.500 |
�� | -0.480 |
clot | -0.467 |
Token | System |
Token ID | 4482 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ilon | +0.246 |
earch | +0.242 |
Daddy | +0.240 |
Strait | +0.226 |
WN | +0.213 |
Neg logit contributions | |
gradation | -0.356 |
================================= | -0.340 |
Templ | -0.325 |
�� | -0.313 |
clot | -0.305 |
Token | ™ |
Token ID | 8151 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ilon | +0.387 |
earch | +0.381 |
Daddy | +0.379 |
Strait | +0.360 |
ktop | +0.341 |
Neg logit contributions | |
gradation | -0.473 |
================================= | -0.449 |
Templ | -0.428 |
�� | -0.410 |
clot | -0.400 |
Token | that |
Token ID | 326 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ilon | +0.336 |
earch | +0.331 |
Daddy | +0.329 |
Strait | +0.312 |
ktop | +0.295 |
Neg logit contributions | |
gradation | -0.419 |
================================= | -0.398 |
Templ | -0.379 |
�� | -0.364 |
clot | -0.355 |
Token | " |
Token ID | 366 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
ilon | +0.067 |
earch | +0.067 |
Daddy | +0.066 |
Strait | +0.063 |
WN | +0.060 |
Neg logit contributions | |
gradation | -0.074 |
================================= | -0.070 |
Templ | -0.067 |
�� | -0.064 |
clot | -0.062 |
Token | One |
Token ID | 3198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ilon | +0.251 |
earch | +0.248 |
Daddy | +0.245 |
Strait | +0.234 |
ktop | +0.222 |
Neg logit contributions | |
gradation | -0.299 |
================================= | -0.284 |
Templ | -0.270 |
�� | -0.259 |
clot | -0.251 |
Token | Fle |
Token ID | 12005 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ilon | +0.890 |
earch | +0.886 |
Daddy | +0.867 |
Strait | +0.819 |
ktop | +0.786 |
Neg logit contributions | |
gradation | -1.227 |
================================= | -1.178 |
Templ | -1.127 |
�� | -1.072 |
clot | -1.051 |
Token | w |
Token ID | 86 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
gradation | +0.178 |
================================= | +0.171 |
Templ | +0.164 |
�� | +0.159 |
clot | +0.155 |
Neg logit contributions | |
ilon | -0.095 |
earch | -0.093 |
Daddy | -0.092 |
Strait | -0.086 |
WN | -0.080 |
Token | Over |
Token ID | 3827 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ilon | +0.145 |
earch | +0.144 |
Daddy | +0.142 |
Strait | +0.136 |
WN | +0.129 |
Neg logit contributions | |
gradation | -0.160 |
================================= | -0.152 |
Templ | -0.144 |
�� | -0.138 |
clot | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
gradation | +0.087 |
================================= | +0.083 |
Templ | +0.079 |
�� | +0.076 |
clot | +0.074 |
Neg logit contributions | |
ilon | -0.065 |
earch | -0.064 |
Daddy | -0.064 |
Strait | -0.060 |
WN | -0.057 |
Token | C |
Token ID | 327 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
earch | +1.477 |
ilon | +1.421 |
Daddy | +1.370 |
ktop | +1.314 |
Strait | +1.271 |
Neg logit contributions | |
gradation | -2.148 |
================================= | -2.095 |
Templ | -2.026 |
�� | -1.919 |
』 | -1.883 |
Token | uck |
Token ID | 1347 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ilon | +0.370 |
earch | +0.366 |
Daddy | +0.364 |
Strait | +0.346 |
ktop | +0.333 |
Neg logit contributions | |
gradation | -0.379 |
================================= | -0.360 |
Templ | -0.340 |
�� | -0.325 |
jar | -0.317 |
Token | oo |
Token ID | 2238 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
gradation | +0.405 |
================================= | +0.385 |
Templ | +0.369 |
�� | +0.358 |
clot | +0.346 |
Neg logit contributions | |
ilon | -0.269 |
earch | -0.264 |
Daddy | -0.263 |
Strait | -0.249 |
WN | -0.232 |
Token | 's |
Token ID | 338 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ilon | +0.441 |
earch | +0.438 |
Daddy | +0.432 |
Strait | +0.407 |
ktop | +0.392 |
Neg logit contributions | |
gradation | -0.534 |
================================= | -0.509 |
Templ | -0.483 |
�� | -0.463 |
clot | -0.453 |
Token | Nest |
Token ID | 21420 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
ilon | +1.055 |
earch | +1.043 |
Daddy | +1.011 |
Strait | +0.939 |
ktop | +0.915 |
Neg logit contributions | |
gradation | -1.749 |
================================= | -1.719 |
Templ | -1.640 |
�� | -1.560 |
jar | -1.537 |