Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ment | +0.192 |
heid | +0.185 |
grave | +0.183 |
uph | +0.172 |
alis | +0.169 |
Neg logit contributions | |
itle | -0.226 |
Huss | -0.223 |
rooms | -0.214 |
ollow | -0.205 |
gdala | -0.204 |
Token | as |
Token ID | 355 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ment | +0.088 |
heid | +0.085 |
grave | +0.084 |
uph | +0.079 |
alis | +0.078 |
Neg logit contributions | |
itle | -0.101 |
Huss | -0.100 |
rooms | -0.095 |
ollow | -0.092 |
gdala | -0.091 |
Token | Louisiana |
Token ID | 13340 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ment | +0.352 |
heid | +0.338 |
grave | +0.336 |
uph | +0.315 |
alis | +0.310 |
Neg logit contributions | |
itle | -0.398 |
Huss | -0.393 |
rooms | -0.375 |
ollow | -0.360 |
gdala | -0.357 |
Token | Gov |
Token ID | 10964 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
itle | +0.151 |
Huss | +0.148 |
rooms | +0.142 |
ollow | +0.137 |
gdala | +0.136 |
Neg logit contributions | |
ment | -0.127 |
heid | -0.121 |
grave | -0.121 |
uph | -0.113 |
alis | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
itle | +0.142 |
Huss | +0.140 |
rooms | +0.134 |
ollow | +0.129 |
gdala | +0.128 |
Neg logit contributions | |
ment | -0.118 |
heid | -0.113 |
grave | -0.112 |
uph | -0.105 |
alis | -0.103 |
Token | Bobby |
Token ID | 17155 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
itle | +0.456 |
Huss | +0.448 |
rooms | +0.432 |
ollow | +0.416 |
gdala | +0.415 |
Neg logit contributions | |
ment | -0.338 |
heid | -0.321 |
grave | -0.320 |
uph | -0.297 |
alis | -0.292 |
Token | Jindal |
Token ID | 49816 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
itle | +0.735 |
Huss | +0.701 |
rooms | +0.661 |
ollow | +0.600 |
gdala | +0.578 |
Neg logit contributions | |
ment | -2.397 |
grave | -2.323 |
heid | -2.319 |
uph | -2.227 |
alis | -2.200 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ment | +0.023 |
heid | +0.022 |
grave | +0.022 |
uph | +0.020 |
alis | +0.020 |
Neg logit contributions | |
itle | -0.028 |
Huss | -0.028 |
rooms | -0.027 |
ollow | -0.026 |
gdala | -0.026 |
Token | Heritage |
Token ID | 18518 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ment | +0.130 |
heid | +0.125 |
grave | +0.124 |
uph | +0.117 |
alis | +0.115 |
Neg logit contributions | |
itle | -0.146 |
Huss | -0.144 |
rooms | -0.138 |
ollow | -0.132 |
gdala | -0.131 |
Token | are |
Token ID | 389 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ment | +0.160 |
heid | +0.154 |
grave | +0.153 |
uph | +0.143 |
alis | +0.141 |
Neg logit contributions | |
itle | -0.182 |
Huss | -0.180 |
rooms | -0.172 |
ollow | -0.165 |
gdala | -0.164 |
Token | � |
Token ID | 564 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ment | +0.086 |
heid | +0.082 |
grave | +0.082 |
uph | +0.077 |
alis | +0.076 |
Neg logit contributions | |
itle | -0.090 |
Huss | -0.089 |
rooms | -0.085 |
ollow | -0.081 |
gdala | -0.081 |
Token | South |
Token ID | 2520 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
itle | +0.384 |
Huss | +0.376 |
rooms | +0.358 |
ollow | +0.342 |
gdala | +0.342 |
Neg logit contributions | |
ment | -0.417 |
heid | -0.401 |
grave | -0.398 |
uph | -0.376 |
alis | -0.370 |
Token | Australia |
Token ID | 4505 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
itle | +0.246 |
Huss | +0.242 |
rooms | +0.233 |
ollow | +0.224 |
gdala | +0.223 |
Neg logit contributions | |
ment | -0.200 |
heid | -0.191 |
grave | -0.190 |
uph | -0.177 |
alis | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ment | +0.651 |
heid | +0.629 |
grave | +0.628 |
uph | +0.589 |
inth | +0.579 |
Neg logit contributions | |
itle | -0.722 |
Huss | -0.715 |
rooms | -0.695 |
gdala | -0.656 |
ollow | -0.649 |
Token | As |
Token ID | 1081 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ment | +0.125 |
grave | +0.120 |
heid | +0.119 |
uph | +0.112 |
alis | +0.111 |
Neg logit contributions | |
itle | -0.124 |
Huss | -0.123 |
rooms | -0.117 |
ollow | -0.112 |
gdala | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ment | +0.189 |
heid | +0.180 |
grave | +0.180 |
uph | +0.169 |
alis | +0.167 |
Neg logit contributions | |
itle | -0.221 |
Huss | -0.218 |
rooms | -0.210 |
ollow | -0.201 |
gdala | -0.200 |
Token | news |
Token ID | 1705 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
itle | +0.199 |
Huss | +0.196 |
rooms | +0.188 |
ollow | +0.181 |
gdala | +0.181 |
Neg logit contributions | |
ment | -0.160 |
heid | -0.153 |
grave | -0.152 |
uph | -0.142 |
alis | -0.139 |
Token | organisation |
Token ID | 12684 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
itle | +1.208 |
Huss | +1.187 |
rooms | +1.087 |
ollow | +1.051 |
gdala | +1.050 |
Neg logit contributions | |
ment | -1.907 |
grave | -1.849 |
heid | -1.841 |
uph | -1.739 |
inth | -1.727 |
Token | it |
Token ID | 340 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
itle | +0.313 |
Huss | +0.308 |
rooms | +0.295 |
ollow | +0.283 |
gdala | +0.282 |
Neg logit contributions | |
ment | -0.280 |
heid | -0.268 |
grave | -0.266 |
uph | -0.249 |
alis | -0.246 |
Token | offers |
Token ID | 4394 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
ment | +1.043 |
grave | +1.016 |
heid | +1.009 |
inth | +0.931 |
uph | +0.929 |
Neg logit contributions | |
itle | -1.326 |
Huss | -1.303 |
rooms | -1.277 |
ollow | -1.211 |
gdala | -1.202 |
Token | an |
Token ID | 281 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ment | +0.588 |
grave | +0.566 |
heid | +0.562 |
uph | +0.530 |
alis | +0.519 |
Neg logit contributions | |
itle | -0.704 |
Huss | -0.701 |
rooms | -0.673 |
ollow | -0.648 |
gdala | -0.640 |
Token | alternative |
Token ID | 5559 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ment | +0.052 |
heid | +0.049 |
grave | +0.049 |
uph | +0.044 |
alis | +0.043 |
Neg logit contributions | |
itle | -0.094 |
Huss | -0.093 |
rooms | -0.090 |
ollow | -0.087 |
gdala | -0.086 |
Token | Donald |
Token ID | 3759 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
itle | +0.081 |
Huss | +0.080 |
rooms | +0.077 |
ollow | +0.074 |
gdala | +0.073 |
Neg logit contributions | |
ment | -0.069 |
heid | -0.067 |
grave | -0.066 |
uph | -0.062 |
alis | -0.061 |
Token | Trump |
Token ID | 1301 |
Feature activation | +8.07e-03 |
Pos logit contributions | |
itle | +0.249 |
Huss | +0.245 |
rooms | +0.232 |
ollow | +0.221 |
gdala | +0.220 |
Neg logit contributions | |
ment | -0.317 |
heid | -0.306 |
grave | -0.304 |
uph | -0.288 |
alis | -0.285 |
Token | Donald |
Token ID | 3759 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
itle | +0.006 |
Huss | +0.006 |
rooms | +0.006 |
ollow | +0.006 |
gdala | +0.006 |
Neg logit contributions | |
ment | -0.005 |
heid | -0.005 |
grave | -0.005 |
uph | -0.005 |
alis | -0.005 |
Token | John |
Token ID | 1757 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
ment | +0.125 |
heid | +0.120 |
grave | +0.119 |
uph | +0.112 |
alis | +0.110 |
Neg logit contributions | |
itle | -0.141 |
Huss | -0.139 |
rooms | -0.133 |
ollow | -0.127 |
gdala | -0.127 |
Token | Trump |
Token ID | 1301 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
itle | +0.281 |
Huss | +0.276 |
rooms | +0.262 |
ollow | +0.249 |
gdala | +0.248 |
Neg logit contributions | |
ment | -0.358 |
heid | -0.345 |
grave | -0.343 |
uph | -0.325 |
alis | -0.321 |
Token | House |
Token ID | 18102 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
itle | +0.629 |
Huss | +0.619 |
rooms | +0.591 |
ollow | +0.566 |
gdala | +0.565 |
Neg logit contributions | |
ment | -0.603 |
heid | -0.577 |
grave | -0.574 |
uph | -0.541 |
alis | -0.532 |
Token | committee |
Token ID | 5583 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
itle | +1.649 |
Huss | +1.626 |
rooms | +1.570 |
ollow | +1.508 |
gdala | +1.492 |
Neg logit contributions | |
ment | -1.460 |
heid | -1.374 |
grave | -1.359 |
uph | -1.275 |
tooth | -1.269 |
Token | believes |
Token ID | 5804 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ment | +0.130 |
heid | +0.126 |
grave | +0.124 |
uph | +0.116 |
alis | +0.115 |
Neg logit contributions | |
itle | -0.149 |
Huss | -0.147 |
rooms | -0.141 |
ollow | -0.135 |
gdala | -0.134 |
Token | it |
Token ID | 340 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
itle | +0.836 |
Huss | +0.819 |
rooms | +0.789 |
ollow | +0.757 |
gdala | +0.754 |
Neg logit contributions | |
ment | -0.774 |
grave | -0.739 |
heid | -0.738 |
uph | -0.690 |
alis | -0.682 |
Token | has |
Token ID | 468 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
itle | +0.068 |
Huss | +0.067 |
rooms | +0.064 |
ollow | +0.061 |
gdala | +0.061 |
Neg logit contributions | |
ment | -0.064 |
heid | -0.062 |
grave | -0.061 |
uph | -0.058 |
alis | -0.057 |
Token | evidence |
Token ID | 2370 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
itle | +0.234 |
Huss | +0.231 |
rooms | +0.223 |
ollow | +0.216 |
gdala | +0.216 |
Neg logit contributions | |
ment | -0.114 |
heid | -0.107 |
grave | -0.106 |
uph | -0.096 |
alis | -0.094 |
Token | Les |
Token ID | 11732 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
itle | +0.228 |
Huss | +0.225 |
rooms | +0.216 |
ollow | +0.207 |
gdala | +0.207 |
Neg logit contributions | |
ment | -0.184 |
heid | -0.175 |
grave | -0.174 |
uph | -0.163 |
alis | -0.160 |
Token | nar |
Token ID | 23955 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
ment | +0.018 |
heid | +0.017 |
grave | +0.017 |
uph | +0.015 |
alis | +0.015 |
Neg logit contributions | |
itle | -0.028 |
Huss | -0.028 |
rooms | -0.027 |
ollow | -0.026 |
gdala | -0.026 |
Token | will |
Token ID | 481 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
itle | +0.462 |
Huss | +0.455 |
rooms | +0.437 |
ollow | +0.421 |
gdala | +0.419 |
Neg logit contributions | |
ment | -0.373 |
heid | -0.355 |
grave | -0.353 |
uph | -0.330 |
alis | -0.325 |
Token | face |
Token ID | 1986 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
itle | +0.377 |
Huss | +0.372 |
rooms | +0.357 |
ollow | +0.343 |
gdala | +0.342 |
Neg logit contributions | |
ment | -0.310 |
heid | -0.296 |
grave | -0.294 |
uph | -0.275 |
alis | -0.271 |
Token | Randy |
Token ID | 21248 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
itle | +0.327 |
Huss | +0.322 |
rooms | +0.310 |
ollow | +0.298 |
gdala | +0.297 |
Neg logit contributions | |
ment | -0.260 |
heid | -0.248 |
grave | -0.246 |
uph | -0.230 |
alis | -0.226 |
Token | Or |
Token ID | 1471 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
itle | +0.440 |
Huss | +0.431 |
rooms | +0.413 |
ollow | +0.394 |
gdala | +0.393 |
Neg logit contributions | |
ment | -0.495 |
heid | -0.475 |
grave | -0.473 |
uph | -0.446 |
alis | -0.441 |
Token | ton |
Token ID | 1122 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
itle | +1.721 |
Huss | +1.705 |
rooms | +1.629 |
ollow | +1.588 |
gdala | +1.583 |
Neg logit contributions | |
ment | -1.395 |
grave | -1.304 |
heid | -1.292 |
uph | -1.195 |
inth | -1.185 |
Token | at |
Token ID | 379 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
itle | +0.467 |
Huss | +0.459 |
rooms | +0.442 |
ollow | +0.425 |
gdala | +0.424 |
Neg logit contributions | |
ment | -0.370 |
heid | -0.353 |
grave | -0.351 |
uph | -0.327 |
alis | -0.323 |
Token | next |
Token ID | 1306 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
itle | +0.121 |
Huss | +0.119 |
rooms | +0.113 |
ollow | +0.108 |
gdala | +0.107 |
Neg logit contributions | |
ment | -0.141 |
heid | -0.136 |
grave | -0.135 |
uph | -0.127 |
alis | -0.126 |
Token | month |
Token ID | 1227 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
itle | +0.183 |
Huss | +0.180 |
rooms | +0.172 |
ollow | +0.165 |
gdala | +0.164 |
Neg logit contributions | |
ment | -0.177 |
heid | -0.170 |
grave | -0.169 |
uph | -0.159 |
alis | -0.156 |
Token | � |
Token ID | 447 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
itle | +0.309 |
Huss | +0.305 |
rooms | +0.293 |
ollow | +0.282 |
gdala | +0.281 |
Neg logit contributions | |
ment | -0.247 |
heid | -0.235 |
grave | -0.234 |
uph | -0.218 |
alis | -0.215 |
Token | Wisconsin |
Token ID | 9279 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ment | +0.222 |
heid | +0.214 |
grave | +0.212 |
uph | +0.198 |
alis | +0.195 |
Neg logit contributions | |
itle | -0.254 |
Huss | -0.251 |
rooms | -0.239 |
ollow | -0.230 |
gdala | -0.229 |
Token | conservative |
Token ID | 5940 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ment | +0.125 |
heid | +0.121 |
grave | +0.120 |
uph | +0.113 |
alis | +0.111 |
Neg logit contributions | |
itle | -0.120 |
Huss | -0.118 |
rooms | -0.113 |
ollow | -0.107 |
gdala | -0.107 |
Token | radio |
Token ID | 5243 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ment | +0.120 |
heid | +0.115 |
grave | +0.114 |
uph | +0.107 |
alis | +0.105 |
Neg logit contributions | |
itle | -0.139 |
Huss | -0.137 |
rooms | -0.131 |
ollow | -0.126 |
gdala | -0.125 |
Token | host |
Token ID | 2583 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ment | +0.010 |
heid | +0.010 |
grave | +0.010 |
uph | +0.009 |
alis | +0.009 |
Neg logit contributions | |
itle | -0.009 |
Huss | -0.009 |
rooms | -0.008 |
ollow | -0.008 |
gdala | -0.008 |
Token | Charlie |
Token ID | 11526 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
itle | +0.137 |
Huss | +0.135 |
rooms | +0.129 |
ollow | +0.124 |
gdala | +0.123 |
Neg logit contributions | |
ment | -0.121 |
heid | -0.116 |
grave | -0.115 |
uph | -0.108 |
alis | -0.106 |
Token | Sy |
Token ID | 1632 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
itle | +0.438 |
Huss | +0.430 |
rooms | +0.413 |
ollow | +0.396 |
gdala | +0.395 |
Neg logit contributions | |
ment | -0.392 |
heid | -0.375 |
grave | -0.373 |
uph | -0.349 |
alis | -0.345 |
Token | kes |
Token ID | 5209 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
itle | +1.567 |
Huss | +1.544 |
rooms | +1.503 |
ollow | +1.423 |
gdala | +1.421 |
Neg logit contributions | |
ment | -1.503 |
heid | -1.425 |
grave | -1.423 |
uph | -1.317 |
alis | -1.308 |
Token | , |
Token ID | 11 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
itle | +0.092 |
Huss | +0.090 |
rooms | +0.087 |
ollow | +0.083 |
gdala | +0.083 |
Neg logit contributions | |
ment | -0.077 |
heid | -0.074 |
grave | -0.073 |
uph | -0.069 |
alis | -0.067 |
Token | announced |
Token ID | 3414 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ment | +0.030 |
heid | +0.029 |
grave | +0.029 |
uph | +0.027 |
alis | +0.027 |
Neg logit contributions | |
itle | -0.036 |
Huss | -0.035 |
rooms | -0.034 |
ollow | -0.033 |
gdala | -0.032 |
Token | that |
Token ID | 326 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
itle | +0.014 |
Huss | +0.013 |
rooms | +0.013 |
ollow | +0.012 |
gdala | +0.012 |
Neg logit contributions | |
ment | -0.011 |
heid | -0.011 |
grave | -0.011 |
uph | -0.010 |
alis | -0.010 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
ment | +0.022 |
heid | +0.021 |
grave | +0.021 |
uph | +0.020 |
alis | +0.020 |
Neg logit contributions | |
itle | -0.025 |
Huss | -0.024 |
rooms | -0.023 |
ollow | -0.022 |
gdala | -0.022 |
Token | practice |
Token ID | 3357 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ment | +0.043 |
heid | +0.041 |
grave | +0.041 |
uph | +0.039 |
alis | +0.038 |
Neg logit contributions | |
itle | -0.052 |
Huss | -0.051 |
rooms | -0.049 |
ollow | -0.047 |
gdala | -0.047 |
Token | when |
Token ID | 618 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ment | +0.090 |
heid | +0.087 |
grave | +0.086 |
uph | +0.081 |
alis | +0.079 |
Neg logit contributions | |
itle | -0.104 |
Huss | -0.102 |
rooms | -0.098 |
ollow | -0.094 |
gdala | -0.094 |
Token | cornerback |
Token ID | 26683 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
itle | +0.176 |
Huss | +0.173 |
rooms | +0.166 |
ollow | +0.160 |
gdala | +0.159 |
Neg logit contributions | |
ment | -0.145 |
heid | -0.139 |
grave | -0.138 |
uph | -0.129 |
alis | -0.127 |
Token | A |
Token ID | 317 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
itle | +0.083 |
Huss | +0.081 |
rooms | +0.078 |
ollow | +0.075 |
gdala | +0.075 |
Neg logit contributions | |
ment | -0.070 |
heid | -0.067 |
grave | -0.067 |
uph | -0.062 |
alis | -0.061 |
Token | q |
Token ID | 80 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
itle | +0.183 |
Huss | +0.180 |
rooms | +0.173 |
ollow | +0.167 |
gdala | +0.166 |
Neg logit contributions | |
ment | -0.136 |
heid | -0.129 |
grave | -0.128 |
uph | -0.119 |
alis | -0.117 |
Token | ib |
Token ID | 571 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
itle | +0.919 |
Huss | +0.909 |
rooms | +0.875 |
gdala | +0.847 |
ollow | +0.845 |
Neg logit contributions | |
ment | -0.554 |
heid | -0.522 |
grave | -0.517 |
uph | -0.477 |
alis | -0.470 |
Token | Tal |
Token ID | 7193 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
itle | +1.570 |
Huss | +1.525 |
rooms | +1.506 |
gdala | +1.435 |
ollow | +1.423 |
Neg logit contributions | |
ment | -1.444 |
heid | -1.371 |
grave | -1.338 |
uph | -1.285 |
alis | -1.267 |
Token | ib |
Token ID | 571 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
ment | +0.128 |
heid | +0.121 |
grave | +0.120 |
uph | +0.111 |
alis | +0.109 |
Neg logit contributions | |
itle | -0.198 |
Huss | -0.195 |
rooms | -0.188 |
ollow | -0.182 |
gdala | -0.180 |
Token | jumped |
Token ID | 11687 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
itle | +0.159 |
Huss | +0.157 |
rooms | +0.151 |
ollow | +0.145 |
gdala | +0.144 |
Neg logit contributions | |
ment | -0.130 |
heid | -0.124 |
grave | -0.123 |
uph | -0.115 |
alis | -0.113 |
Token | an |
Token ID | 281 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
itle | +0.048 |
Huss | +0.047 |
rooms | +0.045 |
ollow | +0.043 |
gdala | +0.043 |
Neg logit contributions | |
ment | -0.037 |
heid | -0.035 |
grave | -0.035 |
uph | -0.033 |
alis | -0.032 |
Token | out |
Token ID | 503 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
ment | +0.007 |
heid | +0.007 |
grave | +0.007 |
uph | +0.006 |
alis | +0.006 |
Neg logit contributions | |
itle | -0.009 |
Huss | -0.009 |
rooms | -0.008 |
ollow | -0.008 |
gdala | -0.008 |
Token | Trevor |
Token ID | 25389 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ment | +0.102 |
heid | +0.098 |
grave | +0.097 |
uph | +0.091 |
alis | +0.089 |
Neg logit contributions | |
itle | -0.128 |
Huss | -0.126 |
rooms | -0.121 |
ollow | -0.116 |
gdala | -0.116 |
Token | Siem |
Token ID | 45196 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
itle | +0.947 |
Huss | +0.921 |
rooms | +0.884 |
gdala | +0.842 |
ollow | +0.838 |
Neg logit contributions | |
ment | -1.277 |
heid | -1.224 |
grave | -1.219 |
uph | -1.156 |
alis | -1.155 |
Token | ian |
Token ID | 666 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
itle | +0.725 |
Huss | +0.716 |
rooms | +0.689 |
gdala | +0.660 |
ollow | +0.660 |
Neg logit contributions | |
ment | -0.594 |
heid | -0.563 |
grave | -0.559 |
uph | -0.524 |
alis | -0.518 |
Token | and |
Token ID | 290 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
itle | +0.162 |
Huss | +0.160 |
rooms | +0.153 |
ollow | +0.147 |
gdala | +0.147 |
Neg logit contributions | |
ment | -0.132 |
heid | -0.126 |
grave | -0.125 |
uph | -0.117 |
alis | -0.115 |
Token | Pa |
Token ID | 11243 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
itle | +0.148 |
Huss | +0.145 |
rooms | +0.139 |
ollow | +0.134 |
gdala | +0.133 |
Neg logit contributions | |
ment | -0.133 |
heid | -0.127 |
grave | -0.126 |
uph | -0.119 |
alis | -0.117 |
Token | xton |
Token ID | 22874 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
itle | +0.041 |
Huss | +0.040 |
rooms | +0.038 |
ollow | +0.036 |
gdala | +0.035 |
Neg logit contributions | |
ment | -0.074 |
heid | -0.072 |
grave | -0.071 |
uph | -0.068 |
alis | -0.067 |
Token | Lynch |
Token ID | 16093 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
itle | +1.379 |
Huss | +1.335 |
rooms | +1.268 |
gdala | +1.222 |
ollow | +1.214 |
Neg logit contributions | |
ment | -1.636 |
heid | -1.558 |
grave | -1.534 |
uph | -1.460 |
alis | -1.458 |
Token | is |
Token ID | 318 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
itle | +0.317 |
Huss | +0.313 |
rooms | +0.300 |
ollow | +0.289 |
gdala | +0.288 |
Neg logit contributions | |
ment | -0.253 |
heid | -0.241 |
grave | -0.239 |
uph | -0.224 |
alis | -0.220 |
Token | the |
Token ID | 262 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
itle | +0.149 |
Huss | +0.147 |
rooms | +0.141 |
ollow | +0.135 |
gdala | +0.135 |
Neg logit contributions | |
ment | -0.129 |
heid | -0.123 |
grave | -0.122 |
uph | -0.114 |
alis | -0.113 |
Token | biggest |
Token ID | 4094 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
itle | +0.618 |
Huss | +0.608 |
rooms | +0.585 |
ollow | +0.562 |
gdala | +0.560 |
Neg logit contributions | |
ment | -0.508 |
heid | -0.483 |
grave | -0.481 |
uph | -0.450 |
alis | -0.443 |
Token | story |
Token ID | 1621 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
itle | +0.294 |
Huss | +0.290 |
rooms | +0.278 |
ollow | +0.268 |
gdala | +0.267 |
Neg logit contributions | |
ment | -0.233 |
heid | -0.223 |
grave | -0.221 |
uph | -0.206 |
alis | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
itle | +0.254 |
Huss | +0.249 |
rooms | +0.239 |
ollow | +0.229 |
gdala | +0.228 |
Neg logit contributions | |
ment | -0.235 |
heid | -0.225 |
grave | -0.223 |
uph | -0.210 |
alis | -0.207 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
itle | +0.148 |
Huss | +0.146 |
rooms | +0.140 |
ollow | +0.135 |
gdala | +0.134 |
Neg logit contributions | |
ment | -0.109 |
heid | -0.104 |
grave | -0.103 |
uph | -0.096 |
alis | -0.095 |
Token | Remember |
Token ID | 16676 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
itle | +0.192 |
Huss | +0.189 |
rooms | +0.181 |
ollow | +0.173 |
gdala | +0.172 |
Neg logit contributions | |
ment | -0.181 |
heid | -0.173 |
grave | -0.172 |
uph | -0.162 |
alis | -0.160 |
Token | Na |
Token ID | 11013 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
itle | +0.370 |
Huss | +0.364 |
rooms | +0.349 |
ollow | +0.336 |
gdala | +0.335 |
Neg logit contributions | |
ment | -0.313 |
heid | -0.299 |
grave | -0.297 |
uph | -0.278 |
alis | -0.273 |
Token | V |
Token ID | 53 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ment | +0.058 |
heid | +0.055 |
grave | +0.055 |
uph | +0.051 |
alis | +0.050 |
Neg logit contributions | |
itle | -0.081 |
Huss | -0.079 |
rooms | -0.076 |
ollow | -0.074 |
gdala | -0.073 |
Token | or |
Token ID | 273 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
itle | +0.426 |
Huss | +0.421 |
rooms | +0.400 |
ollow | +0.381 |
gdala | +0.381 |
Neg logit contributions | |
ment | -0.481 |
heid | -0.463 |
grave | -0.460 |
uph | -0.435 |
alis | -0.429 |
Token | ro |
Token ID | 305 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Huss | +1.032 |
itle | +1.026 |
rooms | +0.966 |
gdala | +0.914 |
ollow | +0.888 |
Neg logit contributions | |
ment | -1.939 |
heid | -1.846 |
grave | -1.830 |
uph | -1.773 |
inth | -1.750 |
Token | Bowman |
Token ID | 38774 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
itle | +0.076 |
Huss | +0.075 |
rooms | +0.071 |
ollow | +0.067 |
gdala | +0.066 |
Neg logit contributions | |
ment | -0.118 |
heid | -0.114 |
grave | -0.113 |
uph | -0.108 |
alis | -0.107 |
Token | at |
Token ID | 379 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
itle | +0.172 |
Huss | +0.169 |
rooms | +0.163 |
ollow | +0.156 |
gdala | +0.156 |
Neg logit contributions | |
ment | -0.132 |
heid | -0.126 |
grave | -0.125 |
uph | -0.117 |
alis | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
itle | +0.400 |
Huss | +0.394 |
rooms | +0.379 |
ollow | +0.364 |
gdala | +0.362 |
Neg logit contributions | |
ment | -0.340 |
heid | -0.325 |
grave | -0.323 |
uph | -0.302 |
alis | -0.298 |
Token | goal |
Token ID | 3061 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
itle | +0.057 |
Huss | +0.057 |
rooms | +0.054 |
ollow | +0.052 |
gdala | +0.052 |
Neg logit contributions | |
ment | -0.049 |
heid | -0.047 |
grave | -0.046 |
uph | -0.043 |
alis | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ment | +0.029 |
heid | +0.027 |
grave | +0.027 |
uph | +0.025 |
alis | +0.025 |
Neg logit contributions | |
itle | -0.036 |
Huss | -0.036 |
rooms | -0.034 |
ollow | -0.033 |
gdala | -0.033 |
Token | down |
Token ID | 866 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
itle | +0.179 |
Huss | +0.176 |
rooms | +0.169 |
ollow | +0.162 |
gdala | +0.162 |
Neg logit contributions | |
ment | -0.148 |
heid | -0.142 |
grave | -0.141 |
uph | -0.131 |
alis | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
itle | +0.075 |
Huss | +0.074 |
rooms | +0.071 |
ollow | +0.068 |
gdala | +0.068 |
Neg logit contributions | |
ment | -0.061 |
heid | -0.059 |
grave | -0.058 |
uph | -0.054 |
alis | -0.054 |
Token | eastern |
Token ID | 10183 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
itle | +0.189 |
Huss | +0.186 |
rooms | +0.178 |
ollow | +0.171 |
gdala | +0.170 |
Neg logit contributions | |
ment | -0.166 |
heid | -0.159 |
grave | -0.158 |
uph | -0.148 |
alis | -0.145 |
Token | se |
Token ID | 384 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ment | +0.092 |
heid | +0.089 |
grave | +0.089 |
uph | +0.083 |
alis | +0.082 |
Neg logit contributions | |
itle | -0.094 |
Huss | -0.093 |
rooms | -0.088 |
ollow | -0.085 |
gdala | -0.084 |
Token | ab |
Token ID | 397 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
itle | +1.135 |
Huss | +1.127 |
rooms | +1.080 |
gdala | +1.045 |
ollow | +1.043 |
Neg logit contributions | |
ment | -0.742 |
heid | -0.691 |
grave | -0.688 |
uph | -0.643 |
inth | -0.628 |
Token | oard |
Token ID | 11953 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
itle | +0.800 |
Huss | +0.796 |
rooms | +0.717 |
gdala | +0.672 |
ollow | +0.644 |
Neg logit contributions | |
ment | -2.150 |
heid | -2.070 |
grave | -2.054 |
uph | -1.985 |
inth | -1.969 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
ment | +0.142 |
heid | +0.136 |
grave | +0.135 |
uph | +0.126 |
alis | +0.123 |
Neg logit contributions | |
itle | -0.181 |
Huss | -0.178 |
rooms | -0.172 |
ollow | -0.165 |
gdala | -0.164 |
Token | They |
Token ID | 1119 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
itle | +0.014 |
Huss | +0.014 |
rooms | +0.013 |
ollow | +0.013 |
gdala | +0.013 |
Neg logit contributions | |
ment | -0.009 |
heid | -0.009 |
grave | -0.009 |
uph | -0.008 |
alis | -0.008 |
Token | now |
Token ID | 783 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
ment | +0.107 |
heid | +0.102 |
grave | +0.102 |
uph | +0.095 |
alis | +0.093 |
Neg logit contributions | |
itle | -0.137 |
Huss | -0.135 |
rooms | -0.130 |
ollow | -0.125 |
gdala | -0.124 |
Token | have |
Token ID | 423 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ment | +0.022 |
heid | +0.021 |
grave | +0.021 |
uph | +0.019 |
alis | +0.019 |
Neg logit contributions | |
itle | -0.028 |
Huss | -0.027 |
rooms | -0.026 |
ollow | -0.025 |
gdala | -0.025 |
Token | co |
Token ID | 763 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
itle | +0.079 |
Huss | +0.078 |
rooms | +0.075 |
ollow | +0.072 |
gdala | +0.072 |
Neg logit contributions | |
ment | -0.067 |
heid | -0.064 |
grave | -0.064 |
uph | -0.059 |
alis | -0.059 |
Token | - |
Token ID | 12 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ment | +0.620 |
heid | +0.597 |
grave | +0.592 |
uph | +0.553 |
alis | +0.544 |
Neg logit contributions | |
itle | -0.704 |
Huss | -0.693 |
rooms | -0.665 |
ollow | -0.637 |
gdala | -0.633 |
Token | founder |
Token ID | 15454 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ment | +0.167 |
heid | +0.159 |
grave | +0.157 |
uph | +0.144 |
alis | +0.141 |
Neg logit contributions | |
itle | -0.304 |
Huss | -0.300 |
rooms | -0.291 |
ollow | -0.280 |
gdala | -0.278 |
Token | Fred |
Token ID | 8559 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
ment | +0.143 |
heid | +0.138 |
grave | +0.137 |
uph | +0.127 |
alis | +0.125 |
Neg logit contributions | |
itle | -0.178 |
Huss | -0.176 |
rooms | -0.169 |
ollow | -0.162 |
gdala | -0.162 |
Token | Eh |
Token ID | 31480 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ment | +0.271 |
heid | +0.258 |
grave | +0.257 |
uph | +0.239 |
alis | +0.232 |
Neg logit contributions | |
itle | -0.417 |
Huss | -0.415 |
rooms | -0.397 |
ollow | -0.383 |
gdala | -0.382 |
Token | rs |
Token ID | 3808 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ment | +0.191 |
heid | +0.185 |
grave | +0.184 |
uph | +0.174 |
alis | +0.171 |
Neg logit contributions | |
itle | -0.176 |
Huss | -0.173 |
rooms | -0.166 |
ollow | -0.159 |
gdala | -0.156 |
Token | am |
Token ID | 321 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
itle | +0.904 |
Huss | +0.876 |
rooms | +0.821 |
gdala | +0.774 |
ollow | +0.737 |
Neg logit contributions | |
ment | -2.033 |
heid | -1.969 |
grave | -1.950 |
alis | -1.879 |
uph | -1.872 |
Token | emphasized |
Token ID | 20047 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
itle | +0.311 |
Huss | +0.306 |
rooms | +0.293 |
ollow | +0.281 |
gdala | +0.280 |
Neg logit contributions | |
ment | -0.288 |
heid | -0.275 |
grave | -0.274 |
uph | -0.257 |
alis | -0.253 |
Token | in |
Token ID | 287 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
itle | +0.065 |
Huss | +0.064 |
rooms | +0.061 |
ollow | +0.059 |
gdala | +0.059 |
Neg logit contributions | |
ment | -0.054 |
heid | -0.052 |
grave | -0.052 |
uph | -0.048 |
alis | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
itle | +0.083 |
Huss | +0.082 |
rooms | +0.078 |
ollow | +0.075 |
gdala | +0.075 |
Neg logit contributions | |
ment | -0.067 |
heid | -0.064 |
grave | -0.063 |
uph | -0.059 |
alis | -0.058 |
Token | past |
Token ID | 1613 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
itle | +0.100 |
Huss | +0.099 |
rooms | +0.095 |
ollow | +0.091 |
gdala | +0.090 |
Neg logit contributions | |
ment | -0.090 |
heid | -0.086 |
grave | -0.085 |
uph | -0.080 |
alis | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
itle | +0.454 |
Huss | +0.448 |
rooms | +0.431 |
ollow | +0.415 |
gdala | +0.414 |
Neg logit contributions | |
ment | -0.329 |
heid | -0.312 |
grave | -0.310 |
uph | -0.288 |
alis | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
itle | +0.085 |
Huss | +0.084 |
rooms | +0.081 |
ollow | +0.078 |
gdala | +0.077 |
Neg logit contributions | |
ment | -0.063 |
heid | -0.060 |
grave | -0.060 |
uph | -0.056 |
alis | -0.055 |
Token | Facebook |
Token ID | 12025 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
itle | +0.139 |
Huss | +0.136 |
rooms | +0.130 |
ollow | +0.125 |
gdala | +0.124 |
Neg logit contributions | |
ment | -0.148 |
heid | -0.143 |
grave | -0.142 |
uph | -0.134 |
alis | -0.132 |
Token |
|
Token ID | 198 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ment | +0.199 |
heid | +0.190 |
grave | +0.190 |
uph | +0.177 |
alis | +0.174 |
Neg logit contributions | |
itle | -0.263 |
Huss | -0.260 |
rooms | -0.249 |
ollow | -0.240 |
gdala | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
itle | +0.212 |
Huss | +0.209 |
rooms | +0.201 |
ollow | +0.193 |
gdala | +0.193 |
Neg logit contributions | |
ment | -0.156 |
heid | -0.148 |
grave | -0.147 |
uph | -0.137 |
alis | -0.135 |
Token | St |
Token ID | 1273 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
itle | +1.261 |
Huss | +1.243 |
rooms | +1.198 |
gdala | +1.166 |
ollow | +1.155 |
Neg logit contributions | |
ment | -0.745 |
heid | -0.697 |
grave | -0.689 |
uph | -0.642 |
alis | -0.626 |
Token | umble |
Token ID | 10344 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
itle | +1.034 |
Huss | +1.016 |
rooms | +0.943 |
gdala | +0.927 |
ollow | +0.900 |
Neg logit contributions | |
ment | -1.838 |
heid | -1.786 |
grave | -1.765 |
uph | -1.689 |
alis | -1.676 |
Token | Upon |
Token ID | 23792 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ment | +0.211 |
heid | +0.204 |
grave | +0.204 |
uph | +0.195 |
alis | +0.193 |
Neg logit contributions | |
itle | -0.110 |
Huss | -0.107 |
rooms | -0.101 |
ollow | -0.094 |
gdala | -0.093 |
Token | What |
Token ID | 1867 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
itle | +0.109 |
Huss | +0.108 |
rooms | +0.104 |
ollow | +0.100 |
gdala | +0.099 |
Neg logit contributions | |
ment | -0.084 |
heid | -0.080 |
grave | -0.080 |
uph | -0.074 |
alis | -0.073 |
Token | are |
Token ID | 389 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
itle | +0.051 |
Huss | +0.050 |
rooms | +0.049 |
ollow | +0.047 |
gdala | +0.047 |
Neg logit contributions | |
ment | -0.032 |
heid | -0.031 |
grave | -0.031 |
uph | -0.028 |
alis | -0.028 |
Token | these |
Token ID | 777 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
ment | +0.019 |
heid | +0.018 |
grave | +0.018 |
uph | +0.017 |
alis | +0.017 |
Neg logit contributions | |
itle | -0.024 |
Huss | -0.024 |
rooms | -0.023 |
ollow | -0.022 |
gdala | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ment | +0.275 |
heid | +0.266 |
grave | +0.264 |
uph | +0.245 |
alis | +0.243 |
Neg logit contributions | |
itle | -0.334 |
Huss | -0.328 |
rooms | -0.315 |
ollow | -0.303 |
gdala | -0.302 |
Token | charge |
Token ID | 3877 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ment | +0.902 |
heid | +0.888 |
grave | +0.862 |
uph | +0.818 |
alis | +0.813 |
Neg logit contributions | |
itle | -1.064 |
Huss | -1.057 |
rooms | -1.008 |
ollow | -0.964 |
gdala | -0.952 |
Token | of |
Token ID | 286 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
itle | +0.532 |
Huss | +0.522 |
rooms | +0.502 |
ollow | +0.482 |
gdala | +0.481 |
Neg logit contributions | |
ment | -0.449 |
heid | -0.429 |
grave | -0.425 |
uph | -0.398 |
alis | -0.392 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
itle | +0.695 |
Huss | +0.681 |
rooms | +0.655 |
ollow | +0.628 |
gdala | +0.628 |
Neg logit contributions | |
ment | -0.563 |
heid | -0.533 |
grave | -0.531 |
uph | -0.498 |
alis | -0.487 |
Token | probe |
Token ID | 12774 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
itle | +0.417 |
Huss | +0.410 |
rooms | +0.395 |
ollow | +0.380 |
gdala | +0.379 |
Neg logit contributions | |
ment | -0.316 |
heid | -0.301 |
grave | -0.299 |
uph | -0.278 |
alis | -0.274 |
Token | : |
Token ID | 25 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
itle | +0.687 |
Huss | +0.674 |
rooms | +0.645 |
gdala | +0.619 |
ollow | +0.615 |
Neg logit contributions | |
ment | -0.723 |
heid | -0.690 |
grave | -0.685 |
uph | -0.651 |
alis | -0.642 |
Token | report |
Token ID | 989 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
itle | +1.618 |
Huss | +1.563 |
rooms | +1.504 |
ollow | +1.463 |
gdala | +1.459 |
Neg logit contributions | |
ment | -1.234 |
heid | -1.149 |
grave | -1.148 |
uph | -1.065 |
alis | -1.046 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
itle | +0.626 |
Huss | +0.614 |
rooms | +0.590 |
ollow | +0.566 |
gdala | +0.563 |
Neg logit contributions | |
ment | -0.602 |
heid | -0.576 |
grave | -0.572 |
uph | -0.538 |
alis | -0.531 |
Token | airline |
Token ID | 18091 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
itle | +0.377 |
Huss | +0.371 |
rooms | +0.357 |
ollow | +0.343 |
gdala | +0.342 |
Neg logit contributions | |
ment | -0.305 |
heid | -0.291 |
grave | -0.289 |
uph | -0.269 |
alis | -0.265 |
Token | takes |
Token ID | 2753 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
itle | +0.129 |
Huss | +0.127 |
rooms | +0.123 |
ollow | +0.119 |
gdala | +0.118 |
Neg logit contributions | |
ment | -0.083 |
heid | -0.079 |
grave | -0.078 |
uph | -0.072 |
alis | -0.071 |
Token | steps |
Token ID | 4831 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
ment | +0.251 |
heid | +0.240 |
grave | +0.239 |
uph | +0.220 |
alis | +0.217 |
Neg logit contributions | |
itle | -0.357 |
Huss | -0.353 |
rooms | -0.341 |
ollow | -0.327 |
gdala | -0.323 |
Token | JPMorgan |
Token ID | 43318 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
itle | +0.203 |
Huss | +0.200 |
rooms | +0.192 |
ollow | +0.184 |
gdala | +0.184 |
Neg logit contributions | |
ment | -0.177 |
heid | -0.169 |
grave | -0.168 |
uph | -0.158 |
alis | -0.155 |
Token | Chase |
Token ID | 16346 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ment | +0.177 |
heid | +0.171 |
grave | +0.169 |
uph | +0.159 |
alis | +0.157 |
Neg logit contributions | |
itle | -0.188 |
Huss | -0.186 |
rooms | -0.177 |
ollow | -0.170 |
gdala | -0.169 |
Token | , |
Token ID | 11 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
ment | +0.325 |
heid | +0.313 |
grave | +0.310 |
uph | +0.291 |
alis | +0.286 |
Neg logit contributions | |
itle | -0.378 |
Huss | -0.374 |
rooms | -0.359 |
ollow | -0.344 |
gdala | -0.342 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
itle | +0.179 |
Huss | +0.176 |
rooms | +0.169 |
ollow | +0.163 |
gdala | +0.162 |
Neg logit contributions | |
ment | -0.144 |
heid | -0.138 |
grave | -0.137 |
uph | -0.128 |
alis | -0.126 |
Token | Cit |
Token ID | 15792 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
itle | +0.127 |
Huss | +0.126 |
rooms | +0.121 |
ollow | +0.116 |
gdala | +0.116 |
Neg logit contributions | |
ment | -0.098 |
heid | -0.094 |
grave | -0.093 |
uph | -0.087 |
alis | -0.085 |
Token | ib |
Token ID | 571 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
itle | +0.279 |
Huss | +0.275 |
rooms | +0.263 |
ollow | +0.252 |
gdala | +0.251 |
Neg logit contributions | |
ment | -0.258 |
heid | -0.247 |
grave | -0.245 |
uph | -0.230 |
alis | -0.227 |
Token | ank |
Token ID | 962 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
itle | +0.960 |
Huss | +0.921 |
rooms | +0.875 |
gdala | +0.831 |
ollow | +0.804 |
Neg logit contributions | |
ment | -1.857 |
heid | -1.803 |
grave | -1.786 |
uph | -1.711 |
alis | -1.702 |
Token | were |
Token ID | 547 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ment | +0.158 |
heid | +0.151 |
grave | +0.150 |
uph | +0.140 |
alis | +0.137 |
Neg logit contributions | |
itle | -0.201 |
Huss | -0.199 |
rooms | -0.191 |
ollow | -0.184 |
gdala | -0.182 |
Token | other |
Token ID | 584 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
ment | +0.114 |
heid | +0.109 |
grave | +0.108 |
uph | +0.102 |
alis | +0.100 |
Neg logit contributions | |
itle | -0.127 |
Huss | -0.125 |
rooms | -0.120 |
ollow | -0.115 |
gdala | -0.114 |
Token | top |
Token ID | 1353 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
ment | +0.023 |
heid | +0.022 |
grave | +0.021 |
uph | +0.020 |
alis | +0.020 |
Neg logit contributions | |
itle | -0.028 |
Huss | -0.028 |
rooms | -0.027 |
ollow | -0.026 |
gdala | -0.026 |
Token | targets |
Token ID | 6670 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ment | +0.034 |
heid | +0.032 |
grave | +0.032 |
uph | +0.030 |
alis | +0.030 |
Neg logit contributions | |
itle | -0.039 |
Huss | -0.038 |
rooms | -0.037 |
ollow | -0.035 |
gdala | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
itle | +0.157 |
Huss | +0.155 |
rooms | +0.149 |
ollow | +0.144 |
gdala | +0.143 |
Neg logit contributions | |
ment | -0.115 |
heid | -0.110 |
grave | -0.109 |
uph | -0.102 |
alis | -0.100 |
Token | barracks |
Token ID | 37658 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
itle | +0.239 |
Huss | +0.235 |
rooms | +0.225 |
ollow | +0.216 |
gdala | +0.216 |
Neg logit contributions | |
ment | -0.211 |
heid | -0.202 |
grave | -0.200 |
uph | -0.188 |
alis | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
ment | +0.019 |
heid | +0.018 |
grave | +0.018 |
uph | +0.017 |
alis | +0.016 |
Neg logit contributions | |
itle | -0.022 |
Huss | -0.022 |
rooms | -0.021 |
ollow | -0.020 |
gdala | -0.020 |
Token | while |
Token ID | 981 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
itle | +0.037 |
Huss | +0.037 |
rooms | +0.035 |
ollow | +0.034 |
gdala | +0.034 |
Neg logit contributions | |
ment | -0.033 |
heid | -0.031 |
grave | -0.031 |
uph | -0.029 |
alis | -0.029 |
Token | Ay |
Token ID | 13709 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
ment | +0.012 |
heid | +0.011 |
grave | +0.011 |
uph | +0.011 |
alis | +0.011 |
Neg logit contributions | |
itle | -0.014 |
Huss | -0.014 |
rooms | -0.013 |
ollow | -0.013 |
gdala | -0.012 |
Token | at |
Token ID | 265 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
itle | +0.544 |
Huss | +0.536 |
rooms | +0.508 |
ollow | +0.488 |
gdala | +0.487 |
Neg logit contributions | |
ment | -0.592 |
heid | -0.568 |
grave | -0.565 |
uph | -0.533 |
alis | -0.526 |
Token | ollah |
Token ID | 17999 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
itle | +0.784 |
Huss | +0.748 |
rooms | +0.703 |
gdala | +0.651 |
ollow | +0.636 |
Neg logit contributions | |
ment | -2.038 |
heid | -1.978 |
grave | -1.969 |
uph | -1.887 |
alis | -1.876 |
Token | R |
Token ID | 371 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
itle | +0.626 |
Huss | +0.613 |
rooms | +0.588 |
ollow | +0.563 |
gdala | +0.561 |
Neg logit contributions | |
ment | -0.627 |
heid | -0.602 |
grave | -0.598 |
uph | -0.562 |
alis | -0.555 |
Token | uh |
Token ID | 7456 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ment | +0.199 |
heid | +0.188 |
grave | +0.188 |
uph | +0.174 |
alis | +0.170 |
Neg logit contributions | |
itle | -0.293 |
Huss | -0.289 |
rooms | -0.278 |
ollow | -0.269 |
gdala | -0.267 |
Token | ollah |
Token ID | 17999 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
itle | +0.080 |
Huss | +0.078 |
rooms | +0.071 |
ollow | +0.064 |
gdala | +0.064 |
Neg logit contributions | |
ment | -0.235 |
heid | -0.229 |
grave | -0.228 |
uph | -0.219 |
alis | -0.217 |
Token | Kh |
Token ID | 5311 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
itle | +0.836 |
Huss | +0.821 |
rooms | +0.793 |
ollow | +0.765 |
gdala | +0.763 |
Neg logit contributions | |
ment | -0.558 |
heid | -0.529 |
grave | -0.524 |
uph | -0.486 |
alis | -0.477 |
Token | by |
Token ID | 416 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ment | +0.046 |
heid | +0.044 |
grave | +0.044 |
uph | +0.041 |
alis | +0.040 |
Neg logit contributions | |
itle | -0.054 |
Huss | -0.053 |
rooms | -0.051 |
ollow | -0.049 |
gdala | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ment | +0.132 |
heid | +0.126 |
grave | +0.125 |
uph | +0.117 |
alis | +0.115 |
Neg logit contributions | |
itle | -0.166 |
Huss | -0.164 |
rooms | -0.158 |
ollow | -0.151 |
gdala | -0.151 |
Token | Australian |
Token ID | 6638 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
ment | +0.247 |
heid | +0.236 |
grave | +0.235 |
uph | +0.220 |
alis | +0.216 |
Neg logit contributions | |
itle | -0.306 |
Huss | -0.302 |
rooms | -0.290 |
ollow | -0.278 |
gdala | -0.277 |
Token | Communications |
Token ID | 14620 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
ment | +0.125 |
heid | +0.120 |
grave | +0.119 |
uph | +0.111 |
alis | +0.108 |
Neg logit contributions | |
itle | -0.176 |
Huss | -0.174 |
rooms | -0.167 |
ollow | -0.161 |
gdala | -0.161 |
Token | and |
Token ID | 290 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
itle | +0.490 |
Huss | +0.482 |
rooms | +0.462 |
ollow | +0.445 |
gdala | +0.443 |
Neg logit contributions | |
ment | -0.412 |
heid | -0.392 |
grave | -0.390 |
uph | -0.364 |
alis | -0.359 |
Token | Media |
Token ID | 6343 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
itle | +0.640 |
Huss | +0.631 |
rooms | +0.606 |
gdala | +0.585 |
ollow | +0.585 |
Neg logit contributions | |
ment | -0.455 |
heid | -0.433 |
grave | -0.428 |
uph | -0.397 |
alis | -0.389 |
Token | Authority |
Token ID | 11416 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
itle | +1.554 |
Huss | +1.509 |
rooms | +1.441 |
gdala | +1.405 |
ollow | +1.404 |
Neg logit contributions | |
ment | -1.271 |
grave | -1.205 |
heid | -1.200 |
uph | -1.107 |
quer | -1.098 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
itle | +0.097 |
Huss | +0.095 |
rooms | +0.091 |
ollow | +0.088 |
gdala | +0.087 |
Neg logit contributions | |
ment | -0.079 |
heid | -0.076 |
grave | -0.075 |
uph | -0.070 |
alis | -0.069 |
Token | However |
Token ID | 2102 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ment | +0.192 |
heid | +0.184 |
grave | +0.184 |
uph | +0.173 |
alis | +0.170 |
Neg logit contributions | |
itle | -0.184 |
Huss | -0.181 |
rooms | -0.173 |
ollow | -0.166 |
gdala | -0.164 |
Token | , |
Token ID | 11 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
ment | +0.104 |
heid | +0.100 |
grave | +0.099 |
uph | +0.093 |
alis | +0.091 |
Neg logit contributions | |
itle | -0.122 |
Huss | -0.120 |
rooms | -0.115 |
ollow | -0.111 |
gdala | -0.110 |
Token | it |
Token ID | 340 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
ment | +0.063 |
heid | +0.060 |
grave | +0.060 |
uph | +0.056 |
alis | +0.055 |
Neg logit contributions | |
itle | -0.076 |
Huss | -0.075 |
rooms | -0.072 |
ollow | -0.069 |
gdala | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
itle | +0.234 |
Huss | +0.230 |
rooms | +0.221 |
ollow | +0.212 |
gdala | +0.211 |
Neg logit contributions | |
ment | -0.215 |
heid | -0.206 |
grave | -0.205 |
uph | -0.192 |
alis | -0.189 |
Token |
|
Token ID | 198 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
itle | +0.083 |
Huss | +0.082 |
rooms | +0.079 |
ollow | +0.076 |
gdala | +0.075 |
Neg logit contributions | |
ment | -0.061 |
heid | -0.059 |
grave | -0.058 |
uph | -0.054 |
alis | -0.053 |
Token | More |
Token ID | 5167 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
itle | +0.272 |
Huss | +0.268 |
rooms | +0.257 |
ollow | +0.246 |
gdala | +0.245 |
Neg logit contributions | |
ment | -0.254 |
heid | -0.244 |
grave | -0.242 |
uph | -0.227 |
alis | -0.224 |
Token | from |
Token ID | 422 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
itle | +0.573 |
Huss | +0.563 |
rooms | +0.542 |
ollow | +0.519 |
gdala | +0.518 |
Neg logit contributions | |
ment | -0.485 |
heid | -0.464 |
grave | -0.461 |
uph | -0.430 |
alis | -0.424 |
Token | Cat |
Token ID | 5181 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
itle | +0.412 |
Huss | +0.407 |
rooms | +0.395 |
ollow | +0.383 |
gdala | +0.382 |
Neg logit contributions | |
ment | -0.177 |
heid | -0.165 |
grave | -0.164 |
uph | -0.147 |
alis | -0.143 |
Token | Sc |
Token ID | 1446 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
itle | +0.312 |
Huss | +0.307 |
rooms | +0.295 |
ollow | +0.284 |
gdala | +0.283 |
Neg logit contributions | |
ment | -0.247 |
heid | -0.235 |
grave | -0.234 |
uph | -0.218 |
alis | -0.214 |
Token | ratch |
Token ID | 36722 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Huss | +1.314 |
itle | +1.313 |
rooms | +1.232 |
gdala | +1.185 |
ollow | +1.181 |
Neg logit contributions | |
ment | -1.467 |
heid | -1.392 |
grave | -1.391 |
uph | -1.332 |
alis | -1.305 |
Token | Reader |
Token ID | 25342 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
ment | +0.193 |
heid | +0.185 |
grave | +0.183 |
uph | +0.172 |
alis | +0.169 |
Neg logit contributions | |
itle | -0.236 |
Huss | -0.233 |
rooms | -0.223 |
ollow | -0.215 |
gdala | -0.214 |
Token | : |
Token ID | 25 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
itle | +0.042 |
Huss | +0.041 |
rooms | +0.040 |
ollow | +0.038 |
gdala | +0.038 |
Neg logit contributions | |
ment | -0.034 |
heid | -0.032 |
grave | -0.032 |
uph | -0.030 |
alis | -0.030 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
itle | +0.157 |
Huss | +0.154 |
rooms | +0.148 |
ollow | +0.142 |
gdala | +0.141 |
Neg logit contributions | |
ment | -0.141 |
heid | -0.135 |
grave | -0.134 |
uph | -0.125 |
alis | -0.124 |
Token | The |
Token ID | 464 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ment | +0.105 |
heid | +0.100 |
grave | +0.100 |
uph | +0.094 |
alis | +0.092 |
Neg logit contributions | |
itle | -0.115 |
Huss | -0.113 |
rooms | -0.108 |
ollow | -0.104 |
gdala | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ment | +0.055 |
heid | +0.052 |
grave | +0.052 |
uph | +0.048 |
alis | +0.048 |
Neg logit contributions | |
itle | -0.072 |
Huss | -0.071 |
rooms | -0.068 |
ollow | -0.065 |
gdala | -0.065 |
Token | The |
Token ID | 383 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
itle | +0.104 |
Huss | +0.102 |
rooms | +0.098 |
ollow | +0.094 |
gdala | +0.094 |
Neg logit contributions | |
ment | -0.092 |
heid | -0.088 |
grave | -0.088 |
uph | -0.082 |
alis | -0.081 |
Token | BBC |
Token ID | 7823 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
itle | +0.076 |
Huss | +0.075 |
rooms | +0.073 |
ollow | +0.070 |
gdala | +0.069 |
Neg logit contributions | |
ment | -0.059 |
heid | -0.056 |
grave | -0.056 |
uph | -0.052 |
alis | -0.051 |
Token | 's |
Token ID | 338 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
itle | +0.002 |
Huss | +0.002 |
rooms | +0.002 |
ollow | +0.002 |
gdala | +0.002 |
Neg logit contributions | |
ment | -0.002 |
heid | -0.002 |
grave | -0.002 |
uph | -0.002 |
alis | -0.002 |
Token | Rupert |
Token ID | 34315 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
itle | +0.005 |
Huss | +0.005 |
rooms | +0.005 |
ollow | +0.005 |
gdala | +0.005 |
Neg logit contributions | |
ment | -0.005 |
heid | -0.004 |
grave | -0.004 |
uph | -0.004 |
alis | -0.004 |
Token | Wing |
Token ID | 13405 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
itle | +0.649 |
Huss | +0.637 |
rooms | +0.614 |
ollow | +0.592 |
gdala | +0.591 |
Neg logit contributions | |
ment | -0.493 |
heid | -0.469 |
grave | -0.467 |
uph | -0.433 |
alis | -0.427 |
Token | field |
Token ID | 3245 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
itle | +1.116 |
Huss | +1.094 |
rooms | +1.010 |
gdala | +0.971 |
ollow | +0.970 |
Neg logit contributions | |
ment | -1.664 |
grave | -1.609 |
heid | -1.601 |
uph | -1.523 |
alis | -1.513 |
Token | - |
Token ID | 12 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
itle | +0.240 |
Huss | +0.236 |
rooms | +0.227 |
ollow | +0.219 |
gdala | +0.218 |
Neg logit contributions | |
ment | -0.185 |
heid | -0.177 |
grave | -0.176 |
uph | -0.164 |
alis | -0.161 |
Token | Hay |
Token ID | 31306 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
itle | +0.644 |
Huss | +0.637 |
rooms | +0.615 |
ollow | +0.595 |
gdala | +0.594 |
Neg logit contributions | |
ment | -0.356 |
heid | -0.335 |
grave | -0.334 |
uph | -0.305 |
alis | -0.297 |
Token | es |
Token ID | 274 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
itle | +0.164 |
Huss | +0.161 |
rooms | +0.153 |
ollow | +0.146 |
gdala | +0.145 |
Neg logit contributions | |
ment | -0.196 |
heid | -0.189 |
grave | -0.188 |
uph | -0.178 |
alis | -0.176 |
Token | , |
Token ID | 11 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
itle | +0.284 |
Huss | +0.280 |
rooms | +0.269 |
ollow | +0.259 |
gdala | +0.258 |
Neg logit contributions | |
ment | -0.217 |
heid | -0.207 |
grave | -0.206 |
uph | -0.192 |
alis | -0.188 |
Token | Kh |
Token ID | 5311 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
itle | +0.067 |
Huss | +0.066 |
rooms | +0.064 |
ollow | +0.061 |
gdala | +0.061 |
Neg logit contributions | |
ment | -0.057 |
heid | -0.055 |
grave | -0.054 |
uph | -0.051 |
alis | -0.050 |
Token | ab |
Token ID | 397 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
ment | +0.200 |
heid | +0.191 |
grave | +0.188 |
uph | +0.175 |
alis | +0.171 |
Neg logit contributions | |
itle | -0.289 |
Huss | -0.283 |
rooms | -0.274 |
ollow | -0.264 |
gdala | -0.261 |
Token | ib |
Token ID | 571 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
itle | +0.717 |
Huss | +0.710 |
rooms | +0.683 |
gdala | +0.661 |
ollow | +0.659 |
Neg logit contributions | |
ment | -0.434 |
heid | -0.412 |
grave | -0.408 |
uph | -0.374 |
alis | -0.370 |
Token | Nur |
Token ID | 49281 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
itle | +0.944 |
Huss | +0.918 |
rooms | +0.884 |
gdala | +0.832 |
ollow | +0.818 |
Neg logit contributions | |
ment | -1.408 |
heid | -1.362 |
grave | -1.337 |
uph | -1.290 |
inth | -1.271 |
Token | mag |
Token ID | 19726 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
itle | +0.282 |
Huss | +0.278 |
rooms | +0.268 |
ollow | +0.258 |
gdala | +0.257 |
Neg logit contributions | |
ment | -0.210 |
heid | -0.200 |
grave | -0.199 |
uph | -0.185 |
alis | -0.182 |
Token | omed |
Token ID | 12657 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
itle | +0.705 |
Huss | +0.695 |
rooms | +0.672 |
ollow | +0.649 |
gdala | +0.648 |
Neg logit contributions | |
ment | -0.413 |
heid | -0.391 |
grave | -0.386 |
uph | -0.355 |
alis | -0.348 |
Token | ov |
Token ID | 709 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
itle | +1.095 |
Huss | +1.070 |
rooms | +1.005 |
gdala | +0.969 |
ollow | +0.949 |
Neg logit contributions | |
ment | -1.678 |
heid | -1.617 |
grave | -1.594 |
uph | -1.536 |
alis | -1.513 |
Token | – |
Token ID | 784 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
itle | +0.278 |
Huss | +0.274 |
rooms | +0.263 |
ollow | +0.253 |
gdala | +0.252 |
Neg logit contributions | |
ment | -0.223 |
heid | -0.213 |
grave | -0.211 |
uph | -0.197 |
alis | -0.194 |
Token | which |
Token ID | 543 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
itle | +0.011 |
Huss | +0.011 |
rooms | +0.011 |
ollow | +0.010 |
gdala | +0.010 |
Neg logit contributions | |
ment | -0.010 |
heid | -0.009 |
grave | -0.009 |
uph | -0.009 |
alis | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ment | +0.149 |
heid | +0.143 |
grave | +0.141 |
uph | +0.132 |
alis | +0.130 |
Neg logit contributions | |
itle | -0.181 |
Huss | -0.179 |
rooms | -0.171 |
ollow | -0.165 |
gdala | -0.164 |
Token | pulled |
Token ID | 5954 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
ment | +0.133 |
heid | +0.128 |
grave | +0.127 |
uph | +0.119 |
alis | +0.117 |
Neg logit contributions | |
itle | -0.153 |
Huss | -0.151 |
rooms | -0.145 |
ollow | -0.139 |
gdala | -0.138 |
Token | Detect |
Token ID | 35874 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
itle | +0.148 |
Huss | +0.146 |
rooms | +0.140 |
ollow | +0.134 |
gdala | +0.133 |
Neg logit contributions | |
ment | -0.136 |
heid | -0.131 |
grave | -0.130 |
uph | -0.122 |
alis | -0.120 |
Token | ives |
Token ID | 1083 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
itle | +0.360 |
Huss | +0.354 |
rooms | +0.337 |
ollow | +0.321 |
gdala | +0.320 |
Neg logit contributions | |
ment | -0.417 |
heid | -0.401 |
grave | -0.399 |
uph | -0.376 |
alis | -0.372 |
Token | James |
Token ID | 3700 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
itle | +0.269 |
Huss | +0.265 |
rooms | +0.255 |
ollow | +0.244 |
gdala | +0.243 |
Neg logit contributions | |
ment | -0.229 |
heid | -0.219 |
grave | -0.218 |
uph | -0.204 |
alis | -0.201 |
Token | Gordon |
Token ID | 11646 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
itle | +0.167 |
Huss | +0.165 |
rooms | +0.159 |
ollow | +0.154 |
gdala | +0.154 |
Neg logit contributions | |
ment | -0.084 |
heid | -0.079 |
grave | -0.078 |
uph | -0.071 |
alis | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
itle | +0.383 |
Huss | +0.377 |
rooms | +0.362 |
ollow | +0.348 |
gdala | +0.347 |
Neg logit contributions | |
ment | -0.309 |
heid | -0.295 |
grave | -0.293 |
uph | -0.274 |
alis | -0.270 |
Token | Harvey |
Token ID | 14943 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
itle | +0.195 |
Huss | +0.192 |
rooms | +0.184 |
ollow | +0.176 |
gdala | +0.175 |
Neg logit contributions | |
ment | -0.174 |
heid | -0.167 |
grave | -0.166 |
uph | -0.155 |
alis | -0.153 |
Token | Bull |
Token ID | 8266 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
itle | +1.584 |
Huss | +1.547 |
rooms | +1.506 |
ollow | +1.433 |
gdala | +1.422 |
Neg logit contributions | |
ment | -1.155 |
grave | -1.105 |
heid | -1.095 |
alis | -1.002 |
uph | -1.000 |
Token | ock |
Token ID | 735 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ment | +0.135 |
heid | +0.131 |
grave | +0.129 |
uph | +0.123 |
alis | +0.121 |
Neg logit contributions | |
itle | -0.101 |
Huss | -0.099 |
rooms | -0.094 |
ollow | -0.090 |
gdala | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
itle | +0.179 |
Huss | +0.177 |
rooms | +0.170 |
ollow | +0.163 |
gdala | +0.162 |
Neg logit contributions | |
ment | -0.150 |
heid | -0.143 |
grave | -0.142 |
uph | -0.133 |
alis | -0.131 |
Token | we |
Token ID | 356 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
itle | +0.218 |
Huss | +0.215 |
rooms | +0.205 |
ollow | +0.197 |
gdala | +0.196 |
Neg logit contributions | |
ment | -0.217 |
heid | -0.208 |
grave | -0.207 |
uph | -0.195 |
alis | -0.192 |
Token | follow |
Token ID | 1061 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
itle | +0.160 |
Huss | +0.158 |
rooms | +0.152 |
ollow | +0.146 |
gdala | +0.145 |
Neg logit contributions | |
ment | -0.135 |
heid | -0.129 |
grave | -0.128 |
uph | -0.120 |
alis | -0.118 |
Token | s |
Token ID | 82 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
itle | +0.003 |
Huss | +0.002 |
rooms | +0.002 |
ollow | +0.002 |
gdala | +0.002 |
Neg logit contributions | |
ment | -0.003 |
heid | -0.003 |
grave | -0.003 |
uph | -0.003 |
alis | -0.003 |
Token | supreme |
Token ID | 17700 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
itle | +0.403 |
Huss | +0.395 |
rooms | +0.380 |
ollow | +0.364 |
gdala | +0.363 |
Neg logit contributions | |
ment | -0.358 |
heid | -0.343 |
grave | -0.340 |
uph | -0.319 |
alis | -0.315 |
Token | leader |
Token ID | 3554 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ment | +0.520 |
heid | +0.498 |
grave | +0.497 |
uph | +0.466 |
alis | +0.458 |
Neg logit contributions | |
itle | -0.598 |
Huss | -0.593 |
rooms | -0.566 |
ollow | -0.545 |
gdala | -0.536 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
itle | +0.120 |
Huss | +0.118 |
rooms | +0.114 |
ollow | +0.110 |
gdala | +0.109 |
Neg logit contributions | |
ment | -0.092 |
heid | -0.088 |
grave | -0.087 |
uph | -0.081 |
alis | -0.080 |
Token | Ay |
Token ID | 13709 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
itle | +0.298 |
Huss | +0.295 |
rooms | +0.285 |
ollow | +0.276 |
gdala | +0.275 |
Neg logit contributions | |
ment | -0.150 |
heid | -0.141 |
grave | -0.140 |
uph | -0.127 |
alis | -0.125 |
Token | at |
Token ID | 265 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
itle | +0.500 |
Huss | +0.491 |
rooms | +0.467 |
ollow | +0.448 |
gdala | +0.446 |
Neg logit contributions | |
ment | -0.543 |
heid | -0.521 |
grave | -0.518 |
uph | -0.488 |
alis | -0.483 |
Token | ollah |
Token ID | 17999 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
itle | +0.770 |
Huss | +0.737 |
rooms | +0.693 |
gdala | +0.644 |
ollow | +0.628 |
Neg logit contributions | |
ment | -1.974 |
heid | -1.911 |
grave | -1.907 |
uph | -1.827 |
alis | -1.816 |
Token | Ali |
Token ID | 12104 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
itle | +0.953 |
Huss | +0.929 |
rooms | +0.900 |
ollow | +0.864 |
gdala | +0.863 |
Neg logit contributions | |
ment | -0.792 |
heid | -0.758 |
grave | -0.752 |
uph | -0.700 |
alis | -0.691 |
Token | Kham |
Token ID | 45159 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
itle | +0.442 |
Huss | +0.427 |
rooms | +0.406 |
ollow | +0.379 |
gdala | +0.378 |
Neg logit contributions | |
ment | -0.791 |
heid | -0.767 |
grave | -0.762 |
uph | -0.728 |
alis | -0.722 |
Token | enei |
Token ID | 46009 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ment | +0.109 |
heid | +0.104 |
grave | +0.103 |
uph | +0.096 |
alis | +0.094 |
Neg logit contributions | |
itle | -0.144 |
Huss | -0.141 |
rooms | -0.136 |
ollow | -0.131 |
gdala | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
itle | +0.278 |
Huss | +0.274 |
rooms | +0.262 |
ollow | +0.252 |
gdala | +0.251 |
Neg logit contributions | |
ment | -0.254 |
heid | -0.243 |
grave | -0.241 |
uph | -0.226 |
alis | -0.223 |
Token | Enemy |
Token ID | 21785 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ment | +0.619 |
heid | +0.596 |
grave | +0.584 |
uph | +0.532 |
inth | +0.528 |
Neg logit contributions | |
itle | -1.002 |
Huss | -0.996 |
rooms | -0.951 |
ollow | -0.917 |
gdala | -0.909 |
Token | of |
Token ID | 286 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
itle | +0.016 |
Huss | +0.016 |
rooms | +0.015 |
ollow | +0.015 |
gdala | +0.015 |
Neg logit contributions | |
ment | -0.014 |
heid | -0.014 |
grave | -0.014 |
uph | -0.013 |
alis | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
itle | +0.130 |
Huss | +0.128 |
rooms | +0.123 |
ollow | +0.118 |
gdala | +0.118 |
Neg logit contributions | |
ment | -0.105 |
heid | -0.101 |
grave | -0.100 |
uph | -0.094 |
alis | -0.092 |
Token | State |
Token ID | 1812 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
ment | +0.186 |
heid | +0.177 |
grave | +0.175 |
uph | +0.160 |
inth | +0.158 |
Neg logit contributions | |
itle | -0.323 |
Huss | -0.318 |
rooms | -0.306 |
ollow | -0.297 |
gdala | -0.295 |
Token | : |
Token ID | 25 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
ment | +0.593 |
heid | +0.571 |
grave | +0.558 |
uph | +0.529 |
inth | +0.523 |
Neg logit contributions | |
itle | -0.686 |
Huss | -0.678 |
rooms | -0.654 |
ollow | -0.626 |
gdala | -0.622 |
Token | The |
Token ID | 383 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ment | +0.562 |
heid | +0.538 |
grave | +0.537 |
uph | +0.511 |
inth | +0.500 |
Neg logit contributions | |
itle | -0.502 |
Huss | -0.494 |
rooms | -0.467 |
gdala | -0.448 |
ollow | -0.447 |
Token | Life |
Token ID | 5155 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
ment | +1.953 |
heid | +1.932 |
grave | +1.874 |
uph | +1.817 |
alis | +1.765 |
Neg logit contributions | |
itle | -2.306 |
Huss | -2.233 |
rooms | -2.176 |
gery | -2.109 |
ollow | -2.076 |
Token | of |
Token ID | 286 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
ment | +0.437 |
heid | +0.422 |
grave | +0.414 |
uph | +0.392 |
alis | +0.385 |
Neg logit contributions | |
itle | -0.467 |
Huss | -0.458 |
rooms | -0.441 |
ollow | -0.421 |
gdala | -0.420 |
Token | Murray |
Token ID | 12164 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ment | +0.496 |
heid | +0.471 |
grave | +0.468 |
uph | +0.439 |
alis | +0.432 |
Neg logit contributions | |
itle | -0.693 |
Huss | -0.682 |
rooms | -0.649 |
ollow | -0.625 |
gdala | -0.625 |
Token | N |
Token ID | 399 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ment | +0.650 |
heid | +0.625 |
grave | +0.610 |
uph | +0.582 |
quer | +0.567 |
Neg logit contributions | |
itle | -0.822 |
Huss | -0.820 |
rooms | -0.778 |
ollow | -0.756 |
gdala | -0.745 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
ment | +0.344 |
heid | +0.332 |
grave | +0.327 |
uph | +0.309 |
quer | +0.303 |
Neg logit contributions | |
itle | -0.397 |
Huss | -0.391 |
rooms | -0.375 |
ollow | -0.360 |
gdala | -0.357 |
Token | V |
Token ID | 569 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ment | +0.238 |
heid | +0.226 |
grave | +0.224 |
uph | +0.207 |
alis | +0.203 |
Neg logit contributions | |
itle | -0.405 |
Huss | -0.400 |
rooms | -0.385 |
ollow | -0.372 |
gdala | -0.371 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
itle | +0.226 |
Huss | +0.222 |
rooms | +0.212 |
ollow | +0.202 |
gdala | +0.201 |
Neg logit contributions | |
ment | -0.255 |
heid | -0.245 |
grave | -0.244 |
uph | -0.230 |
alis | -0.227 |
Token | Greg |
Token ID | 8547 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ment | +0.075 |
heid | +0.072 |
grave | +0.072 |
uph | +0.067 |
alis | +0.066 |
Neg logit contributions | |
itle | -0.086 |
Huss | -0.085 |
rooms | -0.081 |
ollow | -0.078 |
gdala | -0.078 |
Token | Smith |
Token ID | 4176 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ment | +0.835 |
heid | +0.815 |
grave | +0.807 |
uph | +0.768 |
alis | +0.763 |
Neg logit contributions | |
itle | -0.596 |
Huss | -0.592 |
rooms | -0.553 |
ollow | -0.523 |
gdala | -0.523 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ment | +0.154 |
heid | +0.148 |
grave | +0.146 |
uph | +0.137 |
alis | +0.135 |
Neg logit contributions | |
itle | -0.183 |
Huss | -0.180 |
rooms | -0.173 |
ollow | -0.166 |
gdala | -0.165 |
Token | Richard |
Token ID | 6219 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ment | +0.091 |
heid | +0.087 |
grave | +0.087 |
uph | +0.081 |
alis | +0.080 |
Neg logit contributions | |
itle | -0.109 |
Huss | -0.108 |
rooms | -0.103 |
ollow | -0.099 |
gdala | -0.099 |
Token | Jefferson |
Token ID | 15375 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ment | +1.779 |
grave | +1.711 |
heid | +1.694 |
alis | +1.593 |
uph | +1.591 |
Neg logit contributions | |
Huss | -1.883 |
itle | -1.843 |
rooms | -1.759 |
gdala | -1.695 |
ollow | -1.686 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ment | +0.164 |
heid | +0.158 |
grave | +0.157 |
uph | +0.147 |
alis | +0.144 |
Neg logit contributions | |
itle | -0.195 |
Huss | -0.192 |
rooms | -0.184 |
ollow | -0.176 |
gdala | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ment | +0.071 |
heid | +0.068 |
grave | +0.068 |
uph | +0.063 |
alis | +0.062 |
Neg logit contributions | |
itle | -0.085 |
Huss | -0.084 |
rooms | -0.081 |
ollow | -0.078 |
gdala | -0.077 |
Token | Bernard |
Token ID | 16197 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ment | +0.069 |
heid | +0.066 |
grave | +0.066 |
uph | +0.062 |
alis | +0.061 |
Neg logit contributions | |
itle | -0.083 |
Huss | -0.082 |
rooms | -0.078 |
ollow | -0.075 |
gdala | -0.075 |
Token | James |
Token ID | 3700 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ment | +0.113 |
heid | +0.109 |
grave | +0.108 |
uph | +0.101 |
alis | +0.100 |
Neg logit contributions | |
itle | -0.128 |
Huss | -0.126 |
rooms | -0.121 |
ollow | -0.116 |
gdala | -0.115 |
Token | David |
Token ID | 3271 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
itle | +0.625 |
Huss | +0.612 |
rooms | +0.591 |
gdala | +0.568 |
ollow | +0.567 |
Neg logit contributions | |
ment | -0.510 |
heid | -0.486 |
grave | -0.485 |
uph | -0.452 |
alis | -0.445 |
Token | Gordon |
Token ID | 11646 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
itle | +0.924 |
Huss | +0.910 |
rooms | +0.887 |
ollow | +0.858 |
gdala | +0.858 |
Neg logit contributions | |
ment | -0.339 |
heid | -0.313 |
grave | -0.312 |
uph | -0.275 |
alis | -0.266 |
Token | ( |
Token ID | 357 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
itle | +0.372 |
Huss | +0.366 |
rooms | +0.352 |
ollow | +0.338 |
gdala | +0.337 |
Neg logit contributions | |
ment | -0.298 |
heid | -0.284 |
grave | -0.282 |
uph | -0.263 |
alis | -0.260 |
Token | IS |
Token ID | 1797 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
ment | +0.293 |
heid | +0.282 |
grave | +0.279 |
uph | +0.263 |
inth | +0.257 |
Neg logit contributions | |
itle | -0.337 |
Huss | -0.332 |
rooms | -0.318 |
ollow | -0.304 |
gdala | -0.301 |
Token | I |
Token ID | 40 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
itle | +0.424 |
Huss | +0.418 |
rooms | +0.399 |
ollow | +0.383 |
gdala | +0.381 |
Neg logit contributions | |
ment | -0.421 |
heid | -0.404 |
grave | -0.402 |
uph | -0.376 |
alis | -0.372 |
Token | Books |
Token ID | 13661 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
ment | +0.317 |
heid | +0.306 |
grave | +0.299 |
uph | +0.279 |
inth | +0.271 |
Neg logit contributions | |
itle | -0.524 |
Huss | -0.519 |
rooms | -0.501 |
ollow | -0.481 |
gdala | -0.479 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ment | +1.808 |
heid | +1.788 |
grave | +1.746 |
uph | +1.707 |
inth | +1.644 |
Neg logit contributions | |
itle | -1.776 |
Huss | -1.774 |
rooms | -1.709 |
ollow | -1.622 |
gdala | -1.568 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
ment | +0.218 |
heid | +0.210 |
grave | +0.208 |
uph | +0.197 |
alis | +0.195 |
Neg logit contributions | |
itle | -0.204 |
Huss | -0.200 |
rooms | -0.192 |
ollow | -0.183 |
gdala | -0.181 |
Token | ). |
Token ID | 737 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ment | +0.510 |
heid | +0.493 |
grave | +0.484 |
uph | +0.458 |
alis | +0.451 |
Neg logit contributions | |
itle | -0.607 |
Huss | -0.599 |
rooms | -0.572 |
ollow | -0.549 |
gdala | -0.546 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
ment | +0.365 |
heid | +0.350 |
grave | +0.346 |
uph | +0.327 |
alis | +0.319 |
Neg logit contributions | |
itle | -0.471 |
Huss | -0.467 |
rooms | -0.443 |
ollow | -0.429 |
gdala | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
ment | +0.017 |
heid | +0.016 |
grave | +0.016 |
uph | +0.015 |
alis | +0.015 |
Neg logit contributions | |
itle | -0.023 |
Huss | -0.023 |
rooms | -0.022 |
ollow | -0.021 |
gdala | -0.021 |
Token | � |
Token ID | 1587 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ment | +0.403 |
heid | +0.388 |
grave | +0.387 |
uph | +0.366 |
alis | +0.360 |
Neg logit contributions | |
itle | -0.441 |
Huss | -0.437 |
rooms | -0.415 |
ollow | -0.402 |
gdala | -0.396 |
Token | � |
Token ID | 245 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
itle | +0.380 |
Huss | +0.374 |
rooms | +0.359 |
ollow | +0.345 |
gdala | +0.343 |
Neg logit contributions | |
ment | -0.327 |
heid | -0.312 |
grave | -0.310 |
uph | -0.291 |
alis | -0.286 |
Token | all |
Token ID | 477 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ment | +0.404 |
heid | +0.389 |
grave | +0.387 |
uph | +0.362 |
alis | +0.359 |
Neg logit contributions | |
itle | -0.500 |
Huss | -0.496 |
rooms | -0.472 |
gdala | -0.455 |
ollow | -0.453 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ment | +0.896 |
heid | +0.883 |
grave | +0.877 |
uph | +0.821 |
inth | +0.815 |
Neg logit contributions | |
itle | -1.046 |
Huss | -1.027 |
rooms | -0.982 |
ollow | -0.953 |
gdala | -0.931 |
Token | only |
Token ID | 691 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
ment | +0.638 |
heid | +0.614 |
grave | +0.611 |
uph | +0.575 |
alis | +0.564 |
Neg logit contributions | |
itle | -0.846 |
Huss | -0.841 |
rooms | -0.804 |
ollow | -0.777 |
gdala | -0.763 |
Token | $ |
Token ID | 720 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ment | +0.510 |
heid | +0.485 |
grave | +0.479 |
uph | +0.454 |
alis | +0.444 |
Neg logit contributions | |
itle | -0.622 |
Huss | -0.613 |
rooms | -0.588 |
ollow | -0.564 |
gdala | -0.561 |
Token | 19 |
Token ID | 1129 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
ment | +1.597 |
grave | +1.541 |
heid | +1.520 |
uph | +1.433 |
alis | +1.401 |
Neg logit contributions | |
itle | -1.991 |
Huss | -1.974 |
rooms | -1.877 |
ollow | -1.821 |
gery | -1.782 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
itle | +0.048 |
Huss | +0.047 |
rooms | +0.045 |
ollow | +0.044 |
gdala | +0.043 |
Neg logit contributions | |
ment | -0.040 |
heid | -0.039 |
grave | -0.038 |
uph | -0.036 |
alis | -0.035 |
Token | 99 |
Token ID | 2079 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ment | +0.171 |
heid | +0.163 |
grave | +0.162 |
uph | +0.152 |
alis | +0.149 |
Neg logit contributions | |
itle | -0.220 |
Huss | -0.218 |
rooms | -0.209 |
ollow | -0.201 |
gdala | -0.200 |
Token | ... |
Token ID | 986 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ment | +0.255 |
heid | +0.245 |
grave | +0.244 |
uph | +0.228 |
alis | +0.225 |
Neg logit contributions | |
itle | -0.293 |
Huss | -0.290 |
rooms | -0.277 |
ollow | -0.266 |
gdala | -0.264 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
itle | +0.476 |
Huss | +0.469 |
rooms | +0.451 |
ollow | +0.435 |
gdala | +0.433 |
Neg logit contributions | |
ment | -0.344 |
heid | -0.328 |
grave | -0.325 |
uph | -0.302 |
alis | -0.296 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
itle | +0.057 |
Huss | +0.056 |
rooms | +0.054 |
ollow | +0.051 |
gdala | +0.051 |
Neg logit contributions | |
ment | -0.067 |
heid | -0.064 |
grave | -0.064 |
uph | -0.060 |
alis | -0.060 |
Token | 's |
Token ID | 338 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
itle | +0.050 |
Huss | +0.050 |
rooms | +0.048 |
ollow | +0.046 |
gdala | +0.046 |
Neg logit contributions | |
ment | -0.043 |
heid | -0.041 |
grave | -0.040 |
uph | -0.038 |
alis | -0.037 |
Token | campaign |
Token ID | 1923 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ment | +0.142 |
heid | +0.136 |
grave | +0.134 |
uph | +0.126 |
alis | +0.123 |
Neg logit contributions | |
itle | -0.179 |
Huss | -0.177 |
rooms | -0.170 |
ollow | -0.163 |
gdala | -0.163 |
Token | manager |
Token ID | 4706 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
ment | +0.264 |
heid | +0.254 |
grave | +0.253 |
uph | +0.236 |
alis | +0.232 |
Neg logit contributions | |
itle | -0.303 |
Huss | -0.301 |
rooms | -0.288 |
ollow | -0.276 |
gdala | -0.274 |
Token | Rob |
Token ID | 3851 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ment | +0.306 |
heid | +0.295 |
grave | +0.293 |
uph | +0.274 |
alis | +0.269 |
Neg logit contributions | |
itle | -0.359 |
Huss | -0.355 |
rooms | -0.340 |
ollow | -0.326 |
gdala | -0.324 |
Token | by |
Token ID | 1525 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ment | +0.795 |
heid | +0.774 |
grave | +0.768 |
uph | +0.727 |
alis | +0.707 |
Neg logit contributions | |
itle | -0.814 |
Huss | -0.812 |
rooms | -0.772 |
ollow | -0.739 |
gdala | -0.727 |
Token | M |
Token ID | 337 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
ment | +0.917 |
grave | +0.879 |
heid | +0.841 |
uph | +0.787 |
quer | +0.733 |
Neg logit contributions | |
Huss | -2.611 |
itle | -2.605 |
rooms | -2.541 |
gdala | -2.482 |
ollow | -2.471 |
Token | ook |
Token ID | 566 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ment | +0.393 |
heid | +0.378 |
grave | +0.372 |
uph | +0.344 |
alis | +0.334 |
Neg logit contributions | |
itle | -0.769 |
Huss | -0.752 |
rooms | -0.737 |
ollow | -0.711 |
gdala | -0.702 |
Token | pointed |
Token ID | 6235 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ment | +0.088 |
heid | +0.085 |
grave | +0.084 |
uph | +0.079 |
alis | +0.077 |
Neg logit contributions | |
itle | -0.103 |
Huss | -0.101 |
rooms | -0.097 |
ollow | -0.093 |
gdala | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
itle | +0.191 |
Huss | +0.188 |
rooms | +0.181 |
ollow | +0.174 |
gdala | +0.173 |
Neg logit contributions | |
ment | -0.149 |
heid | -0.142 |
grave | -0.141 |
uph | -0.132 |
alis | -0.130 |
Token | media |
Token ID | 2056 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ment | +0.019 |
heid | +0.018 |
grave | +0.018 |
uph | +0.017 |
alis | +0.017 |
Neg logit contributions | |
itle | -0.023 |
Huss | -0.022 |
rooms | -0.021 |
ollow | -0.020 |
gdala | -0.020 |
Token | such |
Token ID | 884 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ment | +0.193 |
heid | +0.187 |
grave | +0.185 |
uph | +0.173 |
alis | +0.172 |
Neg logit contributions | |
itle | -0.216 |
Huss | -0.212 |
rooms | -0.203 |
ollow | -0.195 |
gdala | -0.192 |
Token | as |
Token ID | 355 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ment | +0.101 |
heid | +0.097 |
grave | +0.096 |
uph | +0.091 |
alis | +0.089 |
Neg logit contributions | |
itle | -0.115 |
Huss | -0.114 |
rooms | -0.109 |
ollow | -0.105 |
gdala | -0.104 |
Token | NES |
Token ID | 31925 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
itle | +0.427 |
Huss | +0.419 |
rooms | +0.400 |
ollow | +0.382 |
gdala | +0.382 |
Neg logit contributions | |
ment | -0.464 |
heid | -0.445 |
grave | -0.444 |
uph | -0.418 |
alis | -0.412 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ment | +0.479 |
heid | +0.461 |
grave | +0.452 |
uph | +0.422 |
alis | +0.413 |
Neg logit contributions | |
itle | -0.739 |
Huss | -0.722 |
rooms | -0.704 |
ollow | -0.672 |
gdala | -0.669 |
Token | , |
Token ID | 11 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
ment | +0.125 |
heid | +0.121 |
grave | +0.119 |
uph | +0.112 |
alis | +0.110 |
Neg logit contributions | |
itle | -0.145 |
Huss | -0.143 |
rooms | -0.137 |
ollow | -0.132 |
gdala | -0.131 |
Token | Super |
Token ID | 3115 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
itle | +0.041 |
Huss | +0.040 |
rooms | +0.038 |
ollow | +0.036 |
gdala | +0.036 |
Neg logit contributions | |
ment | -0.057 |
heid | -0.055 |
grave | -0.054 |
uph | -0.052 |
alis | -0.051 |
Token | NES |
Token ID | 31925 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
heid | +1.932 |
ment | +1.914 |
grave | +1.913 |
uph | +1.779 |
inth | +1.761 |
Neg logit contributions | |
itle | -1.451 |
Huss | -1.416 |
rooms | -1.367 |
gdala | -1.277 |
gery | -1.268 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ment | +0.284 |
heid | +0.271 |
grave | +0.269 |
uph | +0.249 |
alis | +0.243 |
Neg logit contributions | |
itle | -0.450 |
Huss | -0.442 |
rooms | -0.428 |
ollow | -0.412 |
gdala | -0.410 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ment | +0.097 |
heid | +0.093 |
grave | +0.092 |
uph | +0.086 |
alis | +0.085 |
Neg logit contributions | |
itle | -0.113 |
Huss | -0.111 |
rooms | -0.107 |
ollow | -0.103 |
gdala | -0.102 |
Token | Game |
Token ID | 3776 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ment | +0.130 |
heid | +0.127 |
grave | +0.126 |
uph | +0.122 |
alis | +0.120 |
Neg logit contributions | |
itle | -0.049 |
Huss | -0.047 |
rooms | -0.043 |
ollow | -0.040 |
gdala | -0.039 |
Token | Boy |
Token ID | 6387 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ment | +0.815 |
heid | +0.795 |
grave | +0.791 |
uph | +0.734 |
inth | +0.721 |
Neg logit contributions | |
itle | -1.227 |
Huss | -1.203 |
rooms | -1.171 |
ollow | -1.116 |
gdala | -1.097 |
Token | iae |
Token ID | 33100 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
itle | +0.062 |
Huss | +0.061 |
rooms | +0.058 |
ollow | +0.056 |
gdala | +0.056 |
Neg logit contributions | |
ment | -0.058 |
heid | -0.056 |
grave | -0.055 |
uph | -0.052 |
alis | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ment | +0.102 |
heid | +0.097 |
grave | +0.096 |
uph | +0.090 |
alis | +0.089 |
Neg logit contributions | |
itle | -0.123 |
Huss | -0.121 |
rooms | -0.116 |
ollow | -0.112 |
gdala | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ment | +0.063 |
heid | +0.060 |
grave | +0.059 |
uph | +0.055 |
alis | +0.054 |
Neg logit contributions | |
itle | -0.084 |
Huss | -0.083 |
rooms | -0.080 |
ollow | -0.077 |
gdala | -0.076 |
Token | Please |
Token ID | 5492 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ment | +0.215 |
heid | +0.207 |
grave | +0.205 |
uph | +0.193 |
alis | +0.190 |
Neg logit contributions | |
itle | -0.235 |
Huss | -0.231 |
rooms | -0.221 |
ollow | -0.212 |
gdala | -0.211 |
Token | help |
Token ID | 1037 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
ment | +0.173 |
heid | +0.166 |
grave | +0.165 |
uph | +0.154 |
alis | +0.152 |
Neg logit contributions | |
itle | -0.205 |
Huss | -0.202 |
rooms | -0.193 |
ollow | -0.186 |
gdala | -0.185 |
Token | support |
Token ID | 1104 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ment | +0.435 |
heid | +0.416 |
grave | +0.415 |
uph | +0.385 |
alis | +0.382 |
Neg logit contributions | |
itle | -0.498 |
Huss | -0.491 |
rooms | -0.469 |
ollow | -0.453 |
gdala | -0.446 |
Token | the |
Token ID | 262 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
ment | +1.643 |
grave | +1.592 |
heid | +1.587 |
uph | +1.467 |
alis | +1.467 |
Neg logit contributions | |
itle | -1.725 |
Huss | -1.720 |
rooms | -1.622 |
ollow | -1.547 |
gery | -1.521 |
Token | mission |
Token ID | 4365 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ment | +0.381 |
grave | +0.368 |
heid | +0.366 |
uph | +0.341 |
alis | +0.339 |
Neg logit contributions | |
itle | -0.387 |
Huss | -0.381 |
rooms | -0.362 |
ollow | -0.347 |
gdala | -0.344 |
Token | of |
Token ID | 286 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ment | +0.804 |
grave | +0.788 |
heid | +0.780 |
uph | +0.735 |
alis | +0.729 |
Neg logit contributions | |
itle | -0.856 |
Huss | -0.844 |
rooms | -0.805 |
ollow | -0.779 |
gdala | -0.764 |
Token | New |
Token ID | 968 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ment | +1.146 |
grave | +1.098 |
heid | +1.077 |
alis | +1.009 |
uph | +1.009 |
Neg logit contributions | |
Huss | -1.379 |
itle | -1.375 |
rooms | -1.314 |
ollow | -1.263 |
gdala | -1.235 |
Token | Advent |
Token ID | 33732 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ment | +0.590 |
heid | +0.562 |
grave | +0.550 |
uph | +0.518 |
inth | +0.506 |
Neg logit contributions | |
itle | -1.085 |
Huss | -1.085 |
rooms | -1.049 |
ollow | -1.006 |
gdala | -1.005 |
Token | uk |
Token ID | 2724 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
ment | +0.411 |
heid | +0.398 |
grave | +0.396 |
uph | +0.376 |
alis | +0.372 |
Neg logit contributions | |
itle | -0.286 |
Huss | -0.280 |
rooms | -0.267 |
ollow | -0.253 |
gdala | -0.250 |
Token | or |
Token ID | 393 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ment | +0.064 |
heid | +0.061 |
grave | +0.061 |
uph | +0.057 |
alis | +0.056 |
Neg logit contributions | |
itle | -0.075 |
Huss | -0.073 |
rooms | -0.071 |
ollow | -0.068 |
gdala | -0.067 |
Token | call |
Token ID | 869 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
itle | +0.173 |
Huss | +0.170 |
rooms | +0.164 |
ollow | +0.157 |
gdala | +0.157 |
Neg logit contributions | |
ment | -0.139 |
heid | -0.133 |
grave | -0.132 |
uph | -0.123 |
alis | -0.121 |
Token | 0 |
Token ID | 657 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
ment | +0.005 |
heid | +0.004 |
grave | +0.004 |
uph | +0.004 |
alis | +0.004 |
Neg logit contributions | |
itle | -0.005 |
Huss | -0.005 |
rooms | -0.005 |
ollow | -0.004 |
gdala | -0.004 |
Token | 207 |
Token ID | 22745 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
itle | +0.017 |
Huss | +0.017 |
rooms | +0.016 |
ollow | +0.016 |
gdala | +0.015 |
Neg logit contributions | |
ment | -0.020 |
heid | -0.019 |
grave | -0.019 |
uph | -0.018 |
alis | -0.018 |
Token | 7 |
Token ID | 767 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ment | +0.961 |
heid | +0.931 |
grave | +0.926 |
uph | +0.872 |
alis | +0.860 |
Neg logit contributions | |
itle | -1.138 |
Huss | -1.134 |
rooms | -1.084 |
ollow | -1.063 |
gdala | -1.032 |
Token | 82 |
Token ID | 6469 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ment | +1.535 |
heid | +1.521 |
grave | +1.513 |
uph | +1.410 |
alis | +1.396 |
Neg logit contributions | |
itle | -1.685 |
Huss | -1.634 |
rooms | -1.573 |
ollow | -1.535 |
gdala | -1.488 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ment | +1.017 |
heid | +0.993 |
grave | +0.965 |
uph | +0.923 |
alis | +0.908 |
Neg logit contributions | |
itle | -1.166 |
Huss | -1.141 |
rooms | -1.120 |
ollow | -1.072 |
gdala | -1.057 |
Token | 368 |
Token ID | 27412 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
itle | +0.350 |
Huss | +0.345 |
rooms | +0.330 |
ollow | +0.315 |
gdala | +0.315 |
Neg logit contributions | |
ment | -0.343 |
heid | -0.329 |
grave | -0.327 |
uph | -0.308 |
alis | -0.303 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
itle | +0.149 |
Huss | +0.146 |
rooms | +0.140 |
ollow | +0.134 |
gdala | +0.134 |
Neg logit contributions | |
ment | -0.143 |
heid | -0.138 |
grave | -0.137 |
uph | -0.129 |
alis | -0.127 |
Token | To |
Token ID | 2514 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
ment | +0.091 |
heid | +0.087 |
grave | +0.086 |
uph | +0.081 |
alis | +0.080 |
Neg logit contributions | |
itle | -0.099 |
Huss | -0.097 |
rooms | -0.093 |
ollow | -0.089 |
gdala | -0.089 |
Token | Also |
Token ID | 4418 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
itle | +0.048 |
Huss | +0.048 |
rooms | +0.046 |
ollow | +0.044 |
gdala | +0.044 |
Neg logit contributions | |
ment | -0.040 |
heid | -0.039 |
grave | -0.038 |
uph | -0.036 |
alis | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
itle | +0.080 |
Huss | +0.079 |
rooms | +0.076 |
ollow | +0.073 |
gdala | +0.073 |
Neg logit contributions | |
ment | -0.066 |
heid | -0.064 |
grave | -0.063 |
uph | -0.059 |
alis | -0.058 |
Token | in |
Token ID | 287 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
itle | +0.084 |
Huss | +0.083 |
rooms | +0.079 |
ollow | +0.076 |
gdala | +0.076 |
Neg logit contributions | |
ment | -0.069 |
heid | -0.066 |
grave | -0.065 |
uph | -0.061 |
alis | -0.060 |
Token | The |
Token ID | 383 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ment | +0.009 |
heid | +0.008 |
grave | +0.008 |
uph | +0.008 |
alis | +0.008 |
Neg logit contributions | |
itle | -0.010 |
Huss | -0.010 |
rooms | -0.010 |
ollow | -0.010 |
gdala | -0.009 |
Token | ss |
Token ID | 824 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ment | +0.121 |
heid | +0.116 |
grave | +0.115 |
uph | +0.108 |
alis | +0.107 |
Neg logit contributions | |
itle | -0.137 |
Huss | -0.135 |
rooms | -0.129 |
ollow | -0.124 |
gdala | -0.124 |
Token | alon |
Token ID | 40755 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ment | +0.334 |
heid | +0.320 |
grave | +0.320 |
uph | +0.301 |
alis | +0.295 |
Neg logit contributions | |
itle | -0.326 |
Huss | -0.320 |
rooms | -0.306 |
ollow | -0.293 |
gdala | -0.291 |
Token | iki |
Token ID | 5580 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
ment | +1.521 |
grave | +1.477 |
heid | +1.477 |
uph | +1.362 |
alis | +1.361 |
Neg logit contributions | |
itle | -1.618 |
Huss | -1.608 |
rooms | -1.538 |
ollow | -1.471 |
gdala | -1.451 |
Token | we |
Token ID | 356 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
itle | +0.034 |
Huss | +0.033 |
rooms | +0.032 |
ollow | +0.031 |
gdala | +0.031 |
Neg logit contributions | |
ment | -0.028 |
heid | -0.026 |
grave | -0.026 |
uph | -0.025 |
alis | -0.024 |
Token | participate |
Token ID | 8277 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
itle | +0.002 |
Huss | +0.002 |
rooms | +0.002 |
ollow | +0.002 |
gdala | +0.002 |
Neg logit contributions | |
ment | -0.002 |
heid | -0.002 |
grave | -0.002 |
uph | -0.002 |
alis | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
itle | +0.022 |
Huss | +0.022 |
rooms | +0.021 |
ollow | +0.020 |
gdala | +0.020 |
Neg logit contributions | |
ment | -0.018 |
heid | -0.018 |
grave | -0.018 |
uph | -0.016 |
alis | -0.016 |
Token | two |
Token ID | 734 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
itle | +0.263 |
Huss | +0.259 |
rooms | +0.248 |
ollow | +0.239 |
gdala | +0.238 |
Neg logit contributions | |
ment | -0.228 |
heid | -0.218 |
grave | -0.217 |
uph | -0.203 |
alis | -0.200 |
Token | author |
Token ID | 1772 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
ment | +0.668 |
heid | +0.641 |
grave | +0.637 |
uph | +0.597 |
alis | +0.585 |
Neg logit contributions | |
itle | -0.695 |
Huss | -0.691 |
rooms | -0.656 |
ollow | -0.631 |
gdala | -0.624 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ment | +0.509 |
heid | +0.488 |
grave | +0.482 |
uph | +0.456 |
inth | +0.448 |
Neg logit contributions | |
itle | -0.573 |
Huss | -0.565 |
rooms | -0.541 |
gdala | -0.518 |
ollow | -0.517 |
Token | not |
Token ID | 407 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ment | +1.127 |
heid | +1.092 |
grave | +1.083 |
uph | +1.018 |
inth | +1.007 |
Neg logit contributions | |
itle | -1.237 |
Huss | -1.236 |
rooms | -1.158 |
ollow | -1.116 |
gdala | -1.100 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ment | +0.906 |
grave | +0.878 |
heid | +0.869 |
uph | +0.817 |
inth | +0.812 |
Neg logit contributions | |
itle | -1.027 |
Huss | -1.025 |
rooms | -0.973 |
gdala | -0.929 |
ollow | -0.924 |
Token | position |
Token ID | 2292 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ment | +1.193 |
heid | +1.159 |
grave | +1.146 |
uph | +1.074 |
alis | +1.067 |
Neg logit contributions | |
itle | -1.211 |
Huss | -1.201 |
rooms | -1.153 |
ollow | -1.093 |
gdala | -1.079 |
Token | of |
Token ID | 286 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ment | +0.874 |
heid | +0.842 |
grave | +0.839 |
uph | +0.789 |
alis | +0.780 |
Neg logit contributions | |
itle | -0.925 |
Huss | -0.907 |
rooms | -0.871 |
ollow | -0.833 |
gdala | -0.826 |
Token | EUR |
Token ID | 27526 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
ment | +1.299 |
grave | +1.249 |
heid | +1.221 |
uph | +1.174 |
alis | +1.134 |
Neg logit contributions | |
Huss | -1.743 |
itle | -1.730 |
rooms | -1.646 |
ollow | -1.582 |
gdala | -1.574 |
Token | OP |
Token ID | 3185 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
ment | +0.513 |
heid | +0.492 |
grave | +0.491 |
uph | +0.459 |
alis | +0.449 |
Neg logit contributions | |
itle | -0.651 |
Huss | -0.640 |
rooms | -0.609 |
ollow | -0.593 |
gdala | -0.584 |
Token | P |
Token ID | 47 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ment | +0.558 |
heid | +0.541 |
grave | +0.535 |
uph | +0.500 |
inth | +0.487 |
Neg logit contributions | |
itle | -0.751 |
Huss | -0.732 |
rooms | -0.708 |
ollow | -0.688 |
gdala | -0.672 |
Token | – |
Token ID | 784 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ment | +0.656 |
heid | +0.629 |
grave | +0.622 |
uph | +0.589 |
inth | +0.573 |
Neg logit contributions | |
itle | -0.880 |
Huss | -0.875 |
rooms | -0.838 |
ollow | -0.816 |
gdala | -0.797 |
Token | European |
Token ID | 3427 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ment | +1.231 |
grave | +1.204 |
heid | +1.187 |
uph | +1.118 |
inth | +1.101 |
Neg logit contributions | |
Huss | -1.408 |
itle | -1.402 |
rooms | -1.315 |
ollow | -1.282 |
gdala | -1.274 |
Token | makes |
Token ID | 1838 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ment | +0.074 |
heid | +0.070 |
grave | +0.070 |
uph | +0.064 |
alis | +0.063 |
Neg logit contributions | |
itle | -0.103 |
Huss | -0.102 |
rooms | -0.098 |
ollow | -0.095 |
gdala | -0.094 |
Token | Black |
Token ID | 2619 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ment | +0.872 |
grave | +0.827 |
heid | +0.825 |
uph | +0.787 |
inth | +0.773 |
Neg logit contributions | |
itle | -0.847 |
Huss | -0.846 |
rooms | -0.805 |
ollow | -0.766 |
gdala | -0.760 |
Token | Voice |
Token ID | 15282 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ment | +1.139 |
grave | +1.124 |
heid | +1.117 |
uph | +1.062 |
inth | +1.051 |
Neg logit contributions | |
itle | -0.754 |
Huss | -0.751 |
rooms | -0.696 |
ollow | -0.664 |
gdala | -0.649 |
Token | louder |
Token ID | 27089 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ment | +0.226 |
heid | +0.218 |
grave | +0.216 |
uph | +0.198 |
alis | +0.196 |
Neg logit contributions | |
itle | -0.340 |
Huss | -0.336 |
rooms | -0.325 |
ollow | -0.312 |
gdala | -0.309 |
Token | ! |
Token ID | 0 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ment | +1.184 |
grave | +1.122 |
heid | +1.118 |
uph | +1.068 |
�� | +1.038 |
Neg logit contributions | |
Huss | -1.477 |
itle | -1.472 |
rooms | -1.421 |
ollow | -1.354 |
gdala | -1.344 |
Token | Share |
Token ID | 8734 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ment | +0.739 |
grave | +0.711 |
heid | +0.707 |
uph | +0.668 |
inth | +0.660 |
Neg logit contributions | |
itle | -0.792 |
Huss | -0.792 |
rooms | -0.755 |
gdala | -0.718 |
ollow | -0.716 |
Token | To |
Token ID | 1675 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
ment | +1.696 |
grave | +1.661 |
heid | +1.636 |
uph | +1.574 |
inth | +1.567 |
Neg logit contributions | |
itle | -1.272 |
Huss | -1.246 |
rooms | -1.191 |
ollow | -1.124 |
gdala | -1.103 |
Token | Share |
Token ID | 8734 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ment | +0.209 |
heid | +0.200 |
grave | +0.199 |
uph | +0.186 |
alis | +0.184 |
Neg logit contributions | |
itle | -0.237 |
Huss | -0.233 |
rooms | -0.223 |
ollow | -0.215 |
gdala | -0.213 |
Token | To |
Token ID | 1675 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ment | +0.511 |
grave | +0.493 |
heid | +0.490 |
uph | +0.466 |
alis | +0.459 |
Neg logit contributions | |
itle | -0.417 |
Huss | -0.410 |
rooms | -0.390 |
ollow | -0.371 |
gdala | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
itle | +0.639 |
Huss | +0.631 |
rooms | +0.608 |
gdala | +0.586 |
ollow | +0.585 |
Neg logit contributions | |
ment | -0.458 |
heid | -0.435 |
grave | -0.431 |
uph | -0.401 |
alis | -0.392 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ment | +0.102 |
heid | +0.097 |
grave | +0.097 |
uph | +0.090 |
alis | +0.089 |
Neg logit contributions | |
itle | -0.136 |
Huss | -0.134 |
rooms | -0.129 |
ollow | -0.124 |
gdala | -0.123 |
Token | ES |
Token ID | 1546 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ment | +0.067 |
heid | +0.064 |
grave | +0.064 |
uph | +0.060 |
alis | +0.059 |
Neg logit contributions | |
itle | -0.083 |
Huss | -0.082 |
rooms | -0.078 |
ollow | -0.075 |
gdala | -0.075 |
Token | IN |
Token ID | 3268 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
ment | +0.111 |
heid | +0.106 |
grave | +0.105 |
uph | +0.098 |
alis | +0.096 |
Neg logit contributions | |
itle | -0.167 |
Huss | -0.164 |
rooms | -0.158 |
ollow | -0.153 |
gdala | -0.152 |
Token | THE |
Token ID | 3336 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
ment | +0.316 |
heid | +0.305 |
grave | +0.303 |
uph | +0.283 |
alis | +0.278 |
Neg logit contributions | |
itle | -0.375 |
Huss | -0.367 |
rooms | -0.351 |
ollow | -0.340 |
gdala | -0.336 |
Token | MAR |
Token ID | 18805 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ment | +0.025 |
heid | +0.024 |
grave | +0.023 |
uph | +0.021 |
alis | +0.021 |
Neg logit contributions | |
itle | -0.045 |
Huss | -0.044 |
rooms | -0.043 |
ollow | -0.041 |
gdala | -0.041 |
Token | G |
Token ID | 38 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
itle | +0.092 |
Huss | +0.091 |
rooms | +0.087 |
ollow | +0.083 |
gdala | +0.083 |
Neg logit contributions | |
ment | -0.083 |
heid | -0.079 |
grave | -0.079 |
uph | -0.074 |
alis | -0.073 |
Token | IN |
Token ID | 1268 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ment | +0.201 |
heid | +0.194 |
grave | +0.192 |
uph | +0.181 |
alis | +0.178 |
Neg logit contributions | |
itle | -0.219 |
Huss | -0.216 |
rooms | -0.207 |
ollow | -0.198 |
gdala | -0.196 |
Token |
|
Token ID | 198 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
ment | +1.311 |
heid | +1.310 |
grave | +1.285 |
uph | +1.212 |
alis | +1.182 |
Neg logit contributions | |
itle | -1.584 |
Huss | -1.567 |
rooms | -1.481 |
ollow | -1.438 |
gdala | -1.414 |
Token |
|
Token ID | 198 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
ment | +0.053 |
heid | +0.050 |
grave | +0.050 |
uph | +0.047 |
alis | +0.046 |
Neg logit contributions | |
itle | -0.070 |
Huss | -0.069 |
rooms | -0.067 |
ollow | -0.064 |
gdala | -0.064 |
Token | You |
Token ID | 1639 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
itle | +0.612 |
Huss | +0.605 |
rooms | +0.578 |
gdala | +0.554 |
ollow | +0.554 |
Neg logit contributions | |
ment | -0.559 |
heid | -0.531 |
grave | -0.528 |
uph | -0.495 |
alis | -0.489 |
Token | can |
Token ID | 460 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
itle | +0.154 |
Huss | +0.152 |
rooms | +0.146 |
ollow | +0.140 |
gdala | +0.140 |
Neg logit contributions | |
ment | -0.116 |
heid | -0.110 |
grave | -0.110 |
uph | -0.102 |
alis | -0.100 |
Token | check |
Token ID | 2198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
itle | +1.187 |
Huss | +1.169 |
rooms | +1.131 |
gdala | +1.098 |
ollow | +1.085 |
Neg logit contributions | |
ment | -0.723 |
heid | -0.678 |
grave | -0.677 |
uph | -0.621 |
alis | -0.612 |
Token | players |
Token ID | 1938 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
ment | +0.182 |
heid | +0.176 |
grave | +0.174 |
uph | +0.163 |
alis | +0.160 |
Neg logit contributions | |
itle | -0.205 |
Huss | -0.202 |
rooms | -0.193 |
ollow | -0.185 |
gdala | -0.184 |
Token | such |
Token ID | 884 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
ment | +0.003 |
heid | +0.003 |
grave | +0.003 |
uph | +0.003 |
alis | +0.003 |
Neg logit contributions | |
itle | -0.004 |
Huss | -0.004 |
rooms | -0.004 |
ollow | -0.004 |
gdala | -0.004 |
Token | as |
Token ID | 355 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ment | +0.051 |
heid | +0.049 |
grave | +0.049 |
uph | +0.046 |
alis | +0.045 |
Neg logit contributions | |
itle | -0.059 |
Huss | -0.058 |
rooms | -0.056 |
ollow | -0.053 |
gdala | -0.053 |
Token | Sad |
Token ID | 14668 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ment | +0.179 |
heid | +0.172 |
grave | +0.170 |
uph | +0.159 |
alis | +0.156 |
Neg logit contributions | |
itle | -0.215 |
Huss | -0.213 |
rooms | -0.203 |
ollow | -0.196 |
gdala | -0.195 |
Token | io |
Token ID | 952 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
ment | +0.008 |
heid | +0.008 |
grave | +0.008 |
uph | +0.007 |
alis | +0.007 |
Neg logit contributions | |
itle | -0.009 |
Huss | -0.009 |
rooms | -0.008 |
ollow | -0.008 |
gdala | -0.008 |
Token | Man |
Token ID | 1869 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
itle | +0.447 |
Huss | +0.441 |
rooms | +0.425 |
ollow | +0.410 |
gdala | +0.409 |
Neg logit contributions | |
ment | -0.308 |
heid | -0.293 |
grave | -0.291 |
uph | -0.269 |
alis | -0.265 |
Token | é |
Token ID | 2634 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ment | +1.011 |
heid | +0.977 |
grave | +0.948 |
uph | +0.879 |
alis | +0.860 |
Neg logit contributions | |
itle | -1.845 |
Huss | -1.818 |
rooms | -1.748 |
ollow | -1.721 |
gdala | -1.685 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
itle | +0.357 |
Huss | +0.351 |
rooms | +0.337 |
ollow | +0.324 |
gdala | +0.323 |
Neg logit contributions | |
ment | -0.294 |
heid | -0.281 |
grave | -0.279 |
uph | -0.260 |
alis | -0.256 |
Token | Adam |
Token ID | 7244 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ment | +0.108 |
heid | +0.103 |
grave | +0.102 |
uph | +0.095 |
alis | +0.094 |
Neg logit contributions | |
itle | -0.133 |
Huss | -0.131 |
rooms | -0.126 |
ollow | -0.121 |
gdala | -0.120 |
Token | L |
Token ID | 406 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
ment | +0.719 |
heid | +0.698 |
grave | +0.686 |
uph | +0.649 |
alis | +0.635 |
Neg logit contributions | |
Huss | -0.848 |
itle | -0.848 |
rooms | -0.799 |
gdala | -0.769 |
ollow | -0.765 |
Token | all |
Token ID | 439 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
itle | +0.685 |
Huss | +0.675 |
rooms | +0.649 |
ollow | +0.622 |
gdala | +0.620 |
Neg logit contributions | |
ment | -0.606 |
heid | -0.579 |
grave | -0.573 |
uph | -0.535 |
alis | -0.529 |
Token | a |
Token ID | 257 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
itle | +0.269 |
Huss | +0.265 |
rooms | +0.254 |
ollow | +0.244 |
gdala | +0.243 |
Neg logit contributions | |
ment | -0.222 |
heid | -0.212 |
grave | -0.210 |
uph | -0.197 |
alis | -0.194 |
Token | different |
Token ID | 1180 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ment | +0.209 |
grave | +0.199 |
heid | +0.199 |
uph | +0.186 |
alis | +0.182 |
Neg logit contributions | |
itle | -0.273 |
Huss | -0.269 |
rooms | -0.259 |
ollow | -0.250 |
gdala | -0.249 |
Token | voice |
Token ID | 3809 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ment | +0.783 |
grave | +0.756 |
heid | +0.751 |
uph | +0.723 |
alis | +0.708 |
Neg logit contributions | |
itle | -0.705 |
Huss | -0.691 |
rooms | -0.663 |
gdala | -0.634 |
ollow | -0.629 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ment | +0.365 |
grave | +0.351 |
heid | +0.348 |
uph | +0.327 |
alis | +0.320 |
Neg logit contributions | |
itle | -0.429 |
Huss | -0.424 |
rooms | -0.410 |
ollow | -0.389 |
gdala | -0.389 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ment | +0.772 |
grave | +0.744 |
heid | +0.743 |
uph | +0.703 |
inth | +0.690 |
Neg logit contributions | |
itle | -0.854 |
Huss | -0.840 |
rooms | -0.822 |
ollow | -0.779 |
gery | -0.765 |
Token | closer |
Token ID | 5699 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ment | +0.428 |
grave | +0.406 |
heid | +0.399 |
uph | +0.359 |
alis | +0.353 |
Neg logit contributions | |
itle | -1.019 |
Huss | -1.010 |
rooms | -0.979 |
ollow | -0.948 |
gdala | -0.946 |
Token | look |
Token ID | 804 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ment | +1.157 |
grave | +1.125 |
heid | +1.087 |
uph | +1.040 |
alis | +1.011 |
Neg logit contributions | |
itle | -1.677 |
Huss | -1.669 |
rooms | -1.602 |
ollow | -1.560 |
gdala | -1.536 |
Token | at |
Token ID | 379 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ment | +0.257 |
grave | +0.248 |
heid | +0.247 |
uph | +0.231 |
alis | +0.228 |
Neg logit contributions | |
itle | -0.294 |
Huss | -0.291 |
rooms | -0.279 |
ollow | -0.268 |
gdala | -0.267 |
Token | what |
Token ID | 644 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
ment | +1.223 |
heid | +1.174 |
grave | +1.170 |
uph | +1.084 |
alis | +1.080 |
Neg logit contributions | |
itle | -1.542 |
Huss | -1.512 |
rooms | -1.455 |
gdala | -1.390 |
ollow | -1.387 |
Token | is |
Token ID | 318 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ment | +0.414 |
heid | +0.396 |
grave | +0.394 |
uph | +0.365 |
alis | +0.360 |
Neg logit contributions | |
itle | -0.540 |
Huss | -0.533 |
rooms | -0.512 |
ollow | -0.493 |
gdala | -0.489 |
Token | happening |
Token ID | 5836 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
itle | +0.177 |
Huss | +0.174 |
rooms | +0.167 |
ollow | +0.160 |
gdala | +0.160 |
Neg logit contributions | |
ment | -0.159 |
heid | -0.152 |
grave | -0.151 |
uph | -0.142 |
alis | -0.139 |
Token | Kim |
Token ID | 6502 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
itle | +0.412 |
Huss | +0.405 |
rooms | +0.390 |
ollow | +0.374 |
gdala | +0.374 |
Neg logit contributions | |
ment | -0.333 |
heid | -0.317 |
grave | -0.315 |
uph | -0.294 |
alis | -0.290 |
Token | b |
Token ID | 65 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ment | +0.109 |
heid | +0.105 |
grave | +0.104 |
uph | +0.097 |
alis | +0.095 |
Neg logit contributions | |
itle | -0.136 |
Huss | -0.134 |
rooms | -0.128 |
ollow | -0.124 |
gdala | -0.123 |
Token | rough |
Token ID | 740 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
ment | +0.250 |
heid | +0.242 |
grave | +0.240 |
uph | +0.228 |
alis | +0.225 |
Neg logit contributions | |
itle | -0.194 |
Huss | -0.191 |
rooms | -0.182 |
ollow | -0.173 |
gdala | -0.171 |
Token | and |
Token ID | 290 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
itle | +0.311 |
Huss | +0.306 |
rooms | +0.294 |
ollow | +0.283 |
gdala | +0.282 |
Neg logit contributions | |
ment | -0.248 |
heid | -0.237 |
grave | -0.236 |
uph | -0.220 |
alis | -0.216 |
Token | Ros |
Token ID | 10018 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ment | +0.142 |
heid | +0.136 |
grave | +0.135 |
uph | +0.127 |
alis | +0.124 |
Neg logit contributions | |
itle | -0.175 |
Huss | -0.173 |
rooms | -0.165 |
ollow | -0.159 |
gdala | -0.158 |
Token | cos |
Token ID | 6966 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
itle | +0.138 |
Huss | +0.137 |
rooms | +0.132 |
ollow | +0.127 |
gdala | +0.127 |
Neg logit contributions | |
ment | -0.078 |
heid | -0.073 |
grave | -0.073 |
uph | -0.067 |
alis | -0.065 |
Token | mos |
Token ID | 16785 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ment | +0.961 |
heid | +0.906 |
grave | +0.887 |
uph | +0.815 |
inth | +0.799 |
Neg logit contributions | |
itle | -1.896 |
Huss | -1.881 |
rooms | -1.833 |
ollow | -1.743 |
gdala | -1.736 |
Token | cos |
Token ID | 8615 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ment | +0.019 |
heid | +0.018 |
grave | +0.018 |
uph | +0.017 |
alis | +0.016 |
Neg logit contributions | |
itle | -0.026 |
Huss | -0.026 |
rooms | -0.025 |
ollow | -0.024 |
gdala | -0.024 |
Token | mon |
Token ID | 2144 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ment | +0.288 |
heid | +0.278 |
grave | +0.274 |
uph | +0.258 |
alis | +0.255 |
Neg logit contributions | |
itle | -0.325 |
Huss | -0.319 |
rooms | -0.307 |
ollow | -0.294 |
gdala | -0.291 |
Token | auts |
Token ID | 17712 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ment | +0.057 |
heid | +0.053 |
grave | +0.052 |
uph | +0.047 |
alis | +0.045 |
Neg logit contributions | |
itle | -0.135 |
Huss | -0.133 |
rooms | -0.129 |
ollow | -0.125 |
gdala | -0.124 |
Token | Sergey |
Token ID | 36106 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
itle | +0.213 |
Huss | +0.210 |
rooms | +0.201 |
ollow | +0.193 |
gdala | +0.192 |
Neg logit contributions | |
ment | -0.180 |
heid | -0.172 |
grave | -0.171 |
uph | -0.160 |
alis | -0.158 |
Token | PT |
Token ID | 11571 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
ment | +0.277 |
grave | +0.265 |
heid | +0.265 |
uph | +0.247 |
alis | +0.244 |
Neg logit contributions | |
itle | -0.308 |
Huss | -0.303 |
rooms | -0.292 |
ollow | -0.279 |
gdala | -0.277 |
Token | PowerPoint |
Token ID | 43563 |
Feature activation | +3.02e-03 |
Pos logit contributions | |
itle | +0.515 |
Huss | +0.502 |
rooms | +0.478 |
ollow | +0.451 |
gdala | +0.451 |
Neg logit contributions | |
ment | -0.761 |
heid | -0.737 |
grave | -0.734 |
uph | -0.695 |
alis | -0.688 |
Token | slide |
Token ID | 10649 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
itle | +0.001 |
Huss | +0.001 |
rooms | +0.001 |
ollow | +0.001 |
gdala | +0.001 |
Neg logit contributions | |
ment | -0.003 |
heid | -0.003 |
grave | -0.003 |
uph | -0.003 |
alis | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
itle | +0.462 |
Huss | +0.455 |
rooms | +0.438 |
ollow | +0.422 |
gdala | +0.420 |
Neg logit contributions | |
ment | -0.335 |
heid | -0.319 |
grave | -0.316 |
uph | -0.294 |
alis | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
itle | +0.109 |
Huss | +0.107 |
rooms | +0.103 |
ollow | +0.099 |
gdala | +0.099 |
Neg logit contributions | |
ment | -0.080 |
heid | -0.077 |
grave | -0.076 |
uph | -0.071 |
alis | -0.070 |
Token | Power |
Token ID | 13434 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
itle | +0.216 |
Huss | +0.214 |
rooms | +0.208 |
ollow | +0.202 |
gdala | +0.201 |
Neg logit contributions | |
ment | -0.079 |
heid | -0.073 |
grave | -0.072 |
uph | -0.064 |
alis | -0.062 |
Token | Point |
Token ID | 12727 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ment | +1.499 |
heid | +1.498 |
grave | +1.477 |
uph | +1.390 |
quer | +1.388 |
Neg logit contributions | |
Huss | -1.312 |
itle | -1.298 |
rooms | -1.255 |
gdala | -1.175 |
ollow | -1.147 |
Token | slide |
Token ID | 10649 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
itle | +0.060 |
Huss | +0.058 |
rooms | +0.054 |
ollow | +0.050 |
gdala | +0.049 |
Neg logit contributions | |
ment | -0.136 |
heid | -0.133 |
grave | -0.132 |
uph | -0.126 |
alis | -0.125 |
Token | PNG |
Token ID | 36182 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
itle | +0.764 |
Huss | +0.744 |
rooms | +0.703 |
gdala | +0.663 |
ollow | +0.661 |
Neg logit contributions | |
ment | -1.467 |
heid | -1.407 |
grave | -1.404 |
uph | -1.352 |
inth | -1.341 |
Token | larger |
Token ID | 4025 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ment | +0.447 |
heid | +0.433 |
grave | +0.428 |
uph | +0.403 |
inth | +0.394 |
Neg logit contributions | |
itle | -0.538 |
Huss | -0.531 |
rooms | -0.509 |
ollow | -0.488 |
gdala | -0.487 |
Token | image |
Token ID | 2939 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ment | +0.376 |
heid | +0.368 |
grave | +0.365 |
uph | +0.349 |
alis | +0.343 |
Neg logit contributions | |
itle | -0.239 |
Huss | -0.233 |
rooms | -0.220 |
ollow | -0.207 |
gdala | -0.206 |
Token | that |
Token ID | 326 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ment | +0.190 |
heid | +0.182 |
grave | +0.181 |
uph | +0.169 |
alis | +0.166 |
Neg logit contributions | |
itle | -0.227 |
Huss | -0.224 |
rooms | -0.215 |
ollow | -0.206 |
gdala | -0.205 |
Token | troubled |
Token ID | 17840 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ment | +0.193 |
heid | +0.186 |
grave | +0.184 |
uph | +0.173 |
alis | +0.170 |
Neg logit contributions | |
itle | -0.227 |
Huss | -0.224 |
rooms | -0.215 |
ollow | -0.206 |
gdala | -0.205 |
Token | state |
Token ID | 1181 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ment | +0.149 |
heid | +0.143 |
grave | +0.143 |
uph | +0.133 |
alis | +0.131 |
Neg logit contributions | |
itle | -0.183 |
Huss | -0.181 |
rooms | -0.173 |
ollow | -0.166 |
gdala | -0.165 |
Token | fund |
Token ID | 1814 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ment | +0.207 |
heid | +0.199 |
grave | +0.197 |
uph | +0.185 |
alis | +0.182 |
Neg logit contributions | |
itle | -0.244 |
Huss | -0.241 |
rooms | -0.232 |
ollow | -0.222 |
gdala | -0.221 |
Token | 1 |
Token ID | 352 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ment | +0.012 |
heid | +0.012 |
grave | +0.012 |
uph | +0.011 |
alis | +0.011 |
Neg logit contributions | |
itle | -0.015 |
Huss | -0.015 |
rooms | -0.014 |
ollow | -0.013 |
gdala | -0.013 |
Token | Mal |
Token ID | 15029 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ment | +0.183 |
heid | +0.174 |
grave | +0.173 |
uph | +0.160 |
alis | +0.158 |
Neg logit contributions | |
itle | -0.262 |
Huss | -0.258 |
rooms | -0.248 |
ollow | -0.240 |
gdala | -0.238 |
Token | ays |
Token ID | 592 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ment | +1.248 |
heid | +1.200 |
grave | +1.188 |
uph | +1.117 |
alis | +1.088 |
Neg logit contributions | |
itle | -1.563 |
Huss | -1.547 |
rooms | -1.478 |
ollow | -1.408 |
gdala | -1.404 |
Token | ia |
Token ID | 544 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
ment | +0.487 |
heid | +0.467 |
grave | +0.465 |
uph | +0.437 |
alis | +0.427 |
Neg logit contributions | |
itle | -0.538 |
Huss | -0.529 |
rooms | -0.506 |
ollow | -0.485 |
gdala | -0.483 |
Token | Development |
Token ID | 7712 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ment | +0.417 |
heid | +0.399 |
grave | +0.399 |
uph | +0.370 |
inth | +0.363 |
Neg logit contributions | |
itle | -0.532 |
Huss | -0.528 |
rooms | -0.504 |
ollow | -0.486 |
gdala | -0.483 |
Token | Ber |
Token ID | 4312 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ment | +0.285 |
grave | +0.271 |
heid | +0.271 |
uph | +0.253 |
inth | +0.247 |
Neg logit contributions | |
itle | -0.359 |
Huss | -0.354 |
rooms | -0.339 |
ollow | -0.326 |
gdala | -0.326 |
Token | had |
Token ID | 18108 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
itle | +0.708 |
Huss | +0.700 |
rooms | +0.672 |
ollow | +0.646 |
gdala | +0.642 |
Neg logit contributions | |
ment | -0.551 |
heid | -0.525 |
grave | -0.519 |
uph | -0.485 |
alis | -0.477 |
Token | King |
Token ID | 2677 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
ment | +0.174 |
heid | +0.167 |
grave | +0.166 |
uph | +0.155 |
alis | +0.152 |
Neg logit contributions | |
itle | -0.216 |
Huss | -0.213 |
rooms | -0.204 |
ollow | -0.196 |
gdala | -0.195 |
Token | Kong |
Token ID | 9071 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ment | +0.431 |
heid | +0.413 |
grave | +0.409 |
uph | +0.384 |
alis | +0.377 |
Neg logit contributions | |
itle | -0.510 |
Huss | -0.506 |
rooms | -0.485 |
ollow | -0.463 |
gdala | -0.462 |
Token | , |
Token ID | 11 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
ment | +0.109 |
heid | +0.105 |
grave | +0.104 |
uph | +0.097 |
alis | +0.095 |
Neg logit contributions | |
itle | -0.131 |
Huss | -0.130 |
rooms | -0.124 |
ollow | -0.119 |
gdala | -0.119 |
Token | Creature |
Token ID | 33248 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ment | +0.241 |
heid | +0.232 |
grave | +0.230 |
uph | +0.215 |
alis | +0.212 |
Neg logit contributions | |
itle | -0.280 |
Huss | -0.276 |
rooms | -0.264 |
ollow | -0.254 |
gdala | -0.252 |
Token | from |
Token ID | 422 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
itle | +0.102 |
Huss | +0.100 |
rooms | +0.096 |
ollow | +0.091 |
gdala | +0.091 |
Neg logit contributions | |
ment | -0.100 |
heid | -0.096 |
grave | -0.096 |
uph | -0.090 |
alis | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ment | +0.850 |
heid | +0.823 |
grave | +0.810 |
uph | +0.765 |
alis | +0.751 |
Neg logit contributions | |
itle | -0.985 |
Huss | -0.969 |
rooms | -0.931 |
ollow | -0.892 |
gdala | -0.881 |
Token | Black |
Token ID | 2619 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ment | +1.393 |
heid | +1.359 |
grave | +1.329 |
uph | +1.270 |
alis | +1.249 |
Neg logit contributions | |
itle | -1.377 |
Huss | -1.354 |
rooms | -1.297 |
ollow | -1.241 |
gdala | -1.219 |
Token | Lag |
Token ID | 21003 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ment | +0.588 |
heid | +0.569 |
grave | +0.560 |
uph | +0.518 |
alis | +0.513 |
Neg logit contributions | |
itle | -0.927 |
Huss | -0.923 |
rooms | -0.886 |
ollow | -0.855 |
gdala | -0.845 |
Token | oon |
Token ID | 2049 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ment | +0.372 |
heid | +0.357 |
grave | +0.356 |
uph | +0.336 |
alis | +0.329 |
Neg logit contributions | |
itle | -0.434 |
Huss | -0.427 |
rooms | -0.409 |
ollow | -0.395 |
gdala | -0.391 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ment | +0.175 |
heid | +0.168 |
grave | +0.166 |
uph | +0.156 |
alis | +0.153 |
Neg logit contributions | |
itle | -0.207 |
Huss | -0.204 |
rooms | -0.196 |
ollow | -0.188 |
gdala | -0.187 |
Token | Dr |
Token ID | 1583 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
ment | +0.205 |
heid | +0.197 |
grave | +0.196 |
uph | +0.183 |
alis | +0.181 |
Neg logit contributions | |
itle | -0.237 |
Huss | -0.234 |
rooms | -0.224 |
ollow | -0.214 |
gdala | -0.214 |
Token | voice |
Token ID | 3809 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
ment | +0.783 |
grave | +0.756 |
heid | +0.751 |
uph | +0.723 |
alis | +0.708 |
Neg logit contributions | |
itle | -0.705 |
Huss | -0.691 |
rooms | -0.663 |
gdala | -0.634 |
ollow | -0.629 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ment | +0.365 |
grave | +0.351 |
heid | +0.348 |
uph | +0.327 |
alis | +0.320 |
Neg logit contributions | |
itle | -0.429 |
Huss | -0.424 |
rooms | -0.410 |
ollow | -0.389 |
gdala | -0.389 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ment | +0.772 |
grave | +0.744 |
heid | +0.743 |
uph | +0.703 |
inth | +0.690 |
Neg logit contributions | |
itle | -0.854 |
Huss | -0.840 |
rooms | -0.822 |
ollow | -0.779 |
gery | -0.765 |
Token | closer |
Token ID | 5699 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ment | +0.428 |
grave | +0.406 |
heid | +0.399 |
uph | +0.359 |
alis | +0.353 |
Neg logit contributions | |
itle | -1.019 |
Huss | -1.010 |
rooms | -0.979 |
ollow | -0.948 |
gdala | -0.946 |
Token | look |
Token ID | 804 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ment | +1.157 |
grave | +1.125 |
heid | +1.087 |
uph | +1.040 |
alis | +1.011 |
Neg logit contributions | |
itle | -1.677 |
Huss | -1.669 |
rooms | -1.602 |
ollow | -1.560 |
gdala | -1.536 |
Token | at |
Token ID | 379 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ment | +0.257 |
grave | +0.248 |
heid | +0.247 |
uph | +0.231 |
alis | +0.228 |
Neg logit contributions | |
itle | -0.294 |
Huss | -0.291 |
rooms | -0.279 |
ollow | -0.268 |
gdala | -0.267 |
Token | what |
Token ID | 644 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
ment | +1.223 |
heid | +1.174 |
grave | +1.170 |
uph | +1.084 |
alis | +1.080 |
Neg logit contributions | |
itle | -1.542 |
Huss | -1.512 |
rooms | -1.455 |
gdala | -1.390 |
ollow | -1.387 |
Token | is |
Token ID | 318 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ment | +0.414 |
heid | +0.396 |
grave | +0.394 |
uph | +0.365 |
alis | +0.360 |
Neg logit contributions | |
itle | -0.540 |
Huss | -0.533 |
rooms | -0.512 |
ollow | -0.493 |
gdala | -0.489 |
Token | happening |
Token ID | 5836 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
itle | +0.177 |
Huss | +0.174 |
rooms | +0.167 |
ollow | +0.160 |
gdala | +0.160 |
Neg logit contributions | |
ment | -0.159 |
heid | -0.152 |
grave | -0.151 |
uph | -0.142 |
alis | -0.139 |
Token | in |
Token ID | 287 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ment | +0.089 |
heid | +0.085 |
grave | +0.085 |
uph | +0.079 |
alis | +0.078 |
Neg logit contributions | |
itle | -0.106 |
Huss | -0.104 |
rooms | -0.100 |
ollow | -0.096 |
gdala | -0.095 |
Token | our |
Token ID | 674 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
itle | +0.136 |
Huss | +0.134 |
rooms | +0.129 |
ollow | +0.123 |
gdala | +0.123 |
Neg logit contributions | |
ment | -0.123 |
heid | -0.118 |
grave | -0.117 |
uph | -0.110 |
alis | -0.108 |
Token | are |
Token ID | 389 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
ment | +0.514 |
heid | +0.492 |
grave | +0.486 |
uph | +0.450 |
alis | +0.439 |
Neg logit contributions | |
itle | -0.748 |
Huss | -0.743 |
rooms | -0.723 |
ollow | -0.690 |
gdala | -0.688 |
Token | their |
Token ID | 511 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
ment | +0.542 |
heid | +0.526 |
grave | +0.518 |
uph | +0.482 |
inth | +0.477 |
Neg logit contributions | |
itle | -0.667 |
Huss | -0.660 |
rooms | -0.636 |
ollow | -0.608 |
gdala | -0.598 |
Token | own |
Token ID | 898 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ment | +0.547 |
heid | +0.531 |
grave | +0.528 |
uph | +0.504 |
alis | +0.497 |
Neg logit contributions | |
itle | -0.350 |
Huss | -0.343 |
rooms | -0.326 |
ollow | -0.306 |
gdala | -0.303 |
Token | and |
Token ID | 290 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ment | +0.862 |
grave | +0.830 |
heid | +0.828 |
uph | +0.790 |
�� | +0.772 |
Neg logit contributions | |
itle | -0.949 |
Huss | -0.942 |
rooms | -0.900 |
gdala | -0.854 |
ollow | -0.853 |
Token | do |
Token ID | 466 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ment | +0.394 |
heid | +0.379 |
grave | +0.375 |
uph | +0.352 |
inth | +0.344 |
Neg logit contributions | |
itle | -0.482 |
Huss | -0.475 |
rooms | -0.455 |
ollow | -0.436 |
gdala | -0.433 |
Token | not |
Token ID | 407 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ment | +0.462 |
heid | +0.447 |
grave | +0.443 |
uph | +0.417 |
inth | +0.408 |
Neg logit contributions | |
itle | -0.511 |
Huss | -0.507 |
rooms | -0.483 |
ollow | -0.463 |
gdala | -0.458 |
Token | represent |
Token ID | 2380 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ment | +1.152 |
heid | +1.132 |
grave | +1.116 |
uph | +1.033 |
�� | +1.026 |
Neg logit contributions | |
itle | -1.594 |
Huss | -1.586 |
rooms | -1.522 |
ollow | -1.455 |
gdala | -1.436 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ment | +0.834 |
heid | +0.805 |
grave | +0.798 |
uph | +0.751 |
inth | +0.741 |
Neg logit contributions | |
Huss | -0.944 |
itle | -0.937 |
rooms | -0.889 |
ollow | -0.851 |
gdala | -0.839 |
Token | views |
Token ID | 5009 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ment | +1.007 |
heid | +0.961 |
grave | +0.948 |
alis | +0.882 |
uph | +0.880 |
Neg logit contributions | |
itle | -1.191 |
Huss | -1.188 |
rooms | -1.128 |
ollow | -1.088 |
gdala | -1.070 |
Token | of |
Token ID | 286 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ment | +0.341 |
heid | +0.328 |
grave | +0.326 |
uph | +0.306 |
alis | +0.301 |
Neg logit contributions | |
itle | -0.376 |
Huss | -0.370 |
rooms | -0.355 |
ollow | -0.340 |
gdala | -0.338 |
Token | Town |
Token ID | 8329 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ment | +1.182 |
heid | +1.138 |
grave | +1.124 |
uph | +1.071 |
inth | +1.057 |
Neg logit contributions | |
Huss | -1.160 |
itle | -1.148 |
rooms | -1.095 |
ollow | -1.048 |
gdala | -1.019 |
Token | ime |
Token ID | 524 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
itle | +0.082 |
Huss | +0.081 |
rooms | +0.078 |
ollow | +0.075 |
gdala | +0.075 |
Neg logit contributions | |
ment | -0.053 |
heid | -0.051 |
grave | -0.050 |
uph | -0.047 |
alis | -0.046 |
Token | Book |
Token ID | 4897 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
ment | +0.058 |
heid | +0.055 |
grave | +0.055 |
uph | +0.051 |
alis | +0.051 |
Neg logit contributions | |
itle | -0.069 |
Huss | -0.068 |
rooms | -0.065 |
ollow | -0.063 |
gdala | -0.062 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ment | +0.034 |
heid | +0.033 |
grave | +0.033 |
uph | +0.031 |
alis | +0.030 |
Neg logit contributions | |
itle | -0.041 |
Huss | -0.040 |
rooms | -0.039 |
ollow | -0.037 |
gdala | -0.037 |
Token | Pract |
Token ID | 13672 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
itle | +0.097 |
Huss | +0.096 |
rooms | +0.092 |
ollow | +0.088 |
gdala | +0.088 |
Neg logit contributions | |
ment | -0.073 |
heid | -0.069 |
grave | -0.069 |
uph | -0.064 |
alis | -0.063 |
Token | ical |
Token ID | 605 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
ment | +0.006 |
heid | +0.006 |
grave | +0.006 |
uph | +0.005 |
alis | +0.005 |
Neg logit contributions | |
itle | -0.004 |
Huss | -0.004 |
rooms | -0.004 |
ollow | -0.004 |
gdala | -0.004 |
Token | Et |
Token ID | 17906 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
itle | +0.059 |
Huss | +0.058 |
rooms | +0.056 |
ollow | +0.054 |
gdala | +0.054 |
Neg logit contributions | |
ment | -0.047 |
heid | -0.045 |
grave | -0.044 |
uph | -0.041 |
alis | -0.041 |
Token | iquette |
Token ID | 40387 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
itle | +0.627 |
Huss | +0.617 |
rooms | +0.584 |
gdala | +0.555 |
ollow | +0.554 |
Neg logit contributions | |
ment | -0.839 |
heid | -0.810 |
grave | -0.805 |
uph | -0.765 |
alis | -0.757 |
Token | for |
Token ID | 329 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ment | +0.123 |
heid | +0.118 |
grave | +0.117 |
uph | +0.109 |
alis | +0.107 |
Neg logit contributions | |
itle | -0.145 |
Huss | -0.143 |
rooms | -0.137 |
ollow | -0.132 |
gdala | -0.131 |
Token | Ladies |
Token ID | 37401 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
itle | +0.125 |
Huss | +0.123 |
rooms | +0.118 |
ollow | +0.114 |
gdala | +0.113 |
Neg logit contributions | |
ment | -0.099 |
heid | -0.094 |
grave | -0.093 |
uph | -0.087 |
alis | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
itle | +0.109 |
Huss | +0.108 |
rooms | +0.103 |
ollow | +0.099 |
gdala | +0.099 |
Neg logit contributions | |
ment | -0.092 |
heid | -0.088 |
grave | -0.088 |
uph | -0.082 |
alis | -0.081 |
Token | Gentle |
Token ID | 25066 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
itle | +0.335 |
Huss | +0.330 |
rooms | +0.317 |
ollow | +0.304 |
gdala | +0.303 |
Neg logit contributions | |
ment | -0.282 |
heid | -0.269 |
grave | -0.268 |
uph | -0.250 |
alis | -0.246 |
Token | receive |
Token ID | 3328 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
itle | +0.277 |
Huss | +0.273 |
rooms | +0.263 |
ollow | +0.254 |
gdala | +0.253 |
Neg logit contributions | |
ment | -0.192 |
heid | -0.183 |
grave | -0.181 |
uph | -0.168 |
alis | -0.165 |
Token | emails |
Token ID | 7237 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
itle | +0.350 |
Huss | +0.343 |
rooms | +0.326 |
ollow | +0.311 |
gdala | +0.310 |
Neg logit contributions | |
ment | -0.416 |
heid | -0.400 |
grave | -0.398 |
uph | -0.376 |
alis | -0.371 |
Token | containing |
Token ID | 7268 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
itle | +0.060 |
Huss | +0.059 |
rooms | +0.057 |
ollow | +0.055 |
gdala | +0.054 |
Neg logit contributions | |
ment | -0.040 |
heid | -0.038 |
grave | -0.038 |
uph | -0.035 |
alis | -0.035 |
Token | news |
Token ID | 1705 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
itle | +0.555 |
Huss | +0.545 |
rooms | +0.525 |
gdala | +0.504 |
ollow | +0.504 |
Neg logit contributions | |
ment | -0.435 |
heid | -0.415 |
grave | -0.411 |
uph | -0.383 |
alis | -0.376 |
Token | content |
Token ID | 2695 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
itle | +0.829 |
Huss | +0.817 |
rooms | +0.785 |
ollow | +0.761 |
gdala | +0.759 |
Neg logit contributions | |
ment | -0.510 |
heid | -0.482 |
grave | -0.478 |
uph | -0.440 |
alis | -0.432 |
Token | , |
Token ID | 837 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
itle | +0.496 |
Huss | +0.486 |
rooms | +0.459 |
ollow | +0.437 |
gdala | +0.435 |
Neg logit contributions | |
ment | -0.688 |
heid | -0.663 |
grave | -0.658 |
uph | -0.626 |
alis | -0.618 |
Token | updates |
Token ID | 5992 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
itle | +0.928 |
Huss | +0.907 |
rooms | +0.869 |
ollow | +0.835 |
gdala | +0.835 |
Neg logit contributions | |
ment | -0.877 |
heid | -0.835 |
grave | -0.827 |
uph | -0.778 |
alis | -0.770 |
Token | and |
Token ID | 290 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
itle | +0.236 |
Huss | +0.233 |
rooms | +0.223 |
ollow | +0.215 |
gdala | +0.214 |
Neg logit contributions | |
ment | -0.191 |
heid | -0.183 |
grave | -0.182 |
uph | -0.170 |
alis | -0.167 |
Token | promotions |
Token ID | 20699 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
itle | +0.109 |
Huss | +0.107 |
rooms | +0.102 |
ollow | +0.097 |
gdala | +0.096 |
Neg logit contributions | |
ment | -0.129 |
heid | -0.124 |
grave | -0.124 |
uph | -0.117 |
alis | -0.116 |
Token | from |
Token ID | 422 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
itle | +0.600 |
Huss | +0.590 |
rooms | +0.567 |
ollow | +0.546 |
gdala | +0.544 |
Neg logit contributions | |
ment | -0.494 |
heid | -0.471 |
grave | -0.467 |
uph | -0.437 |
alis | -0.430 |
Token | The |
Token ID | 383 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ment | +0.158 |
heid | +0.151 |
grave | +0.151 |
uph | +0.142 |
alis | +0.140 |
Neg logit contributions | |
itle | -0.146 |
Huss | -0.144 |
rooms | -0.137 |
ollow | -0.131 |
gdala | -0.130 |
Token | 204 |
Token ID | 18638 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ment | +0.190 |
heid | +0.184 |
grave | +0.183 |
uph | +0.173 |
alis | +0.171 |
Neg logit contributions | |
itle | -0.146 |
Huss | -0.143 |
rooms | -0.136 |
ollow | -0.129 |
gdala | -0.128 |
Token | O |
Token ID | 440 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
itle | +0.184 |
Huss | +0.181 |
rooms | +0.174 |
ollow | +0.167 |
gdala | +0.166 |
Neg logit contributions | |
ment | -0.157 |
heid | -0.150 |
grave | -0.149 |
uph | -0.140 |
alis | -0.138 |
Token | & |
Token ID | 5 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
itle | +0.174 |
Huss | +0.170 |
rooms | +0.159 |
ollow | +0.148 |
gdala | +0.147 |
Neg logit contributions | |
ment | -0.349 |
heid | -0.338 |
grave | -0.336 |
uph | -0.322 |
alis | -0.319 |
Token | A |
Token ID | 32 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
itle | +0.301 |
Huss | +0.296 |
rooms | +0.283 |
ollow | +0.270 |
gdala | +0.269 |
Neg logit contributions | |
ment | -0.324 |
heid | -0.311 |
grave | -0.309 |
uph | -0.292 |
alis | -0.288 |
Token | - |
Token ID | 12 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
itle | +0.289 |
Huss | +0.284 |
rooms | +0.272 |
ollow | +0.261 |
gdala | +0.260 |
Neg logit contributions | |
ment | -0.263 |
heid | -0.252 |
grave | -0.250 |
uph | -0.235 |
alis | -0.231 |
Token | G |
Token ID | 38 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
itle | +0.197 |
Huss | +0.194 |
rooms | +0.187 |
ollow | +0.179 |
gdala | +0.178 |
Neg logit contributions | |
ment | -0.168 |
heid | -0.160 |
grave | -0.159 |
uph | -0.149 |
alis | -0.147 |
Token | iants |
Token ID | 17883 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
itle | +0.645 |
Huss | +0.636 |
rooms | +0.602 |
gdala | +0.576 |
ollow | +0.576 |
Neg logit contributions | |
ment | -0.755 |
heid | -0.726 |
grave | -0.721 |
uph | -0.682 |
alis | -0.673 |
Token | Super |
Token ID | 3115 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
itle | +0.338 |
Huss | +0.332 |
rooms | +0.318 |
ollow | +0.305 |
gdala | +0.304 |
Neg logit contributions | |
ment | -0.305 |
heid | -0.292 |
grave | -0.290 |
uph | -0.272 |
alis | -0.268 |
Token | bowl |
Token ID | 36859 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ment | +0.316 |
heid | +0.304 |
grave | +0.300 |
uph | +0.281 |
alis | +0.277 |
Neg logit contributions | |
itle | -0.397 |
Huss | -0.391 |
rooms | -0.376 |
ollow | -0.360 |
gdala | -0.359 |
Token | - |
Token ID | 12 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
itle | +0.279 |
Huss | +0.274 |
rooms | +0.261 |
ollow | +0.249 |
gdala | +0.248 |
Neg logit contributions | |
ment | -0.312 |
heid | -0.300 |
grave | -0.298 |
uph | -0.282 |
alis | -0.278 |
Token | Italian |
Token ID | 45696 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
itle | +0.082 |
Huss | +0.080 |
rooms | +0.077 |
ollow | +0.074 |
gdala | +0.074 |
Neg logit contributions | |
ment | -0.073 |
heid | -0.070 |
grave | -0.070 |
uph | -0.065 |
alis | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ment | +0.166 |
heid | +0.159 |
grave | +0.158 |
uph | +0.148 |
alis | +0.145 |
Neg logit contributions | |
itle | -0.207 |
Huss | -0.205 |
rooms | -0.196 |
ollow | -0.189 |
gdala | -0.188 |
Token | Christian |
Token ID | 4302 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ment | +0.154 |
heid | +0.148 |
grave | +0.146 |
uph | +0.137 |
alis | +0.135 |
Neg logit contributions | |
itle | -0.196 |
Huss | -0.194 |
rooms | -0.186 |
ollow | -0.179 |
gdala | -0.178 |
Token | doctrine |
Token ID | 13115 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ment | +0.176 |
heid | +0.169 |
grave | +0.167 |
uph | +0.156 |
alis | +0.154 |
Neg logit contributions | |
itle | -0.206 |
Huss | -0.204 |
rooms | -0.195 |
ollow | -0.187 |
gdala | -0.186 |
Token | ; |
Token ID | 26 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ment | +0.172 |
heid | +0.165 |
grave | +0.164 |
uph | +0.153 |
alis | +0.151 |
Neg logit contributions | |
itle | -0.196 |
Huss | -0.194 |
rooms | -0.185 |
ollow | -0.178 |
gdala | -0.177 |
Token | Od |
Token ID | 10529 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
ment | +0.108 |
heid | +0.103 |
grave | +0.103 |
uph | +0.096 |
alis | +0.095 |
Neg logit contributions | |
itle | -0.127 |
Huss | -0.125 |
rooms | -0.120 |
ollow | -0.115 |
gdala | -0.114 |
Token | ys |
Token ID | 893 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ment | +0.421 |
heid | +0.395 |
grave | +0.391 |
uph | +0.352 |
quer | +0.339 |
Neg logit contributions | |
itle | -0.960 |
Huss | -0.948 |
rooms | -0.919 |
ollow | -0.890 |
gdala | -0.886 |
Token | se |
Token ID | 325 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
itle | +1.028 |
Huss | +1.010 |
rooms | +0.966 |
gdala | +0.927 |
ollow | +0.925 |
Neg logit contributions | |
ment | -0.943 |
heid | -0.906 |
grave | -0.897 |
uph | -0.837 |
alis | -0.834 |
Token | us |
Token ID | 385 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
itle | +0.258 |
Huss | +0.254 |
rooms | +0.245 |
ollow | +0.236 |
gdala | +0.235 |
Neg logit contributions | |
ment | -0.189 |
heid | -0.180 |
grave | -0.179 |
uph | -0.166 |
alis | -0.163 |
Token | tied |
Token ID | 8165 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ment | +0.076 |
heid | +0.072 |
grave | +0.072 |
uph | +0.067 |
alis | +0.066 |
Neg logit contributions | |
itle | -0.091 |
Huss | -0.090 |
rooms | -0.087 |
ollow | -0.083 |
gdala | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
itle | +0.022 |
Huss | +0.022 |
rooms | +0.021 |
ollow | +0.020 |
gdala | +0.020 |
Neg logit contributions | |
ment | -0.018 |
heid | -0.018 |
grave | -0.017 |
uph | -0.016 |
alis | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
itle | +0.008 |
Huss | +0.008 |
rooms | +0.008 |
ollow | +0.007 |
gdala | +0.007 |
Neg logit contributions | |
ment | -0.007 |
heid | -0.006 |
grave | -0.006 |
uph | -0.006 |
alis | -0.006 |
Token | other |
Token ID | 584 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ment | +0.021 |
heid | +0.020 |
grave | +0.020 |
uph | +0.019 |
alis | +0.019 |
Neg logit contributions | |
itle | -0.025 |
Huss | -0.024 |
rooms | -0.023 |
ollow | -0.022 |
gdala | -0.022 |
Token | solid |
Token ID | 4735 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
itle | +0.078 |
Huss | +0.077 |
rooms | +0.074 |
ollow | +0.071 |
gdala | +0.071 |
Neg logit contributions | |
ment | -0.068 |
heid | -0.065 |
grave | -0.064 |
uph | -0.060 |
alis | -0.059 |
Token | players |
Token ID | 1938 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ment | +0.029 |
heid | +0.028 |
grave | +0.028 |
uph | +0.026 |
alis | +0.025 |
Neg logit contributions | |
itle | -0.037 |
Huss | -0.036 |
rooms | -0.035 |
ollow | -0.033 |
gdala | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
itle | +0.096 |
Huss | +0.095 |
rooms | +0.091 |
ollow | +0.087 |
gdala | +0.087 |
Neg logit contributions | |
ment | -0.081 |
heid | -0.077 |
grave | -0.077 |
uph | -0.072 |
alis | -0.071 |
Token | Rub |
Token ID | 6256 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
itle | +0.022 |
Huss | +0.022 |
rooms | +0.021 |
ollow | +0.020 |
gdala | +0.020 |
Neg logit contributions | |
ment | -0.019 |
heid | -0.018 |
grave | -0.018 |
uph | -0.017 |
alis | -0.016 |
Token | en |
Token ID | 268 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
ment | +0.014 |
heid | +0.013 |
grave | +0.013 |
uph | +0.012 |
alis | +0.012 |
Neg logit contributions | |
itle | -0.012 |
Huss | -0.012 |
rooms | -0.012 |
ollow | -0.011 |
gdala | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
itle | +0.788 |
Huss | +0.774 |
rooms | +0.749 |
ollow | +0.721 |
gdala | +0.720 |
Neg logit contributions | |
ment | -0.566 |
heid | -0.537 |
grave | -0.532 |
uph | -0.496 |
alis | -0.487 |
Token | R |
Token ID | 49 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
itle | +0.084 |
Huss | +0.083 |
rooms | +0.079 |
ollow | +0.076 |
gdala | +0.076 |
Neg logit contributions | |
ment | -0.074 |
heid | -0.071 |
grave | -0.071 |
uph | -0.066 |
alis | -0.065 |
Token | UB |
Token ID | 10526 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
ment | +0.034 |
heid | +0.033 |
grave | +0.033 |
uph | +0.031 |
alis | +0.030 |
Neg logit contributions | |
itle | -0.031 |
Huss | -0.030 |
rooms | -0.029 |
ollow | -0.028 |
gdala | -0.027 |
Token | INO |
Token ID | 46016 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
itle | +0.031 |
Huss | +0.031 |
rooms | +0.029 |
ollow | +0.028 |
gdala | +0.028 |
Neg logit contributions | |
ment | -0.032 |
heid | -0.030 |
grave | -0.030 |
uph | -0.028 |
alis | -0.028 |
Token | " |
Token ID | 1 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ment | +0.306 |
heid | +0.290 |
grave | +0.289 |
uph | +0.265 |
alis | +0.260 |
Neg logit contributions | |
itle | -0.500 |
Huss | -0.495 |
rooms | -0.475 |
ollow | -0.460 |
gdala | -0.459 |
Token | re |
Token ID | 260 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
ment | +0.036 |
heid | +0.034 |
grave | +0.034 |
uph | +0.032 |
alis | +0.032 |
Neg logit contributions | |
itle | -0.041 |
Huss | -0.041 |
rooms | -0.039 |
ollow | -0.037 |
gdala | -0.037 |
Token | playing |
Token ID | 2712 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
itle | +0.051 |
Huss | +0.050 |
rooms | +0.048 |
ollow | +0.046 |
gdala | +0.046 |
Neg logit contributions | |
ment | -0.040 |
heid | -0.038 |
grave | -0.038 |
uph | -0.035 |
alis | -0.034 |
Token | against |
Token ID | 1028 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
itle | +0.050 |
Huss | +0.049 |
rooms | +0.047 |
ollow | +0.045 |
gdala | +0.045 |
Neg logit contributions | |
ment | -0.042 |
heid | -0.040 |
grave | -0.040 |
uph | -0.037 |
alis | -0.036 |
Token | each |
Token ID | 1123 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
itle | +0.097 |
Huss | +0.096 |
rooms | +0.092 |
ollow | +0.089 |
gdala | +0.088 |
Neg logit contributions | |
ment | -0.080 |
heid | -0.077 |
grave | -0.076 |
uph | -0.071 |
alis | -0.070 |
Token | other |
Token ID | 584 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
itle | +0.128 |
Huss | +0.126 |
rooms | +0.121 |
ollow | +0.116 |
gdala | +0.116 |
Neg logit contributions | |
ment | -0.108 |
heid | -0.103 |
grave | -0.103 |
uph | -0.096 |
alis | -0.095 |
Token | now |
Token ID | 783 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ment | +0.002 |
heid | +0.002 |
grave | +0.002 |
uph | +0.002 |
alis | +0.002 |
Neg logit contributions | |
itle | -0.003 |
Huss | -0.003 |
rooms | -0.003 |
ollow | -0.003 |
gdala | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
ment | +0.009 |
heid | +0.009 |
grave | +0.009 |
uph | +0.008 |
alis | +0.008 |
Neg logit contributions | |
itle | -0.011 |
Huss | -0.011 |
rooms | -0.010 |
ollow | -0.010 |
gdala | -0.010 |
Token | but |
Token ID | 475 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
itle | +0.058 |
Huss | +0.058 |
rooms | +0.055 |
ollow | +0.053 |
gdala | +0.053 |
Neg logit contributions | |
ment | -0.042 |
heid | -0.040 |
grave | -0.040 |
uph | -0.037 |
alis | -0.037 |
Token | we |
Token ID | 356 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
itle | +0.101 |
Huss | +0.100 |
rooms | +0.096 |
ollow | +0.092 |
gdala | +0.092 |
Neg logit contributions | |
ment | -0.083 |
heid | -0.079 |
grave | -0.078 |
uph | -0.073 |
alis | -0.072 |
Token | did |
Token ID | 750 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
itle | +0.118 |
Huss | +0.116 |
rooms | +0.112 |
ollow | +0.108 |
gdala | +0.107 |
Neg logit contributions | |
ment | -0.089 |
heid | -0.085 |
grave | -0.084 |
uph | -0.078 |
alis | -0.077 |
Token | something |
Token ID | 1223 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
itle | +0.181 |
Huss | +0.178 |
rooms | +0.171 |
ollow | +0.164 |
gdala | +0.163 |
Neg logit contributions | |
ment | -0.156 |
heid | -0.149 |
grave | -0.148 |
uph | -0.139 |
alis | -0.137 |
Token | another |
Token ID | 1194 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
ment | +0.109 |
heid | +0.105 |
grave | +0.104 |
uph | +0.097 |
alis | +0.096 |
Neg logit contributions | |
itle | -0.126 |
Huss | -0.124 |
rooms | -0.119 |
ollow | -0.114 |
gdala | -0.114 |
Token | factor |
Token ID | 5766 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
itle | +0.026 |
Huss | +0.025 |
rooms | +0.024 |
ollow | +0.023 |
gdala | +0.023 |
Neg logit contributions | |
ment | -0.022 |
heid | -0.021 |
grave | -0.021 |
uph | -0.020 |
alis | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ment | +0.067 |
heid | +0.064 |
grave | +0.064 |
uph | +0.060 |
alis | +0.059 |
Neg logit contributions | |
itle | -0.082 |
Huss | -0.081 |
rooms | -0.077 |
ollow | -0.074 |
gdala | -0.074 |
Token | made |
Token ID | 925 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
itle | +0.140 |
Huss | +0.138 |
rooms | +0.132 |
ollow | +0.127 |
gdala | +0.127 |
Neg logit contributions | |
ment | -0.111 |
heid | -0.106 |
grave | -0.105 |
uph | -0.098 |
alis | -0.097 |
Token | us |
Token ID | 514 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
ment | +0.028 |
heid | +0.027 |
grave | +0.027 |
uph | +0.025 |
alis | +0.025 |
Neg logit contributions | |
itle | -0.035 |
Huss | -0.035 |
rooms | -0.033 |
ollow | -0.032 |
gdala | -0.032 |
Token | screw |
Token ID | 9580 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
itle | +0.441 |
Huss | +0.434 |
rooms | +0.418 |
ollow | +0.402 |
gdala | +0.400 |
Neg logit contributions | |
ment | -0.347 |
heid | -0.331 |
grave | -0.328 |
uph | -0.307 |
alis | -0.302 |
Token | procedural |
Token ID | 27931 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
itle | +0.027 |
Huss | +0.027 |
rooms | +0.026 |
ollow | +0.025 |
gdala | +0.025 |
Neg logit contributions | |
ment | -0.018 |
heid | -0.017 |
grave | -0.017 |
uph | -0.015 |
alis | -0.015 |
Token | maps |
Token ID | 8739 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
itle | +0.348 |
Huss | +0.342 |
rooms | +0.328 |
ollow | +0.315 |
gdala | +0.314 |
Neg logit contributions | |
ment | -0.313 |
heid | -0.299 |
grave | -0.297 |
uph | -0.279 |
alis | -0.275 |
Token | for |
Token ID | 329 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ment | +0.044 |
heid | +0.042 |
grave | +0.041 |
uph | +0.039 |
alis | +0.038 |
Neg logit contributions | |
itle | -0.054 |
Huss | -0.053 |
rooms | -0.051 |
ollow | -0.049 |
gdala | -0.049 |
Token | static |
Token ID | 9037 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ment | +0.197 |
heid | +0.190 |
grave | +0.188 |
uph | +0.175 |
alis | +0.172 |
Neg logit contributions | |
itle | -0.245 |
Huss | -0.243 |
rooms | -0.233 |
ollow | -0.224 |
gdala | -0.222 |
Token | maps |
Token ID | 8739 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
itle | +0.185 |
Huss | +0.182 |
rooms | +0.174 |
ollow | +0.167 |
gdala | +0.166 |
Neg logit contributions | |
ment | -0.170 |
heid | -0.163 |
grave | -0.162 |
uph | -0.152 |
alis | -0.149 |
Token | oon |
Token ID | 2049 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
itle | +0.040 |
Huss | +0.039 |
rooms | +0.037 |
ollow | +0.036 |
gdala | +0.035 |
Neg logit contributions | |
ment | -0.045 |
heid | -0.043 |
grave | -0.043 |
uph | -0.041 |
alis | -0.040 |
Token | crisis |
Token ID | 4902 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
itle | +0.266 |
Huss | +0.262 |
rooms | +0.252 |
ollow | +0.243 |
gdala | +0.242 |
Neg logit contributions | |
ment | -0.200 |
heid | -0.190 |
grave | -0.189 |
uph | -0.176 |
alis | -0.173 |
Token | � |
Token ID | 447 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ment | +0.046 |
heid | +0.044 |
grave | +0.044 |
uph | +0.041 |
alis | +0.040 |
Neg logit contributions | |
itle | -0.061 |
Huss | -0.061 |
rooms | -0.058 |
ollow | -0.056 |
gdala | -0.056 |
Token | � |
Token ID | 247 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
itle | +0.008 |
Huss | +0.008 |
rooms | +0.008 |
ollow | +0.008 |
gdala | +0.008 |
Neg logit contributions | |
ment | -0.008 |
heid | -0.008 |
grave | -0.007 |
uph | -0.007 |
alis | -0.007 |
Token | — |
Token ID | 851 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
itle | +0.002 |
Huss | +0.002 |
rooms | +0.002 |
ollow | +0.002 |
gdala | +0.002 |
Neg logit contributions | |
ment | -0.002 |
heid | -0.002 |
grave | -0.002 |
uph | -0.002 |
alis | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
itle | +0.006 |
Huss | +0.005 |
rooms | +0.005 |
ollow | +0.005 |
gdala | +0.005 |
Neg logit contributions | |
ment | -0.005 |
heid | -0.005 |
grave | -0.005 |
uph | -0.005 |
alis | -0.005 |
Token | phrase |
Token ID | 9546 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ment | +0.039 |
heid | +0.037 |
grave | +0.037 |
uph | +0.034 |
alis | +0.034 |
Neg logit contributions | |
itle | -0.048 |
Huss | -0.047 |
rooms | -0.045 |
ollow | -0.043 |
gdala | -0.043 |
Token | I |
Token ID | 314 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
ment | +0.150 |
heid | +0.144 |
grave | +0.143 |
uph | +0.134 |
alis | +0.132 |
Neg logit contributions | |
itle | -0.177 |
Huss | -0.175 |
rooms | -0.167 |
ollow | -0.161 |
gdala | -0.160 |
Token | still |
Token ID | 991 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
ment | +0.006 |
heid | +0.006 |
grave | +0.006 |
uph | +0.006 |
alis | +0.005 |
Neg logit contributions | |
itle | -0.008 |
Huss | -0.007 |
rooms | -0.007 |
ollow | -0.007 |
gdala | -0.007 |
Token | can |
Token ID | 460 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
ment | +0.001 |
heid | +0.001 |
grave | +0.001 |
uph | +0.001 |
alis | +0.001 |
Neg logit contributions | |
itle | -0.002 |
Huss | -0.002 |
rooms | -0.002 |
ollow | -0.002 |
gdala | -0.002 |
Token | � |
Token ID | 447 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ment | +0.036 |
heid | +0.034 |
grave | +0.034 |
uph | +0.032 |
alis | +0.031 |
Neg logit contributions | |
itle | -0.037 |
Huss | -0.036 |
rooms | -0.034 |
ollow | -0.033 |
gdala | -0.033 |
Token | absent |
Token ID | 13717 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
itle | +0.100 |
Huss | +0.098 |
rooms | +0.094 |
ollow | +0.090 |
gdala | +0.090 |
Neg logit contributions | |
ment | -0.094 |
heid | -0.091 |
grave | -0.090 |
uph | -0.085 |
alis | -0.083 |
Token | ( |
Token ID | 357 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ment | +0.052 |
heid | +0.050 |
grave | +0.050 |
uph | +0.047 |
alis | +0.046 |
Neg logit contributions | |
itle | -0.062 |
Huss | -0.061 |
rooms | -0.058 |
ollow | -0.056 |
gdala | -0.056 |
Token | though |
Token ID | 2016 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ment | +0.070 |
heid | +0.068 |
grave | +0.067 |
uph | +0.063 |
alis | +0.062 |
Neg logit contributions | |
itle | -0.074 |
Huss | -0.073 |
rooms | -0.070 |
ollow | -0.067 |
gdala | -0.067 |
Token | expected |
Token ID | 2938 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
ment | +0.115 |
heid | +0.111 |
grave | +0.110 |
uph | +0.103 |
alis | +0.101 |
Neg logit contributions | |
itle | -0.133 |
Huss | -0.131 |
rooms | -0.126 |
ollow | -0.121 |
gdala | -0.120 |
Token | ) |
Token ID | 8 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
itle | +0.079 |
Huss | +0.078 |
rooms | +0.075 |
ollow | +0.072 |
gdala | +0.072 |
Neg logit contributions | |
ment | -0.061 |
heid | -0.059 |
grave | -0.058 |
uph | -0.054 |
alis | -0.053 |
Token | at |
Token ID | 379 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ment | +0.130 |
heid | +0.125 |
grave | +0.124 |
uph | +0.116 |
alis | +0.114 |
Neg logit contributions | |
itle | -0.151 |
Huss | -0.149 |
rooms | -0.143 |
ollow | -0.137 |
gdala | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ment | +0.127 |
heid | +0.122 |
grave | +0.121 |
uph | +0.114 |
alis | +0.112 |
Neg logit contributions | |
itle | -0.134 |
Huss | -0.132 |
rooms | -0.126 |
ollow | -0.121 |
gdala | -0.120 |
Token | battle |
Token ID | 3344 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
itle | +0.016 |
Huss | +0.016 |
rooms | +0.015 |
ollow | +0.015 |
gdala | +0.015 |
Neg logit contributions | |
ment | -0.014 |
heid | -0.013 |
grave | -0.013 |
uph | -0.012 |
alis | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ment | +0.166 |
heid | +0.160 |
grave | +0.158 |
uph | +0.149 |
alis | +0.146 |
Neg logit contributions | |
itle | -0.200 |
Huss | -0.197 |
rooms | -0.190 |
ollow | -0.182 |
gdala | -0.181 |
Token | Hastings |
Token ID | 38330 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
itle | +0.159 |
Huss | +0.156 |
rooms | +0.150 |
ollow | +0.144 |
gdala | +0.143 |
Neg logit contributions | |
ment | -0.141 |
heid | -0.135 |
grave | -0.134 |
uph | -0.125 |
alis | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
itle | +0.163 |
Huss | +0.161 |
rooms | +0.154 |
ollow | +0.148 |
gdala | +0.148 |
Neg logit contributions | |
ment | -0.133 |
heid | -0.128 |
grave | -0.127 |
uph | -0.118 |
alis | -0.116 |
Token | living |
Token ID | 2877 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
itle | +0.022 |
Huss | +0.021 |
rooms | +0.020 |
ollow | +0.020 |
gdala | +0.019 |
Neg logit contributions | |
ment | -0.018 |
heid | -0.017 |
grave | -0.017 |
uph | -0.016 |
alis | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
itle | +0.493 |
Huss | +0.486 |
rooms | +0.466 |
ollow | +0.450 |
gdala | +0.448 |
Neg logit contributions | |
ment | -0.394 |
heid | -0.375 |
grave | -0.372 |
uph | -0.347 |
alis | -0.342 |
Token | fixed |
Token ID | 5969 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
itle | +0.275 |
Huss | +0.271 |
rooms | +0.260 |
ollow | +0.249 |
gdala | +0.248 |
Neg logit contributions | |
ment | -0.242 |
heid | -0.232 |
grave | -0.230 |
uph | -0.216 |
alis | -0.213 |
Token | incomes |
Token ID | 18696 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
itle | +0.189 |
Huss | +0.186 |
rooms | +0.178 |
ollow | +0.170 |
gdala | +0.169 |
Neg logit contributions | |
ment | -0.179 |
heid | -0.171 |
grave | -0.170 |
uph | -0.160 |
alis | -0.158 |
Token | heat |
Token ID | 4894 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
ment | +0.138 |
heid | +0.132 |
grave | +0.131 |
uph | +0.123 |
alis | +0.121 |
Neg logit contributions | |
itle | -0.167 |
Huss | -0.165 |
rooms | -0.158 |
ollow | -0.152 |
gdala | -0.151 |
Token | their |
Token ID | 511 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
ment | +0.286 |
heid | +0.274 |
grave | +0.272 |
uph | +0.253 |
alis | +0.249 |
Neg logit contributions | |
itle | -0.378 |
Huss | -0.373 |
rooms | -0.359 |
ollow | -0.345 |
gdala | -0.342 |
Token | homes |
Token ID | 5682 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
ment | +0.036 |
heid | +0.034 |
grave | +0.034 |
uph | +0.032 |
alis | +0.032 |
Neg logit contributions | |
itle | -0.041 |
Huss | -0.041 |
rooms | -0.039 |
ollow | -0.037 |
gdala | -0.037 |
Token | with |
Token ID | 351 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ment | +0.145 |
heid | +0.139 |
grave | +0.138 |
uph | +0.129 |
alis | +0.127 |
Neg logit contributions | |
itle | -0.175 |
Huss | -0.172 |
rooms | -0.165 |
ollow | -0.159 |
gdala | -0.157 |
Token | oil |
Token ID | 3056 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ment | +0.218 |
heid | +0.209 |
grave | +0.208 |
uph | +0.195 |
alis | +0.191 |
Neg logit contributions | |
itle | -0.254 |
Huss | -0.250 |
rooms | -0.240 |
ollow | -0.230 |
gdala | -0.228 |
Token | during |
Token ID | 1141 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ment | +0.109 |
heid | +0.104 |
grave | +0.103 |
uph | +0.097 |
alis | +0.095 |
Neg logit contributions | |
itle | -0.129 |
Huss | -0.127 |
rooms | -0.122 |
ollow | -0.117 |
gdala | -0.116 |
Token | our |
Token ID | 674 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ment | +0.191 |
heid | +0.183 |
grave | +0.182 |
uph | +0.170 |
alis | +0.167 |
Neg logit contributions | |
itle | -0.241 |
Huss | -0.238 |
rooms | -0.229 |
ollow | -0.219 |
gdala | -0.218 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ment | +0.071 |
heid | +0.068 |
grave | +0.067 |
uph | +0.063 |
alis | +0.062 |
Neg logit contributions | |
itle | -0.090 |
Huss | -0.089 |
rooms | -0.085 |
ollow | -0.082 |
gdala | -0.082 |
Token | offered |
Token ID | 4438 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ment | +0.069 |
heid | +0.067 |
grave | +0.066 |
uph | +0.062 |
alis | +0.061 |
Neg logit contributions | |
itle | -0.080 |
Huss | -0.078 |
rooms | -0.075 |
ollow | -0.072 |
gdala | -0.072 |
Token | in |
Token ID | 287 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ment | +0.109 |
heid | +0.104 |
grave | +0.104 |
uph | +0.097 |
alis | +0.095 |
Neg logit contributions | |
itle | -0.131 |
Huss | -0.130 |
rooms | -0.124 |
ollow | -0.119 |
gdala | -0.119 |
Token | combination |
Token ID | 6087 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
itle | +0.152 |
Huss | +0.150 |
rooms | +0.144 |
ollow | +0.138 |
gdala | +0.138 |
Neg logit contributions | |
ment | -0.127 |
heid | -0.122 |
grave | -0.121 |
uph | -0.113 |
alis | -0.111 |
Token | with |
Token ID | 351 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
itle | +0.005 |
Huss | +0.005 |
rooms | +0.005 |
ollow | +0.005 |
gdala | +0.005 |
Neg logit contributions | |
ment | -0.005 |
heid | -0.004 |
grave | -0.004 |
uph | -0.004 |
alis | -0.004 |
Token | James |
Token ID | 3700 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
itle | +0.033 |
Huss | +0.033 |
rooms | +0.031 |
ollow | +0.030 |
gdala | +0.030 |
Neg logit contributions | |
ment | -0.027 |
heid | -0.026 |
grave | -0.026 |
uph | -0.024 |
alis | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ment | +0.321 |
heid | +0.308 |
grave | +0.305 |
uph | +0.287 |
alis | +0.281 |
Neg logit contributions | |
itle | -0.380 |
Huss | -0.376 |
rooms | -0.359 |
ollow | -0.345 |
gdala | -0.344 |
Token | the |
Token ID | 262 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ment | +0.201 |
heid | +0.192 |
grave | +0.191 |
uph | +0.179 |
alis | +0.175 |
Neg logit contributions | |
itle | -0.243 |
Huss | -0.240 |
rooms | -0.229 |
ollow | -0.221 |
gdala | -0.220 |
Token | Giant |
Token ID | 17384 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ment | +0.123 |
heid | +0.117 |
grave | +0.116 |
uph | +0.109 |
alis | +0.107 |
Neg logit contributions | |
itle | -0.156 |
Huss | -0.154 |
rooms | -0.147 |
ollow | -0.142 |
gdala | -0.141 |
Token | Peach |
Token ID | 33230 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
itle | +0.102 |
Huss | +0.100 |
rooms | +0.095 |
ollow | +0.091 |
gdala | +0.090 |
Neg logit contributions | |
ment | -0.125 |
heid | -0.121 |
grave | -0.120 |
uph | -0.113 |
alis | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ment | +0.340 |
heid | +0.327 |
grave | +0.324 |
uph | +0.303 |
alis | +0.298 |
Neg logit contributions | |
itle | -0.401 |
Huss | -0.396 |
rooms | -0.379 |
ollow | -0.364 |
gdala | -0.362 |
Token | their |
Token ID | 511 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ment | +0.340 |
heid | +0.327 |
grave | +0.325 |
uph | +0.304 |
alis | +0.297 |
Neg logit contributions | |
itle | -0.436 |
Huss | -0.431 |
rooms | -0.415 |
ollow | -0.397 |
gdala | -0.395 |
Token | backyard |
Token ID | 24296 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ment | +0.189 |
heid | +0.181 |
grave | +0.180 |
uph | +0.169 |
alis | +0.166 |
Neg logit contributions | |
itle | -0.206 |
Huss | -0.203 |
rooms | -0.195 |
ollow | -0.187 |
gdala | -0.185 |
Token | , |
Token ID | 11 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
ment | +0.096 |
heid | +0.092 |
grave | +0.092 |
uph | +0.086 |
alis | +0.085 |
Neg logit contributions | |
itle | -0.112 |
Huss | -0.111 |
rooms | -0.107 |
ollow | -0.102 |
gdala | -0.102 |
Token | many |
Token ID | 867 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ment | +0.179 |
heid | +0.172 |
grave | +0.171 |
uph | +0.159 |
alis | +0.156 |
Neg logit contributions | |
itle | -0.229 |
Huss | -0.226 |
rooms | -0.218 |
ollow | -0.209 |
gdala | -0.208 |
Token | small |
Token ID | 1402 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
ment | +0.115 |
heid | +0.110 |
grave | +0.109 |
uph | +0.102 |
alis | +0.100 |
Neg logit contributions | |
itle | -0.140 |
Huss | -0.139 |
rooms | -0.133 |
ollow | -0.128 |
gdala | -0.127 |
Token | cities |
Token ID | 4736 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
ment | +0.043 |
heid | +0.041 |
grave | +0.041 |
uph | +0.038 |
alis | +0.038 |
Neg logit contributions | |
itle | -0.048 |
Huss | -0.047 |
rooms | -0.046 |
ollow | -0.044 |
gdala | -0.043 |
Token | jumped |
Token ID | 11687 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ment | +0.361 |
heid | +0.347 |
grave | +0.345 |
uph | +0.321 |
alis | +0.315 |
Neg logit contributions | |
itle | -0.442 |
Huss | -0.437 |
rooms | -0.421 |
ollow | -0.403 |
gdala | -0.401 |
Token | at |
Token ID | 379 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ment | +0.131 |
heid | +0.126 |
grave | +0.125 |
uph | +0.118 |
alis | +0.116 |
Neg logit contributions | |
itle | -0.145 |
Huss | -0.143 |
rooms | -0.137 |
ollow | -0.131 |
gdala | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | -9.74e-02 |
Pos logit contributions | |
ment | +0.155 |
heid | +0.148 |
grave | +0.147 |
uph | +0.138 |
alis | +0.135 |
Neg logit contributions | |
itle | -0.188 |
Huss | -0.185 |
rooms | -0.178 |
ollow | -0.170 |
gdala | -0.170 |
Token | opportunity |
Token ID | 3663 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ment | +0.048 |
heid | +0.045 |
grave | +0.045 |
uph | +0.041 |
alis | +0.040 |
Neg logit contributions | |
itle | -0.090 |
Huss | -0.089 |
rooms | -0.086 |
ollow | -0.083 |
gdala | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
itle | +0.217 |
Huss | +0.214 |
rooms | +0.206 |
ollow | +0.198 |
gdala | +0.197 |
Neg logit contributions | |
ment | -0.168 |
heid | -0.160 |
grave | -0.159 |
uph | -0.148 |
alis | -0.146 |
Token | of |
Token ID | 286 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
itle | +0.089 |
Huss | +0.088 |
rooms | +0.084 |
ollow | +0.081 |
gdala | +0.080 |
Neg logit contributions | |
ment | -0.076 |
heid | -0.072 |
grave | -0.072 |
uph | -0.067 |
alis | -0.066 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ment | +0.117 |
heid | +0.113 |
grave | +0.112 |
uph | +0.105 |
alis | +0.102 |
Neg logit contributions | |
itle | -0.145 |
Huss | -0.143 |
rooms | -0.137 |
ollow | -0.131 |
gdala | -0.131 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ment | +0.160 |
heid | +0.154 |
grave | +0.154 |
uph | +0.144 |
alis | +0.142 |
Neg logit contributions | |
itle | -0.156 |
Huss | -0.154 |
rooms | -0.147 |
ollow | -0.141 |
gdala | -0.140 |
Token | � |
Token ID | 447 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
ment | +0.138 |
heid | +0.132 |
grave | +0.131 |
uph | +0.122 |
alis | +0.120 |
Neg logit contributions | |
itle | -0.174 |
Huss | -0.172 |
rooms | -0.165 |
ollow | -0.159 |
gdala | -0.158 |
Token | � |
Token ID | 247 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ment | +0.013 |
heid | +0.012 |
grave | +0.012 |
uph | +0.011 |
alis | +0.011 |
Neg logit contributions | |
itle | -0.019 |
Huss | -0.018 |
rooms | -0.018 |
ollow | -0.017 |
gdala | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ment | +0.267 |
heid | +0.259 |
grave | +0.257 |
uph | +0.244 |
alis | +0.241 |
Neg logit contributions | |
itle | -0.202 |
Huss | -0.198 |
rooms | -0.188 |
ollow | -0.178 |
gdala | -0.177 |
Token | primary |
Token ID | 4165 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ment | +0.246 |
heid | +0.236 |
grave | +0.233 |
uph | +0.216 |
alis | +0.211 |
Neg logit contributions | |
itle | -0.365 |
Huss | -0.361 |
rooms | -0.348 |
ollow | -0.334 |
gdala | -0.332 |
Token | campaign |
Token ID | 1923 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ment | +0.227 |
heid | +0.217 |
grave | +0.215 |
uph | +0.199 |
alis | +0.196 |
Neg logit contributions | |
itle | -0.328 |
Huss | -0.324 |
rooms | -0.312 |
ollow | -0.299 |
gdala | -0.298 |
Token | committee |
Token ID | 5583 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ment | +0.331 |
heid | +0.317 |
grave | +0.315 |
uph | +0.290 |
alis | +0.283 |
Neg logit contributions | |
itle | -0.519 |
Huss | -0.514 |
rooms | -0.496 |
ollow | -0.476 |
gdala | -0.474 |
Token | money |
Token ID | 1637 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ment | +0.307 |
heid | +0.294 |
grave | +0.293 |
uph | +0.271 |
alis | +0.266 |
Neg logit contributions | |
itle | -0.444 |
Huss | -0.438 |
rooms | -0.423 |
ollow | -0.406 |
gdala | -0.404 |
Token | comes |
Token ID | 2058 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
ment | +0.177 |
heid | +0.170 |
grave | +0.169 |
uph | +0.158 |
alis | +0.155 |
Neg logit contributions | |
itle | -0.210 |
Huss | -0.207 |
rooms | -0.199 |
ollow | -0.190 |
gdala | -0.189 |
Token | could |
Token ID | 714 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
ment | +0.266 |
heid | +0.255 |
grave | +0.254 |
uph | +0.237 |
alis | +0.232 |
Neg logit contributions | |
itle | -0.348 |
Huss | -0.343 |
rooms | -0.329 |
ollow | -0.316 |
gdala | -0.315 |
Token | be |
Token ID | 307 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
itle | +0.060 |
Huss | +0.059 |
rooms | +0.057 |
ollow | +0.054 |
gdala | +0.054 |
Neg logit contributions | |
ment | -0.047 |
heid | -0.045 |
grave | -0.044 |
uph | -0.041 |
alis | -0.041 |
Token | turn |
Token ID | 1210 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
ment | +0.128 |
heid | +0.123 |
grave | +0.122 |
uph | +0.115 |
alis | +0.113 |
Neg logit contributions | |
itle | -0.151 |
Huss | -0.149 |
rooms | -0.142 |
ollow | -0.137 |
gdala | -0.136 |
Token | into |
Token ID | 656 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
itle | +0.056 |
Huss | +0.055 |
rooms | +0.053 |
ollow | +0.051 |
gdala | +0.050 |
Neg logit contributions | |
ment | -0.047 |
heid | -0.045 |
grave | -0.044 |
uph | -0.041 |
alis | -0.041 |
Token | an |
Token ID | 281 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ment | +0.200 |
heid | +0.191 |
grave | +0.191 |
uph | +0.178 |
alis | +0.175 |
Neg logit contributions | |
itle | -0.240 |
Huss | -0.237 |
rooms | -0.227 |
ollow | -0.218 |
gdala | -0.217 |
Token | M |
Token ID | 337 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
ment | +0.143 |
heid | +0.136 |
grave | +0.136 |
uph | +0.126 |
alis | +0.124 |
Neg logit contributions | |
itle | -0.192 |
Huss | -0.189 |
rooms | -0.181 |
ollow | -0.174 |
gdala | -0.174 |
Token | ST |
Token ID | 2257 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ment | +0.284 |
heid | +0.259 |
grave | +0.258 |
uph | +0.219 |
alis | +0.210 |
Neg logit contributions | |
itle | -1.041 |
Huss | -1.025 |
rooms | -0.998 |
ollow | -0.972 |
gdala | -0.966 |
Token | 3 |
Token ID | 18 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
ment | +0.031 |
heid | +0.029 |
grave | +0.029 |
uph | +0.027 |
alis | +0.026 |
Neg logit contributions | |
itle | -0.047 |
Huss | -0.046 |
rooms | -0.044 |
ollow | -0.043 |
gdala | -0.042 |
Token | K |
Token ID | 42 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
itle | +0.286 |
Huss | +0.281 |
rooms | +0.269 |
ollow | +0.257 |
gdala | +0.256 |
Neg logit contributions | |
ment | -0.308 |
heid | -0.296 |
grave | -0.295 |
uph | -0.278 |
alis | -0.274 |
Token | short |
Token ID | 1790 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
ment | +0.204 |
heid | +0.195 |
grave | +0.195 |
uph | +0.182 |
alis | +0.179 |
Neg logit contributions | |
itle | -0.249 |
Huss | -0.246 |
rooms | -0.235 |
ollow | -0.226 |
gdala | -0.225 |
Token | ? |
Token ID | 30 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ment | +0.043 |
heid | +0.041 |
grave | +0.040 |
uph | +0.038 |
alis | +0.037 |
Neg logit contributions | |
itle | -0.055 |
Huss | -0.054 |
rooms | -0.052 |
ollow | -0.050 |
gdala | -0.050 |
Token | about |
Token ID | 546 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ment | +0.045 |
heid | +0.043 |
grave | +0.043 |
uph | +0.040 |
alis | +0.039 |
Neg logit contributions | |
itle | -0.057 |
Huss | -0.056 |
rooms | -0.054 |
ollow | -0.051 |
gdala | -0.051 |
Token | � |
Token ID | 447 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ment | +0.082 |
heid | +0.078 |
grave | +0.077 |
uph | +0.072 |
alis | +0.071 |
Neg logit contributions | |
itle | -0.108 |
Huss | -0.107 |
rooms | -0.103 |
ollow | -0.099 |
gdala | -0.098 |
Token | � |
Token ID | 247 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
ment | +0.008 |
heid | +0.008 |
grave | +0.008 |
uph | +0.007 |
alis | +0.007 |
Neg logit contributions | |
itle | -0.009 |
Huss | -0.009 |
rooms | -0.008 |
ollow | -0.008 |
gdala | -0.008 |
Token | might |
Token ID | 1244 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
ment | +0.022 |
heid | +0.021 |
grave | +0.021 |
uph | +0.019 |
alis | +0.019 |
Neg logit contributions | |
itle | -0.028 |
Huss | -0.028 |
rooms | -0.027 |
ollow | -0.026 |
gdala | -0.026 |
Token | be |
Token ID | 307 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ment | +0.054 |
heid | +0.052 |
grave | +0.052 |
uph | +0.048 |
alis | +0.047 |
Neg logit contributions | |
itle | -0.076 |
Huss | -0.075 |
rooms | -0.072 |
ollow | -0.069 |
gdala | -0.069 |
Token | an |
Token ID | 281 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ment | +0.066 |
heid | +0.063 |
grave | +0.063 |
uph | +0.059 |
alis | +0.058 |
Neg logit contributions | |
itle | -0.078 |
Huss | -0.077 |
rooms | -0.073 |
ollow | -0.070 |
gdala | -0.070 |
Token | an |
Token ID | 281 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ment | +0.300 |
heid | +0.287 |
grave | +0.285 |
uph | +0.266 |
alis | +0.261 |
Neg logit contributions | |
itle | -0.377 |
Huss | -0.371 |
rooms | -0.355 |
ollow | -0.341 |
gdala | -0.340 |
Token | agram |
Token ID | 6713 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ment | +0.190 |
heid | +0.184 |
grave | +0.184 |
uph | +0.175 |
alis | +0.173 |
Neg logit contributions | |
itle | -0.109 |
Huss | -0.106 |
rooms | -0.100 |
ollow | -0.094 |
gdala | -0.093 |
Token | indicator |
Token ID | 16916 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
ment | +0.085 |
heid | +0.082 |
grave | +0.081 |
uph | +0.076 |
alis | +0.075 |
Neg logit contributions | |
itle | -0.098 |
Huss | -0.096 |
rooms | -0.092 |
ollow | -0.088 |
gdala | -0.088 |
Token | ? |
Token ID | 30 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ment | +0.048 |
heid | +0.046 |
grave | +0.046 |
uph | +0.043 |
alis | +0.042 |
Neg logit contributions | |
itle | -0.059 |
Huss | -0.058 |
rooms | -0.056 |
ollow | -0.054 |
gdala | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ment | +0.086 |
heid | +0.082 |
grave | +0.082 |
uph | +0.077 |
alis | +0.076 |
Neg logit contributions | |
itle | -0.091 |
Huss | -0.090 |
rooms | -0.086 |
ollow | -0.082 |
gdala | -0.082 |
Token | uk |
Token ID | 2724 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
ment | +0.411 |
heid | +0.398 |
grave | +0.396 |
uph | +0.376 |
alis | +0.372 |
Neg logit contributions | |
itle | -0.286 |
Huss | -0.280 |
rooms | -0.267 |
ollow | -0.253 |
gdala | -0.250 |
Token | or |
Token ID | 393 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ment | +0.064 |
heid | +0.061 |
grave | +0.061 |
uph | +0.057 |
alis | +0.056 |
Neg logit contributions | |
itle | -0.075 |
Huss | -0.073 |
rooms | -0.071 |
ollow | -0.068 |
gdala | -0.067 |
Token | call |
Token ID | 869 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
itle | +0.173 |
Huss | +0.170 |
rooms | +0.164 |
ollow | +0.157 |
gdala | +0.157 |
Neg logit contributions | |
ment | -0.139 |
heid | -0.133 |
grave | -0.132 |
uph | -0.123 |
alis | -0.121 |
Token | 0 |
Token ID | 657 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
ment | +0.005 |
heid | +0.004 |
grave | +0.004 |
uph | +0.004 |
alis | +0.004 |
Neg logit contributions | |
itle | -0.005 |
Huss | -0.005 |
rooms | -0.005 |
ollow | -0.004 |
gdala | -0.004 |
Token | 207 |
Token ID | 22745 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
itle | +0.017 |
Huss | +0.017 |
rooms | +0.016 |
ollow | +0.016 |
gdala | +0.015 |
Neg logit contributions | |
ment | -0.020 |
heid | -0.019 |
grave | -0.019 |
uph | -0.018 |
alis | -0.018 |
Token | 7 |
Token ID | 767 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ment | +0.961 |
heid | +0.931 |
grave | +0.926 |
uph | +0.872 |
alis | +0.860 |
Neg logit contributions | |
itle | -1.138 |
Huss | -1.134 |
rooms | -1.084 |
ollow | -1.063 |
gdala | -1.032 |
Token | 82 |
Token ID | 6469 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ment | +1.535 |
heid | +1.521 |
grave | +1.513 |
uph | +1.410 |
alis | +1.396 |
Neg logit contributions | |
itle | -1.685 |
Huss | -1.634 |
rooms | -1.573 |
ollow | -1.535 |
gdala | -1.488 |
Token | 4 |
Token ID | 604 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ment | +1.017 |
heid | +0.993 |
grave | +0.965 |
uph | +0.923 |
alis | +0.908 |
Neg logit contributions | |
itle | -1.166 |
Huss | -1.141 |
rooms | -1.120 |
ollow | -1.072 |
gdala | -1.057 |
Token | 368 |
Token ID | 27412 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
itle | +0.350 |
Huss | +0.345 |
rooms | +0.330 |
ollow | +0.315 |
gdala | +0.315 |
Neg logit contributions | |
ment | -0.343 |
heid | -0.329 |
grave | -0.327 |
uph | -0.308 |
alis | -0.303 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
itle | +0.149 |
Huss | +0.146 |
rooms | +0.140 |
ollow | +0.134 |
gdala | +0.134 |
Neg logit contributions | |
ment | -0.143 |
heid | -0.138 |
grave | -0.137 |
uph | -0.129 |
alis | -0.127 |
Token | To |
Token ID | 2514 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
ment | +0.091 |
heid | +0.087 |
grave | +0.086 |
uph | +0.081 |
alis | +0.080 |
Neg logit contributions | |
itle | -0.099 |
Huss | -0.097 |
rooms | -0.093 |
ollow | -0.089 |
gdala | -0.089 |
Token | iae |
Token ID | 33100 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
itle | +0.062 |
Huss | +0.061 |
rooms | +0.058 |
ollow | +0.056 |
gdala | +0.056 |
Neg logit contributions | |
ment | -0.058 |
heid | -0.056 |
grave | -0.055 |
uph | -0.052 |
alis | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ment | +0.102 |
heid | +0.097 |
grave | +0.096 |
uph | +0.090 |
alis | +0.089 |
Neg logit contributions | |
itle | -0.123 |
Huss | -0.121 |
rooms | -0.116 |
ollow | -0.112 |
gdala | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ment | +0.063 |
heid | +0.060 |
grave | +0.059 |
uph | +0.055 |
alis | +0.054 |
Neg logit contributions | |
itle | -0.084 |
Huss | -0.083 |
rooms | -0.080 |
ollow | -0.077 |
gdala | -0.076 |
Token | Please |
Token ID | 5492 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ment | +0.215 |
heid | +0.207 |
grave | +0.205 |
uph | +0.193 |
alis | +0.190 |
Neg logit contributions | |
itle | -0.235 |
Huss | -0.231 |
rooms | -0.221 |
ollow | -0.212 |
gdala | -0.211 |
Token | help |
Token ID | 1037 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
ment | +0.173 |
heid | +0.166 |
grave | +0.165 |
uph | +0.154 |
alis | +0.152 |
Neg logit contributions | |
itle | -0.205 |
Huss | -0.202 |
rooms | -0.193 |
ollow | -0.186 |
gdala | -0.185 |
Token | support |
Token ID | 1104 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ment | +0.435 |
heid | +0.416 |
grave | +0.415 |
uph | +0.385 |
alis | +0.382 |
Neg logit contributions | |
itle | -0.498 |
Huss | -0.491 |
rooms | -0.469 |
ollow | -0.453 |
gdala | -0.446 |
Token | the |
Token ID | 262 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
ment | +1.643 |
grave | +1.592 |
heid | +1.587 |
uph | +1.467 |
alis | +1.467 |
Neg logit contributions | |
itle | -1.725 |
Huss | -1.720 |
rooms | -1.622 |
ollow | -1.547 |
gery | -1.521 |
Token | mission |
Token ID | 4365 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ment | +0.381 |
grave | +0.368 |
heid | +0.366 |
uph | +0.341 |
alis | +0.339 |
Neg logit contributions | |
itle | -0.387 |
Huss | -0.381 |
rooms | -0.362 |
ollow | -0.347 |
gdala | -0.344 |
Token | of |
Token ID | 286 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ment | +0.804 |
grave | +0.788 |
heid | +0.780 |
uph | +0.735 |
alis | +0.729 |
Neg logit contributions | |
itle | -0.856 |
Huss | -0.844 |
rooms | -0.805 |
ollow | -0.779 |
gdala | -0.764 |
Token | New |
Token ID | 968 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ment | +1.146 |
grave | +1.098 |
heid | +1.077 |
alis | +1.009 |
uph | +1.009 |
Neg logit contributions | |
Huss | -1.379 |
itle | -1.375 |
rooms | -1.314 |
ollow | -1.263 |
gdala | -1.235 |
Token | Advent |
Token ID | 33732 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
ment | +0.590 |
heid | +0.562 |
grave | +0.550 |
uph | +0.518 |
inth | +0.506 |
Neg logit contributions | |
itle | -1.085 |
Huss | -1.085 |
rooms | -1.049 |
ollow | -1.006 |
gdala | -1.005 |
Token | attorneys |
Token ID | 14449 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
itle | +0.623 |
Huss | +0.610 |
rooms | +0.583 |
ollow | +0.561 |
gdala | +0.558 |
Neg logit contributions | |
ment | -0.667 |
heid | -0.639 |
grave | -0.636 |
uph | -0.598 |
alis | -0.590 |
Token | say |
Token ID | 910 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
itle | +0.669 |
Huss | +0.658 |
rooms | +0.633 |
ollow | +0.608 |
gdala | +0.606 |
Neg logit contributions | |
ment | -0.563 |
heid | -0.536 |
grave | -0.533 |
uph | -0.500 |
alis | -0.492 |
Token | he |
Token ID | 339 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
ment | +0.551 |
heid | +0.539 |
grave | +0.532 |
uph | +0.502 |
alis | +0.494 |
Neg logit contributions | |
itle | -0.603 |
Huss | -0.599 |
rooms | -0.571 |
ollow | -0.550 |
gdala | -0.547 |
Token | should |
Token ID | 815 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
ment | +0.407 |
heid | +0.395 |
grave | +0.387 |
uph | +0.363 |
alis | +0.359 |
Neg logit contributions | |
itle | -0.501 |
Huss | -0.497 |
rooms | -0.477 |
ollow | -0.456 |
gdala | -0.455 |
Token | get |
Token ID | 651 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
itle | +0.707 |
Huss | +0.693 |
rooms | +0.662 |
ollow | +0.638 |
gdala | +0.638 |
Neg logit contributions | |
ment | -0.616 |
heid | -0.587 |
grave | -0.583 |
uph | -0.544 |
alis | -0.536 |
Token | less |
Token ID | 1342 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
itle | +0.488 |
Huss | +0.480 |
rooms | +0.461 |
ollow | +0.442 |
gdala | +0.441 |
Neg logit contributions | |
ment | -0.418 |
heid | -0.399 |
grave | -0.397 |
uph | -0.371 |
alis | -0.365 |
Token | than |
Token ID | 621 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ment | +1.304 |
heid | +1.278 |
grave | +1.256 |
uph | +1.192 |
alis | +1.184 |
Neg logit contributions | |
itle | -1.209 |
Huss | -1.185 |
rooms | -1.146 |
gdala | -1.068 |
ollow | -1.067 |
Token | 10 |
Token ID | 838 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ment | +0.841 |
heid | +0.826 |
grave | +0.811 |
uph | +0.759 |
alis | +0.751 |
Neg logit contributions | |
itle | -0.942 |
Huss | -0.937 |
rooms | -0.878 |
ollow | -0.857 |
gdala | -0.845 |
Token | years |
Token ID | 812 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ment | +0.070 |
heid | +0.067 |
grave | +0.066 |
uph | +0.062 |
alis | +0.061 |
Neg logit contributions | |
itle | -0.100 |
Huss | -0.098 |
rooms | -0.094 |
ollow | -0.091 |
gdala | -0.091 |
Token | in |
Token ID | 287 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
itle | +0.176 |
Huss | +0.173 |
rooms | +0.166 |
ollow | +0.160 |
gdala | +0.159 |
Neg logit contributions | |
ment | -0.145 |
heid | -0.139 |
grave | -0.138 |
uph | -0.129 |
alis | -0.127 |
Token | prison |
Token ID | 3770 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ment | +0.188 |
heid | +0.182 |
grave | +0.181 |
uph | +0.172 |
alis | +0.171 |
Neg logit contributions | |
itle | -0.124 |
Huss | -0.121 |
rooms | -0.115 |
ollow | -0.109 |
gdala | -0.108 |
Token | Studios |
Token ID | 13799 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ment | +0.301 |
heid | +0.287 |
grave | +0.280 |
uph | +0.259 |
alis | +0.254 |
Neg logit contributions | |
itle | -0.519 |
Huss | -0.513 |
rooms | -0.496 |
ollow | -0.478 |
gdala | -0.476 |
Token | Hollywood |
Token ID | 8502 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ment | +0.440 |
heid | +0.423 |
grave | +0.417 |
uph | +0.392 |
alis | +0.384 |
Neg logit contributions | |
itle | -0.548 |
Huss | -0.542 |
rooms | -0.522 |
ollow | -0.500 |
gdala | -0.497 |
Token | to |
Token ID | 284 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ment | +0.108 |
heid | +0.104 |
grave | +0.103 |
uph | +0.096 |
alis | +0.094 |
Neg logit contributions | |
itle | -0.132 |
Huss | -0.130 |
rooms | -0.125 |
ollow | -0.120 |
gdala | -0.120 |
Token | see |
Token ID | 766 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
itle | +0.173 |
Huss | +0.170 |
rooms | +0.163 |
ollow | +0.156 |
gdala | +0.156 |
Neg logit contributions | |
ment | -0.156 |
heid | -0.150 |
grave | -0.149 |
uph | -0.139 |
alis | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
ment | +0.126 |
heid | +0.121 |
grave | +0.120 |
uph | +0.112 |
alis | +0.110 |
Neg logit contributions | |
itle | -0.152 |
Huss | -0.150 |
rooms | -0.144 |
ollow | -0.138 |
gdala | -0.137 |
Token | From |
Token ID | 3574 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ment | +0.060 |
heid | +0.057 |
grave | +0.057 |
uph | +0.053 |
alis | +0.052 |
Neg logit contributions | |
itle | -0.073 |
Huss | -0.072 |
rooms | -0.069 |
ollow | -0.067 |
gdala | -0.066 |
Token | Dusk |
Token ID | 42553 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ment | +0.972 |
heid | +0.951 |
grave | +0.909 |
uph | +0.849 |
quer | +0.840 |
Neg logit contributions | |
itle | -1.551 |
Huss | -1.541 |
rooms | -1.460 |
ollow | -1.424 |
gdala | -1.411 |
Token | Till |
Token ID | 17888 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ment | +0.443 |
heid | +0.426 |
grave | +0.423 |
uph | +0.393 |
alis | +0.388 |
Neg logit contributions | |
itle | -0.577 |
Huss | -0.569 |
rooms | -0.547 |
ollow | -0.531 |
gdala | -0.523 |
Token | Dawn |
Token ID | 12258 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ment | +0.751 |
heid | +0.720 |
grave | +0.711 |
uph | +0.667 |
alis | +0.652 |
Neg logit contributions | |
Huss | -1.000 |
itle | -0.998 |
rooms | -0.946 |
ollow | -0.916 |
gdala | -0.900 |
Token | maze |
Token ID | 31237 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ment | +0.126 |
heid | +0.121 |
grave | +0.120 |
uph | +0.112 |
alis | +0.110 |
Neg logit contributions | |
itle | -0.151 |
Huss | -0.149 |
rooms | -0.143 |
ollow | -0.137 |
gdala | -0.136 |
Token | coming |
Token ID | 2406 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
itle | +0.105 |
Huss | +0.104 |
rooms | +0.100 |
ollow | +0.096 |
gdala | +0.095 |
Neg logit contributions | |
ment | -0.090 |
heid | -0.086 |
grave | -0.086 |
uph | -0.080 |
alis | -0.079 |
Token | Catholic |
Token ID | 7835 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ment | +0.141 |
heid | +0.132 |
grave | +0.132 |
uph | +0.121 |
alis | +0.117 |
Neg logit contributions | |
itle | -0.270 |
Huss | -0.269 |
rooms | -0.259 |
ollow | -0.251 |
gdala | -0.248 |
Token | Encyclopedia |
Token ID | 36732 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
itle | +0.021 |
Huss | +0.021 |
rooms | +0.020 |
ollow | +0.019 |
gdala | +0.019 |
Neg logit contributions | |
ment | -0.013 |
heid | -0.012 |
grave | -0.012 |
uph | -0.011 |
alis | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ment | +0.846 |
grave | +0.810 |
heid | +0.804 |
uph | +0.771 |
�� | +0.750 |
Neg logit contributions | |
itle | -0.920 |
Huss | -0.903 |
rooms | -0.863 |
ollow | -0.826 |
gdala | -0.818 |
Token | Church |
Token ID | 4564 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ment | +0.344 |
heid | +0.330 |
grave | +0.322 |
uph | +0.301 |
alis | +0.298 |
Neg logit contributions | |
itle | -0.501 |
Huss | -0.497 |
rooms | -0.474 |
ollow | -0.460 |
gdala | -0.453 |
Token | Fathers |
Token ID | 30969 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ment | +0.559 |
heid | +0.534 |
grave | +0.526 |
uph | +0.474 |
inth | +0.459 |
Neg logit contributions | |
itle | -1.424 |
Huss | -1.416 |
rooms | -1.386 |
ollow | -1.325 |
gdala | -1.318 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ment | +1.296 |
heid | +1.280 |
grave | +1.249 |
uph | +1.203 |
alis | +1.185 |
Neg logit contributions | |
itle | -1.373 |
Huss | -1.353 |
rooms | -1.313 |
gdala | -1.212 |
ollow | -1.210 |
Token | Sum |
Token ID | 5060 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
ment | +0.938 |
heid | +0.915 |
grave | +0.890 |
uph | +0.826 |
alis | +0.825 |
Neg logit contributions | |
itle | -1.567 |
Huss | -1.553 |
rooms | -1.488 |
ollow | -1.446 |
gdala | -1.414 |
Token | ma |
Token ID | 2611 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ment | +0.523 |
heid | +0.507 |
grave | +0.500 |
uph | +0.472 |
inth | +0.458 |
Neg logit contributions | |
itle | -0.614 |
Huss | -0.600 |
rooms | -0.582 |
gdala | -0.552 |
ollow | -0.552 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ment | +0.690 |
grave | +0.662 |
heid | +0.656 |
uph | +0.624 |
alis | +0.604 |
Neg logit contributions | |
itle | -0.759 |
Huss | -0.750 |
rooms | -0.715 |
ollow | -0.682 |
gdala | -0.679 |
Token | Bible |
Token ID | 9111 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
ment | +0.629 |
grave | +0.595 |
heid | +0.594 |
uph | +0.554 |
alis | +0.550 |
Neg logit contributions | |
itle | -0.926 |
Huss | -0.909 |
rooms | -0.872 |
ollow | -0.847 |
gdala | -0.836 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ment | +0.617 |
grave | +0.598 |
heid | +0.593 |
uph | +0.556 |
quer | +0.543 |
Neg logit contributions | |
itle | -0.704 |
Huss | -0.688 |
rooms | -0.668 |
ollow | -0.635 |
gdala | -0.627 |