Token | com |
Token ID | 785 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
�醒 | +0.389 |
olit | +0.330 |
ult | +0.330 |
sted | +0.325 |
adr | +0.309 |
Neg logit contributions | |
DX | -0.481 |
Fathers | -0.473 |
resolves | -0.470 |
DX | -0.470 |
cow | -0.464 |
Token | / |
Token ID | 14 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
�醒 | +0.190 |
ult | +0.171 |
olit | +0.171 |
sted | +0.169 |
adr | +0.164 |
Neg logit contributions | |
DX | -0.083 |
Fathers | -0.081 |
resolves | -0.080 |
DX | -0.080 |
cow | -0.078 |
Token | watch |
Token ID | 8340 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
�醒 | +0.552 |
olit | +0.486 |
ult | +0.484 |
sted | +0.480 |
adr | +0.461 |
Neg logit contributions | |
DX | -0.451 |
Fathers | -0.435 |
DX | -0.433 |
resolves | -0.433 |
cow | -0.428 |
Token | ? |
Token ID | 30 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
DX | +0.211 |
Fathers | +0.207 |
resolves | +0.206 |
DX | +0.206 |
cow | +0.203 |
Neg logit contributions | |
�醒 | -0.238 |
olit | -0.208 |
ult | -0.208 |
sted | -0.206 |
adr | -0.197 |
Token | v |
Token ID | 85 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
�醒 | +0.306 |
olit | +0.266 |
ult | +0.260 |
sted | +0.260 |
adr | +0.250 |
Neg logit contributions | |
DX | -0.268 |
resolves | -0.262 |
DX | -0.260 |
Fathers | -0.259 |
cow | -0.259 |
Token | = |
Token ID | 28 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
�醒 | +0.014 |
olit | +0.012 |
sted | +0.012 |
ult | +0.012 |
adr | +0.011 |
Neg logit contributions | |
DX | -0.012 |
Fathers | -0.011 |
resolves | -0.011 |
DX | -0.011 |
cow | -0.011 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
�醒 | +2.639 |
ult | +2.371 |
olit | +2.371 |
sted | +2.355 |
adr | +2.251 |
Neg logit contributions | |
DX | -2.102 |
Fathers | -2.051 |
resolves | -2.043 |
DX | -2.035 |
cow | -2.003 |
Token | g |
Token ID | 70 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
DX | +0.036 |
DX | +0.034 |
Fathers | +0.033 |
resolves | +0.033 |
cow | +0.033 |
Neg logit contributions | |
�醒 | -0.044 |
olit | -0.038 |
sted | -0.038 |
ult | -0.038 |
adr | -0.036 |
Token | 7 |
Token ID | 22 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
�醒 | +0.066 |
olit | +0.058 |
sted | +0.057 |
ult | +0.057 |
adr | +0.054 |
Neg logit contributions | |
DX | -0.051 |
DX | -0.048 |
Fathers | -0.048 |
resolves | -0.048 |
cow | -0.047 |
Token | p |
Token ID | 79 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
�醒 | +0.049 |
olit | +0.043 |
sted | +0.043 |
ult | +0.043 |
adr | +0.041 |
Neg logit contributions | |
DX | -0.039 |
DX | -0.037 |
Fathers | -0.037 |
resolves | -0.037 |
cow | -0.036 |
Token | k |
Token ID | 74 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
DX | +0.025 |
DX | +0.024 |
Fathers | +0.024 |
resolves | +0.024 |
cow | +0.023 |
Neg logit contributions | |
�醒 | -0.033 |
olit | -0.029 |
sted | -0.029 |
ult | -0.028 |
adr | -0.027 |
Token | 00 |
Token ID | 405 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
DX | +0.327 |
resolves | +0.313 |
DX | +0.312 |
Fathers | +0.308 |
cow | +0.304 |
Neg logit contributions | |
�醒 | -0.446 |
olit | -0.402 |
ult | -0.399 |
sted | -0.396 |
adr | -0.381 |
Token | 65 |
Token ID | 2996 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
DX | +0.310 |
Fathers | +0.300 |
DX | +0.300 |
resolves | +0.297 |
cow | +0.290 |
Neg logit contributions | |
�醒 | -0.220 |
olit | -0.185 |
ult | -0.183 |
sted | -0.183 |
adr | -0.172 |
Token | E |
Token ID | 36 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
DX | +0.284 |
Fathers | +0.275 |
resolves | +0.273 |
DX | +0.271 |
cow | +0.264 |
Neg logit contributions | |
�醒 | -0.746 |
ult | -0.690 |
olit | -0.689 |
sted | -0.686 |
adr | -0.663 |
Token | & |
Token ID | 5 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
�醒 | +0.155 |
olit | +0.142 |
ult | +0.142 |
sted | +0.141 |
adr | +0.136 |
Neg logit contributions | |
DX | -0.082 |
Fathers | -0.080 |
DX | -0.080 |
resolves | -0.080 |
cow | -0.078 |
Token | for |
Token ID | 1640 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
DX | +0.163 |
DX | +0.157 |
resolves | +0.156 |
Fathers | +0.154 |
cow | +0.152 |
Neg logit contributions | |
�醒 | -0.184 |
olit | -0.164 |
sted | -0.162 |
ult | -0.161 |
adr | -0.153 |
Token | = |
Token ID | 28 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
�醒 | +0.308 |
olit | +0.278 |
sted | +0.273 |
ult | +0.272 |
adr | +0.259 |
Neg logit contributions | |
DX | -0.254 |
DX | -0.246 |
Fathers | -0.244 |
resolves | -0.244 |
cow | -0.241 |
Token | count |
Token ID | 9127 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
�醒 | +2.355 |
ult | +2.127 |
olit | +2.123 |
sted | +2.110 |
adr | +2.019 |
Neg logit contributions | |
DX | -1.871 |
Fathers | -1.838 |
resolves | -1.830 |
DX | -1.818 |
cow | -1.793 |
Token | y |
Token ID | 88 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
DX | +0.132 |
Fathers | +0.128 |
resolves | +0.127 |
DX | +0.127 |
cow | +0.124 |
Neg logit contributions | |
�醒 | -0.212 |
ult | -0.192 |
olit | -0.192 |
sted | -0.190 |
adr | -0.182 |
Token | : |
Token ID | 25 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
DX | +0.414 |
DX | +0.400 |
resolves | +0.398 |
Fathers | +0.398 |
cow | +0.388 |
Neg logit contributions | |
�醒 | -0.663 |
olit | -0.603 |
ult | -0.595 |
sted | -0.593 |
adr | -0.569 |
Token | * |
Token ID | 9 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
DX | +0.101 |
DX | +0.096 |
resolves | +0.096 |
Fathers | +0.095 |
cow | +0.094 |
Neg logit contributions | |
�醒 | -0.115 |
olit | -0.103 |
ult | -0.101 |
sted | -0.101 |
adr | -0.096 |
Token | & |
Token ID | 5 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
DX | +0.164 |
DX | +0.158 |
resolves | +0.158 |
Fathers | +0.157 |
cow | +0.154 |
Neg logit contributions | |
�醒 | -0.239 |
olit | -0.217 |
ult | -0.215 |
sted | -0.214 |
adr | -0.205 |
Token | ). |
Token ID | 737 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
�醒 | +0.785 |
olit | +0.716 |
ult | +0.715 |
sted | +0.710 |
adr | +0.685 |
Neg logit contributions | |
DX | -0.387 |
Fathers | -0.378 |
resolves | -0.378 |
DX | -0.377 |
cow | -0.369 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
DX | +0.272 |
Fathers | +0.269 |
DX | +0.268 |
resolves | +0.262 |
cow | +0.257 |
Neg logit contributions | |
�醒 | -0.333 |
olit | -0.297 |
ult | -0.293 |
sted | -0.291 |
adr | -0.278 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
�醒 | +0.449 |
olit | +0.400 |
ult | +0.399 |
sted | +0.396 |
adr | +0.378 |
Neg logit contributions | |
DX | -0.399 |
Fathers | -0.392 |
resolves | -0.390 |
DX | -0.388 |
cow | -0.382 |
Token | This |
Token ID | 1212 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
�醒 | +0.142 |
olit | +0.125 |
sted | +0.123 |
ult | +0.122 |
adr | +0.117 |
Neg logit contributions | |
DX | -0.120 |
DX | -0.113 |
Fathers | -0.113 |
resolves | -0.112 |
cow | -0.109 |
Token | b |
Token ID | 275 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
�醒 | +0.106 |
olit | +0.095 |
ult | +0.094 |
sted | +0.093 |
adr | +0.089 |
Neg logit contributions | |
DX | -0.081 |
resolves | -0.081 |
DX | -0.080 |
Fathers | -0.080 |
cow | -0.078 |
Token | odes |
Token ID | 4147 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
�醒 | +0.338 |
olit | +0.281 |
sted | +0.279 |
ult | +0.275 |
adr | +0.259 |
Neg logit contributions | |
DX | -0.464 |
resolves | -0.460 |
Fathers | -0.457 |
DX | -0.453 |
cow | -0.447 |
Token | well |
Token ID | 880 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
�醒 | +2.434 |
ult | +2.209 |
olit | +2.208 |
sted | +2.197 |
adr | +2.113 |
Neg logit contributions | |
DX | -1.502 |
Fathers | -1.468 |
resolves | -1.462 |
DX | -1.454 |
cow | -1.431 |
Token | for |
Token ID | 329 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
�醒 | +0.592 |
ult | +0.538 |
olit | +0.537 |
sted | +0.536 |
adr | +0.519 |
Neg logit contributions | |
DX | -0.248 |
resolves | -0.244 |
DX | -0.242 |
Fathers | -0.241 |
cow | -0.236 |
Token | pulse |
Token ID | 19445 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
�醒 | +0.268 |
olit | +0.243 |
ult | +0.240 |
sted | +0.240 |
adr | +0.231 |
Neg logit contributions | |
DX | -0.157 |
DX | -0.155 |
resolves | -0.154 |
Fathers | -0.153 |
cow | -0.151 |
Token | j |
Token ID | 73 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
�醒 | +0.147 |
olit | +0.131 |
ult | +0.130 |
sted | +0.129 |
adr | +0.125 |
Neg logit contributions | |
DX | -0.099 |
DX | -0.097 |
resolves | -0.097 |
cow | -0.096 |
Fathers | -0.096 |
Token | ets |
Token ID | 1039 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
DX | +0.364 |
Fathers | +0.355 |
resolves | +0.354 |
DX | +0.354 |
cow | +0.348 |
Neg logit contributions | |
�醒 | -0.473 |
olit | -0.416 |
sted | -0.415 |
ult | -0.414 |
adr | -0.397 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
�醒 | +0.462 |
olit | +0.412 |
ult | +0.411 |
sted | +0.408 |
adr | +0.389 |
Neg logit contributions | |
DX | -0.415 |
Fathers | -0.408 |
resolves | -0.406 |
DX | -0.404 |
cow | -0.398 |
Token | These |
Token ID | 4711 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
�醒 | +0.118 |
olit | +0.105 |
sted | +0.104 |
ult | +0.103 |
adr | +0.099 |
Neg logit contributions | |
DX | -0.097 |
Fathers | -0.092 |
DX | -0.092 |
resolves | -0.091 |
cow | -0.090 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
�醒 | +0.839 |
olit | +0.751 |
ult | +0.746 |
sted | +0.746 |
adr | +0.720 |
Neg logit contributions | |
DX | -0.513 |
Fathers | -0.508 |
DX | -0.503 |
resolves | -0.501 |
cow | -0.497 |
Token | p |
Token ID | 279 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
�醒 | +0.220 |
olit | +0.197 |
ult | +0.196 |
sted | +0.195 |
adr | +0.189 |
Neg logit contributions | |
Fathers | -0.136 |
DX | -0.135 |
DX | -0.134 |
cow | -0.134 |
resolves | -0.133 |
Token | oth |
Token ID | 849 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
�醒 | +0.078 |
sted | +0.068 |
ult | +0.068 |
olit | +0.068 |
adr | +0.066 |
Neg logit contributions | |
DX | -0.054 |
Fathers | -0.054 |
resolves | -0.053 |
DX | -0.052 |
cow | -0.052 |
Token | oles |
Token ID | 4316 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
DX | +0.071 |
Fathers | +0.070 |
resolves | +0.069 |
DX | +0.068 |
cow | +0.066 |
Neg logit contributions | |
�醒 | -0.216 |
sted | -0.196 |
ult | -0.196 |
olit | -0.193 |
adr | -0.190 |
Token | tweet |
Token ID | 6126 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
�醒 | +2.190 |
olit | +1.966 |
ult | +1.965 |
sted | +1.953 |
adr | +1.875 |
Neg logit contributions | |
DX | -1.609 |
Fathers | -1.583 |
resolves | -1.580 |
DX | -1.570 |
cow | -1.550 |
Token | complaints |
Token ID | 9687 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
�醒 | +0.278 |
olit | +0.252 |
ult | +0.250 |
sted | +0.249 |
adr | +0.242 |
Neg logit contributions | |
DX | -0.169 |
Fathers | -0.168 |
resolves | -0.168 |
DX | -0.167 |
cow | -0.166 |
Token | straight |
Token ID | 3892 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
�醒 | +0.268 |
olit | +0.243 |
ult | +0.241 |
sted | +0.240 |
adr | +0.233 |
Neg logit contributions | |
DX | -0.148 |
Fathers | -0.146 |
resolves | -0.146 |
DX | -0.145 |
cow | -0.143 |
Token | to |
Token ID | 284 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
�醒 | +0.429 |
olit | +0.393 |
ult | +0.391 |
sted | +0.390 |
adr | +0.378 |
Neg logit contributions | |
DX | -0.200 |
resolves | -0.196 |
Fathers | -0.195 |
DX | -0.194 |
cow | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
Fathers | +0.146 |
DX | +0.146 |
cow | +0.145 |
DX | +0.145 |
resolves | +0.145 |
Neg logit contributions | |
�醒 | -0.208 |
olit | -0.185 |
ult | -0.184 |
sted | -0.180 |
adr | -0.176 |
Token | one |
Token ID | 530 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
DX | +0.040 |
Fathers | +0.040 |
DX | +0.039 |
resolves | +0.039 |
cow | +0.039 |
Neg logit contributions | |
�醒 | -0.066 |
olit | -0.059 |
ult | -0.059 |
sted | -0.059 |
adr | -0.057 |
Token | could |
Token ID | 714 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
�醒 | +0.194 |
ult | +0.171 |
olit | +0.171 |
sted | +0.170 |
adr | +0.162 |
Neg logit contributions | |
DX | -0.173 |
resolves | -0.172 |
Fathers | -0.172 |
DX | -0.170 |
cow | -0.168 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
DX | +0.085 |
resolves | +0.085 |
Fathers | +0.084 |
cow | +0.084 |
DX | +0.083 |
Neg logit contributions | |
�醒 | -0.114 |
sted | -0.101 |
ult | -0.101 |
olit | -0.101 |
adr | -0.097 |
Token | a |
Token ID | 257 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
Fathers | +0.286 |
DX | +0.285 |
resolves | +0.282 |
DX | +0.282 |
cow | +0.280 |
Neg logit contributions | |
�醒 | -0.505 |
ult | -0.453 |
olit | -0.452 |
sted | -0.449 |
adr | -0.437 |
Token | bit |
Token ID | 1643 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
DX | +0.011 |
cow | +0.010 |
Fathers | +0.010 |
DX | +0.010 |
resolves | +0.010 |
Neg logit contributions | |
�醒 | -0.015 |
ult | -0.013 |
olit | -0.013 |
sted | -0.013 |
adr | -0.013 |
Token | over |
Token ID | 625 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
�醒 | +0.460 |
ult | +0.413 |
olit | +0.412 |
sted | +0.411 |
adr | +0.397 |
Neg logit contributions | |
DX | -0.270 |
Fathers | -0.266 |
resolves | -0.265 |
DX | -0.265 |
cow | -0.261 |
Token | which |
Token ID | 543 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
�醒 | +2.181 |
ult | +1.989 |
olit | +1.986 |
sted | +1.974 |
adr | +1.894 |
Neg logit contributions | |
DX | -1.511 |
Fathers | -1.472 |
resolves | -1.468 |
DX | -1.456 |
cow | -1.432 |
Token | form |
Token ID | 1296 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
�醒 | +0.245 |
olit | +0.219 |
ult | +0.219 |
sted | +0.218 |
adr | +0.208 |
Neg logit contributions | |
DX | -0.174 |
Fathers | -0.173 |
resolves | -0.173 |
DX | -0.172 |
cow | -0.171 |
Token | of |
Token ID | 286 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Fathers | +0.568 |
DX | +0.561 |
resolves | +0.560 |
DX | +0.559 |
cow | +0.551 |
Neg logit contributions | |
�醒 | -1.106 |
sted | -0.986 |
olit | -0.980 |
ult | -0.972 |
adr | -0.944 |
Token | lying |
Token ID | 9105 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Fathers | +0.130 |
DX | +0.130 |
cow | +0.130 |
DX | +0.130 |
resolves | +0.129 |
Neg logit contributions | |
�醒 | -0.192 |
olit | -0.171 |
ult | -0.170 |
sted | -0.169 |
adr | -0.162 |
Token | is |
Token ID | 318 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
�醒 | +0.240 |
olit | +0.210 |
ult | +0.210 |
sted | +0.209 |
adr | +0.200 |
Neg logit contributions | |
DX | -0.204 |
Fathers | -0.203 |
resolves | -0.202 |
DX | -0.201 |
cow | -0.199 |
Token | to |
Token ID | 284 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
�醒 | +1.011 |
ult | +0.918 |
olit | +0.917 |
sted | +0.911 |
adr | +0.886 |
Neg logit contributions | |
DX | -0.490 |
Fathers | -0.485 |
resolves | -0.482 |
DX | -0.476 |
cow | -0.471 |
Token | remember |
Token ID | 3505 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
�醒 | +0.345 |
olit | +0.302 |
ult | +0.302 |
sted | +0.301 |
adr | +0.288 |
Neg logit contributions | |
DX | -0.286 |
resolves | -0.284 |
Fathers | -0.284 |
cow | -0.282 |
DX | -0.281 |
Token | with |
Token ID | 351 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
�醒 | +0.491 |
olit | +0.445 |
ult | +0.444 |
sted | +0.440 |
adr | +0.426 |
Neg logit contributions | |
DX | -0.283 |
Fathers | -0.279 |
resolves | -0.278 |
DX | -0.276 |
cow | -0.272 |
Token | an |
Token ID | 281 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
�醒 | +0.306 |
olit | +0.273 |
ult | +0.270 |
sted | +0.269 |
adr | +0.260 |
Neg logit contributions | |
DX | -0.218 |
Fathers | -0.217 |
resolves | -0.217 |
DX | -0.215 |
cow | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
�醒 | +0.528 |
sted | +0.473 |
olit | +0.471 |
ult | +0.469 |
adr | +0.451 |
Neg logit contributions | |
DX | -0.347 |
resolves | -0.343 |
Fathers | -0.337 |
DX | -0.337 |
cow | -0.333 |
Token | ching |
Token ID | 10813 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
DX | +0.228 |
cow | +0.224 |
resolves | +0.224 |
Fathers | +0.222 |
DX | +0.221 |
Neg logit contributions | |
�醒 | -0.263 |
olit | -0.231 |
sted | -0.229 |
ult | -0.228 |
adr | -0.217 |
Token | need |
Token ID | 761 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
�醒 | +2.099 |
ult | +1.897 |
olit | +1.894 |
sted | +1.882 |
adr | +1.806 |
Neg logit contributions | |
DX | -1.477 |
resolves | -1.449 |
Fathers | -1.448 |
DX | -1.438 |
cow | -1.425 |
Token | that |
Token ID | 326 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
�醒 | +0.536 |
ult | +0.491 |
olit | +0.490 |
sted | +0.488 |
adr | +0.476 |
Neg logit contributions | |
Fathers | -0.240 |
DX | -0.240 |
resolves | -0.240 |
DX | -0.236 |
cow | -0.234 |
Token | has |
Token ID | 468 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
�醒 | +0.566 |
olit | +0.508 |
sted | +0.502 |
ult | +0.501 |
adr | +0.484 |
Neg logit contributions | |
resolves | -0.391 |
DX | -0.385 |
Fathers | -0.385 |
cow | -0.380 |
DX | -0.380 |
Token | her |
Token ID | 607 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
�醒 | +0.473 |
olit | +0.423 |
ult | +0.422 |
sted | +0.418 |
adr | +0.403 |
Neg logit contributions | |
DX | -0.325 |
resolves | -0.324 |
Fathers | -0.322 |
DX | -0.320 |
cow | -0.319 |
Token | sob |
Token ID | 27355 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Fathers | +0.132 |
resolves | +0.132 |
DX | +0.131 |
cow | +0.131 |
DX | +0.130 |
Neg logit contributions | |
�醒 | -0.206 |
ult | -0.183 |
olit | -0.182 |
sted | -0.181 |
adr | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
DX | +0.016 |
resolves | +0.016 |
DX | +0.016 |
Fathers | +0.016 |
cow | +0.015 |
Neg logit contributions | |
�醒 | -0.032 |
olit | -0.028 |
ult | -0.028 |
sted | -0.028 |
adr | -0.027 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
DX | +0.128 |
DX | +0.125 |
Fathers | +0.123 |
resolves | +0.122 |
cow | +0.119 |
Neg logit contributions | |
�醒 | -0.168 |
olit | -0.149 |
sted | -0.148 |
ult | -0.147 |
adr | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
�醒 | +0.012 |
olit | +0.011 |
ult | +0.011 |
sted | +0.011 |
adr | +0.010 |
Neg logit contributions | |
DX | -0.005 |
Fathers | -0.005 |
DX | -0.005 |
resolves | -0.005 |
cow | -0.005 |
Token | [ |
Token ID | 685 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
�醒 | +0.416 |
olit | +0.380 |
sted | +0.378 |
ult | +0.376 |
adr | +0.363 |
Neg logit contributions | |
DX | -0.207 |
DX | -0.203 |
Fathers | -0.200 |
resolves | -0.198 |
cow | -0.195 |
Token | color |
Token ID | 8043 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
�醒 | +1.387 |
olit | +1.237 |
ult | +1.233 |
sted | +1.227 |
adr | +1.173 |
Neg logit contributions | |
DX | -1.151 |
resolves | -1.116 |
Fathers | -1.114 |
DX | -1.112 |
cow | -1.095 |
Token | = |
Token ID | 28 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
�醒 | +0.959 |
olit | +0.841 |
ult | +0.838 |
sted | +0.833 |
adr | +0.790 |
Neg logit contributions | |
DX | -1.003 |
Fathers | -0.980 |
resolves | -0.979 |
DX | -0.976 |
cow | -0.962 |
Token | red |
Token ID | 445 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
�醒 | +1.755 |
olit | +1.547 |
ult | +1.537 |
sted | +1.530 |
adr | +1.454 |
Neg logit contributions | |
DX | -1.817 |
Fathers | -1.774 |
resolves | -1.772 |
DX | -1.763 |
cow | -1.745 |
Token | ][ |
Token ID | 7131 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
�醒 | +0.405 |
olit | +0.372 |
ult | +0.372 |
sted | +0.371 |
adr | +0.358 |
Neg logit contributions | |
DX | -0.160 |
Fathers | -0.154 |
resolves | -0.153 |
DX | -0.153 |
cow | -0.150 |
Token | b |
Token ID | 65 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
DX | +0.018 |
Fathers | +0.018 |
resolves | +0.018 |
DX | +0.018 |
cow | +0.017 |
Neg logit contributions | |
�醒 | -0.016 |
olit | -0.014 |
ult | -0.014 |
sted | -0.014 |
adr | -0.013 |
Token | ] |
Token ID | 60 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
DX | +0.124 |
Fathers | +0.119 |
DX | +0.119 |
resolves | +0.118 |
cow | +0.115 |
Neg logit contributions | |
�醒 | -0.280 |
olit | -0.253 |
ult | -0.252 |
sted | -0.251 |
adr | -0.241 |
Token | U |
Token ID | 52 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
�醒 | +0.246 |
olit | +0.220 |
sted | +0.218 |
ult | +0.215 |
adr | +0.208 |
Neg logit contributions | |
DX | -0.197 |
Fathers | -0.187 |
DX | -0.187 |
resolves | -0.185 |
cow | -0.182 |
Token | cohort |
Token ID | 20812 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
�醒 | +0.127 |
olit | +0.114 |
ult | +0.113 |
sted | +0.112 |
adr | +0.108 |
Neg logit contributions | |
DX | -0.082 |
DX | -0.082 |
resolves | -0.081 |
Fathers | -0.081 |
cow | -0.080 |
Token | of |
Token ID | 286 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
�醒 | +0.263 |
olit | +0.232 |
sted | +0.232 |
ult | +0.232 |
adr | +0.226 |
Neg logit contributions | |
resolves | -0.142 |
DX | -0.142 |
DX | -0.140 |
Fathers | -0.139 |
cow | -0.137 |
Token | patients |
Token ID | 3871 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
�醒 | +0.087 |
olit | +0.077 |
ult | +0.077 |
sted | +0.076 |
adr | +0.074 |
Neg logit contributions | |
DX | -0.057 |
DX | -0.057 |
Fathers | -0.057 |
resolves | -0.056 |
cow | -0.055 |
Token | ( |
Token ID | 357 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
�醒 | +0.268 |
olit | +0.238 |
ult | +0.237 |
sted | +0.237 |
adr | +0.229 |
Neg logit contributions | |
resolves | -0.164 |
DX | -0.163 |
Fathers | -0.162 |
DX | -0.161 |
cow | -0.158 |
Token | n |
Token ID | 77 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
�醒 | +0.570 |
olit | +0.489 |
sted | +0.484 |
ult | +0.480 |
adr | +0.461 |
Neg logit contributions | |
DX | -0.564 |
Fathers | -0.541 |
resolves | -0.537 |
DX | -0.537 |
cow | -0.528 |
Token | = |
Token ID | 28 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
�醒 | +0.337 |
olit | +0.296 |
sted | +0.295 |
ult | +0.294 |
adr | +0.285 |
Neg logit contributions | |
DX | -0.225 |
Fathers | -0.219 |
DX | -0.215 |
resolves | -0.214 |
cow | -0.213 |
Token | 91 |
Token ID | 6420 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
�醒 | +1.861 |
olit | +1.642 |
ult | +1.629 |
sted | +1.619 |
adr | +1.548 |
Neg logit contributions | |
DX | -1.670 |
Fathers | -1.628 |
resolves | -1.616 |
DX | -1.611 |
cow | -1.588 |
Token | ) |
Token ID | 8 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
�醒 | +0.586 |
ult | +0.532 |
olit | +0.531 |
sted | +0.529 |
adr | +0.512 |
Neg logit contributions | |
DX | -0.283 |
Fathers | -0.276 |
resolves | -0.273 |
DX | -0.272 |
cow | -0.266 |
Token | only |
Token ID | 691 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
�醒 | +0.564 |
olit | +0.500 |
ult | +0.499 |
sted | +0.498 |
adr | +0.481 |
Neg logit contributions | |
resolves | -0.370 |
DX | -0.370 |
Fathers | -0.368 |
DX | -0.365 |
cow | -0.359 |
Token | received |
Token ID | 2722 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
resolves | +0.058 |
Fathers | +0.058 |
DX | +0.058 |
DX | +0.057 |
cow | +0.056 |
Neg logit contributions | |
�醒 | -0.108 |
olit | -0.095 |
ult | -0.095 |
sted | -0.094 |
adr | -0.092 |
Token | trans |
Token ID | 1007 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
DX | +0.124 |
DX | +0.123 |
Fathers | +0.122 |
resolves | +0.122 |
cow | +0.121 |
Neg logit contributions | |
�醒 | -0.177 |
olit | -0.159 |
ult | -0.159 |
sted | -0.158 |
adr | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
�醒 | +0.133 |
olit | +0.117 |
ult | +0.116 |
sted | +0.115 |
adr | +0.110 |
Neg logit contributions | |
DX | -0.110 |
Fathers | -0.108 |
DX | -0.107 |
resolves | -0.107 |
cow | -0.105 |
Token | A |
Token ID | 32 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
DX | +0.056 |
Fathers | +0.053 |
DX | +0.053 |
resolves | +0.052 |
cow | +0.052 |
Neg logit contributions | |
�醒 | -0.064 |
olit | -0.056 |
sted | -0.055 |
ult | -0.055 |
adr | -0.053 |
Token | lot |
Token ID | 1256 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
�醒 | +0.061 |
olit | +0.055 |
ult | +0.054 |
sted | +0.054 |
adr | +0.052 |
Neg logit contributions | |
DX | -0.043 |
Fathers | -0.042 |
DX | -0.042 |
cow | -0.042 |
resolves | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
�醒 | +0.193 |
ult | +0.176 |
olit | +0.176 |
sted | +0.174 |
adr | +0.169 |
Neg logit contributions | |
DX | -0.107 |
Fathers | -0.106 |
resolves | -0.105 |
DX | -0.104 |
cow | -0.103 |
Token | public |
Token ID | 1171 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Fathers | +0.325 |
DX | +0.324 |
DX | +0.318 |
cow | +0.316 |
resolves | +0.315 |
Neg logit contributions | |
�醒 | -0.615 |
olit | -0.553 |
ult | -0.543 |
sted | -0.539 |
adr | -0.528 |
Token | domain |
Token ID | 7386 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
�醒 | +0.357 |
olit | +0.317 |
ult | +0.311 |
sted | +0.309 |
adr | +0.305 |
Neg logit contributions | |
DX | -0.215 |
Fathers | -0.215 |
DX | -0.210 |
resolves | -0.209 |
cow | -0.208 |
Token | works |
Token ID | 2499 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
�醒 | +2.325 |
olit | +2.126 |
ult | +2.119 |
sted | +2.111 |
adr | +2.041 |
Neg logit contributions | |
DX | -1.150 |
Fathers | -1.128 |
resolves | -1.118 |
DX | -1.113 |
cow | -1.096 |
Token | are |
Token ID | 389 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
�醒 | +0.658 |
olit | +0.584 |
sted | +0.581 |
ult | +0.580 |
adr | +0.560 |
Neg logit contributions | |
DX | -0.504 |
Fathers | -0.497 |
resolves | -0.493 |
DX | -0.491 |
cow | -0.488 |
Token | also |
Token ID | 635 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
DX | +0.149 |
Fathers | +0.147 |
DX | +0.147 |
cow | +0.147 |
resolves | +0.145 |
Neg logit contributions | |
�醒 | -0.242 |
ult | -0.217 |
olit | -0.217 |
sted | -0.217 |
adr | -0.207 |
Token | available |
Token ID | 1695 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
DX | +0.201 |
Fathers | +0.198 |
DX | +0.198 |
cow | +0.197 |
resolves | +0.195 |
Neg logit contributions | |
�醒 | -0.312 |
ult | -0.280 |
olit | -0.279 |
sted | -0.278 |
adr | -0.265 |
Token | on |
Token ID | 319 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
DX | +0.137 |
DX | +0.135 |
Fathers | +0.134 |
resolves | +0.133 |
cow | +0.132 |
Neg logit contributions | |
�醒 | -0.264 |
ult | -0.238 |
olit | -0.238 |
sted | -0.237 |
adr | -0.229 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
�醒 | +0.471 |
olit | +0.414 |
ult | +0.410 |
sted | +0.406 |
adr | +0.389 |
Neg logit contributions | |
DX | -0.462 |
Fathers | -0.457 |
DX | -0.455 |
resolves | -0.455 |
cow | -0.452 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
DX | +0.095 |
Fathers | +0.093 |
DX | +0.092 |
resolves | +0.092 |
cow | +0.091 |
Neg logit contributions | |
�醒 | -0.206 |
olit | -0.190 |
ult | -0.189 |
sted | -0.188 |
adr | -0.182 |
Token | California |
Token ID | 3442 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
DX | +0.253 |
resolves | +0.251 |
Fathers | +0.250 |
DX | +0.248 |
cow | +0.248 |
Neg logit contributions | |
�醒 | -0.352 |
olit | -0.312 |
ult | -0.305 |
sted | -0.304 |
adr | -0.298 |
Token | . |
Token ID | 13 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
�醒 | +0.146 |
ult | +0.134 |
olit | +0.134 |
sted | +0.133 |
adr | +0.128 |
Neg logit contributions | |
DX | -0.072 |
Fathers | -0.070 |
resolves | -0.069 |
DX | -0.069 |
cow | -0.067 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Fathers | +0.055 |
DX | +0.055 |
DX | +0.055 |
resolves | +0.053 |
cow | +0.052 |
Neg logit contributions | |
�醒 | -0.083 |
ult | -0.074 |
sted | -0.074 |
olit | -0.074 |
adr | -0.071 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
�醒 | +0.792 |
ult | +0.725 |
olit | +0.721 |
sted | +0.721 |
adr | +0.688 |
Neg logit contributions | |
DX | -0.624 |
resolves | -0.609 |
Fathers | -0.607 |
DX | -0.601 |
cow | -0.596 |
Token | 9 |
Token ID | 860 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
�醒 | +1.846 |
olit | +1.704 |
sted | +1.692 |
ult | +1.686 |
adr | +1.617 |
Neg logit contributions | |
DX | -1.520 |
resolves | -1.478 |
Fathers | -1.461 |
cow | -1.449 |
advancements | -1.440 |
Token | of |
Token ID | 286 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
DX | +0.248 |
Fathers | +0.242 |
resolves | +0.240 |
DX | +0.240 |
cow | +0.235 |
Neg logit contributions | |
�醒 | -0.478 |
olit | -0.433 |
ult | -0.431 |
sted | -0.429 |
adr | -0.415 |
Token | 15 |
Token ID | 1315 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
�醒 | +0.342 |
ult | +0.308 |
olit | +0.308 |
sted | +0.307 |
adr | +0.291 |
Neg logit contributions | |
DX | -0.311 |
Fathers | -0.305 |
resolves | -0.304 |
DX | -0.302 |
cow | -0.299 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
�醒 | +0.490 |
olit | +0.438 |
ult | +0.438 |
sted | +0.436 |
adr | +0.410 |
Neg logit contributions | |
DX | -0.602 |
resolves | -0.590 |
Fathers | -0.589 |
DX | -0.583 |
cow | -0.580 |
Token | : |
Token ID | 25 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
�醒 | +1.219 |
ult | +1.131 |
sted | +1.122 |
olit | +1.121 |
adr | +1.070 |
Neg logit contributions | |
DX | -0.881 |
resolves | -0.861 |
Fathers | -0.860 |
DX | -0.849 |
cow | -0.841 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
DX | +0.281 |
DX | +0.279 |
Fathers | +0.279 |
resolves | +0.275 |
cow | +0.274 |
Neg logit contributions | |
�醒 | -0.343 |
olit | -0.302 |
ult | -0.301 |
sted | -0.297 |
adr | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
DX | +0.314 |
Fathers | +0.304 |
DX | +0.303 |
resolves | +0.301 |
cow | +0.295 |
Neg logit contributions | |
�醒 | -0.638 |
olit | -0.586 |
ult | -0.585 |
sted | -0.581 |
adr | -0.563 |
Token | California |
Token ID | 3442 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
DX | +0.240 |
resolves | +0.235 |
DX | +0.235 |
Fathers | +0.235 |
cow | +0.234 |
Neg logit contributions | |
�醒 | -0.319 |
olit | -0.286 |
ult | -0.282 |
sted | -0.280 |
adr | -0.274 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
DX | +0.136 |
Fathers | +0.133 |
resolves | +0.132 |
DX | +0.131 |
cow | +0.128 |
Neg logit contributions | |
�醒 | -0.288 |
ult | -0.264 |
olit | -0.264 |
sted | -0.263 |
adr | -0.254 |
Token | Hide |
Token ID | 10415 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
Fathers | +0.019 |
DX | +0.019 |
DX | +0.019 |
resolves | +0.018 |
cow | +0.018 |
Neg logit contributions | |
�醒 | -0.040 |
ult | -0.036 |
olit | -0.036 |
sted | -0.036 |
adr | -0.035 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
�醒 | +0.683 |
ult | +0.626 |
olit | +0.622 |
sted | +0.622 |
adr | +0.594 |
Neg logit contributions | |
DX | -0.542 |
resolves | -0.528 |
Fathers | -0.527 |
DX | -0.521 |
cow | -0.518 |
Token | 12 |
Token ID | 1105 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
�醒 | +1.587 |
ult | +1.498 |
olit | +1.470 |
sted | +1.462 |
adr | +1.410 |
Neg logit contributions | |
DX | -1.596 |
Fathers | -1.562 |
resolves | -1.553 |
cow | -1.543 |
advancements | -1.538 |
Token | of |
Token ID | 286 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
DX | +0.090 |
Fathers | +0.088 |
resolves | +0.088 |
DX | +0.087 |
cow | +0.086 |
Neg logit contributions | |
�醒 | -0.170 |
olit | -0.155 |
ult | -0.154 |
sted | -0.153 |
adr | -0.148 |
Token | 15 |
Token ID | 1315 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
�醒 | +0.021 |
ult | +0.019 |
olit | +0.019 |
sted | +0.019 |
adr | +0.018 |
Neg logit contributions | |
DX | -0.019 |
Fathers | -0.018 |
resolves | -0.018 |
DX | -0.018 |
cow | -0.018 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
�醒 | +0.417 |
olit | +0.372 |
ult | +0.372 |
sted | +0.370 |
adr | +0.348 |
Neg logit contributions | |
DX | -0.507 |
resolves | -0.497 |
Fathers | -0.497 |
DX | -0.492 |
cow | -0.490 |
Token | : |
Token ID | 25 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
�醒 | +1.215 |
ult | +1.128 |
sted | +1.119 |
olit | +1.118 |
adr | +1.068 |
Neg logit contributions | |
DX | -0.881 |
resolves | -0.862 |
Fathers | -0.860 |
DX | -0.849 |
cow | -0.842 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
DX | +0.213 |
Fathers | +0.209 |
resolves | +0.208 |
DX | +0.207 |
cow | +0.204 |
Neg logit contributions | |
�醒 | -0.259 |
ult | -0.233 |
olit | -0.233 |
sted | -0.231 |
adr | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
DX | +0.012 |
Fathers | +0.012 |
resolves | +0.012 |
DX | +0.012 |
cow | +0.012 |
Neg logit contributions | |
�醒 | -0.024 |
ult | -0.022 |
olit | -0.022 |
sted | -0.022 |
adr | -0.021 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
DX | +0.144 |
Fathers | +0.143 |
DX | +0.142 |
resolves | +0.141 |
cow | +0.140 |
Neg logit contributions | |
�醒 | -0.220 |
olit | -0.196 |
ult | -0.194 |
sted | -0.193 |
adr | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
�醒 | +0.374 |
ult | +0.344 |
olit | +0.343 |
sted | +0.341 |
adr | +0.329 |
Neg logit contributions | |
DX | -0.188 |
Fathers | -0.183 |
resolves | -0.182 |
DX | -0.180 |
cow | -0.177 |
Token | Hide |
Token ID | 10415 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
Fathers | +0.103 |
DX | +0.101 |
DX | +0.101 |
resolves | +0.098 |
cow | +0.096 |
Neg logit contributions | |
�醒 | -0.215 |
ult | -0.195 |
olit | -0.195 |
sted | -0.195 |
adr | -0.188 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
�醒 | +0.657 |
ult | +0.601 |
olit | +0.598 |
sted | +0.597 |
adr | +0.570 |
Neg logit contributions | |
DX | -0.518 |
resolves | -0.505 |
Fathers | -0.504 |
DX | -0.498 |
cow | -0.494 |
Token | 8 |
Token ID | 807 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
�醒 | +1.680 |
ult | +1.571 |
olit | +1.554 |
sted | +1.551 |
adr | +1.495 |
Neg logit contributions | |
DX | -1.509 |
Fathers | -1.490 |
resolves | -1.467 |
advancements | -1.452 |
cow | -1.451 |
Token | of |
Token ID | 286 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
�醒 | +0.037 |
olit | +0.033 |
ult | +0.033 |
sted | +0.033 |
adr | +0.032 |
Neg logit contributions | |
DX | -0.020 |
Fathers | -0.019 |
resolves | -0.019 |
DX | -0.019 |
cow | -0.019 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
�醒 | +0.183 |
ult | +0.164 |
olit | +0.164 |
sted | +0.163 |
adr | +0.156 |
Neg logit contributions | |
DX | -0.163 |
Fathers | -0.160 |
resolves | -0.159 |
DX | -0.158 |
cow | -0.156 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
�醒 | +0.593 |
olit | +0.534 |
ult | +0.533 |
sted | +0.532 |
adr | +0.499 |
Neg logit contributions | |
DX | -0.742 |
resolves | -0.728 |
Fathers | -0.726 |
DX | -0.719 |
cow | -0.716 |
Token | : |
Token ID | 25 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
�醒 | +1.205 |
ult | +1.117 |
sted | +1.108 |
olit | +1.108 |
adr | +1.057 |
Neg logit contributions | |
DX | -0.870 |
resolves | -0.851 |
Fathers | -0.850 |
DX | -0.839 |
cow | -0.831 |
Token | : |
Token ID | 25 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Fathers | +0.125 |
DX | +0.124 |
DX | +0.122 |
resolves | +0.122 |
cow | +0.121 |
Neg logit contributions | |
�醒 | -0.182 |
ult | -0.165 |
olit | -0.164 |
sted | -0.163 |
adr | -0.158 |
Token | " |
Token ID | 366 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
�醒 | +0.539 |
ult | +0.487 |
olit | +0.485 |
sted | +0.483 |
adr | +0.461 |
Neg logit contributions | |
DX | -0.376 |
Fathers | -0.374 |
DX | -0.370 |
resolves | -0.364 |
cow | -0.364 |
Token | I |
Token ID | 40 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
�醒 | +0.326 |
olit | +0.290 |
sted | +0.287 |
ult | +0.286 |
adr | +0.275 |
Neg logit contributions | |
DX | -0.281 |
Fathers | -0.274 |
DX | -0.270 |
resolves | -0.268 |
cow | -0.266 |
Token | Can |
Token ID | 1680 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
�醒 | +0.304 |
olit | +0.264 |
ult | +0.262 |
sted | +0.260 |
adr | +0.253 |
Neg logit contributions | |
DX | -0.244 |
Fathers | -0.242 |
cow | -0.240 |
resolves | -0.240 |
DX | -0.239 |
Token | Think |
Token ID | 11382 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
�醒 | +0.390 |
ult | +0.347 |
sted | +0.346 |
olit | +0.345 |
adr | +0.333 |
Neg logit contributions | |
DX | -0.311 |
Fathers | -0.306 |
DX | -0.303 |
resolves | -0.301 |
cow | -0.299 |
Token | Of |
Token ID | 3226 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
�醒 | +0.868 |
ult | +0.782 |
olit | +0.778 |
sted | +0.773 |
adr | +0.747 |
Neg logit contributions | |
DX | -0.656 |
Fathers | -0.653 |
DX | -0.643 |
resolves | -0.641 |
cow | -0.632 |
Token | No |
Token ID | 1400 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
�醒 | +1.714 |
ult | +1.533 |
olit | +1.532 |
sted | +1.520 |
adr | +1.451 |
Neg logit contributions | |
DX | -1.538 |
Fathers | -1.512 |
resolves | -1.502 |
DX | -1.497 |
cow | -1.476 |
Token | Reason |
Token ID | 23219 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
�醒 | +0.595 |
ult | +0.534 |
olit | +0.531 |
sted | +0.528 |
adr | +0.509 |
Neg logit contributions | |
Fathers | -0.451 |
DX | -0.451 |
DX | -0.442 |
resolves | -0.438 |
cow | -0.435 |
Token | Why |
Token ID | 4162 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
�醒 | +0.322 |
ult | +0.290 |
olit | +0.287 |
sted | +0.287 |
adr | +0.277 |
Neg logit contributions | |
Fathers | -0.248 |
DX | -0.247 |
DX | -0.244 |
cow | -0.240 |
resolves | -0.240 |
Token | In |
Token ID | 554 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Fathers | +0.242 |
DX | +0.236 |
DX | +0.235 |
cow | +0.232 |
resolves | +0.231 |
Neg logit contributions | |
�醒 | -0.318 |
ult | -0.281 |
olit | -0.280 |
sted | -0.277 |
adr | -0.270 |
Token | A |
Token ID | 317 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
�醒 | +0.380 |
olit | +0.337 |
ult | +0.337 |
sted | +0.335 |
adr | +0.324 |
Neg logit contributions | |
Fathers | -0.285 |
DX | -0.285 |
DX | -0.281 |
resolves | -0.276 |
cow | -0.276 |
Token | Are |
Token ID | 4231 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
�醒 | +0.218 |
olit | +0.193 |
sted | +0.191 |
ult | +0.190 |
adr | +0.182 |
Neg logit contributions | |
DX | -0.169 |
Fathers | -0.168 |
DX | -0.167 |
resolves | -0.166 |
cow | -0.163 |
Token | there |
Token ID | 612 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
�醒 | +0.377 |
olit | +0.340 |
ult | +0.337 |
sted | +0.335 |
adr | +0.325 |
Neg logit contributions | |
DX | -0.240 |
Fathers | -0.237 |
DX | -0.235 |
cow | -0.235 |
resolves | -0.235 |
Token | more |
Token ID | 517 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
�醒 | +0.394 |
olit | +0.356 |
ult | +0.355 |
sted | +0.353 |
adr | +0.342 |
Neg logit contributions | |
DX | -0.219 |
Fathers | -0.216 |
resolves | -0.214 |
cow | -0.214 |
DX | -0.213 |
Token | p |
Token ID | 279 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
Fathers | +0.151 |
DX | +0.150 |
cow | +0.150 |
resolves | +0.149 |
DX | +0.148 |
Neg logit contributions | |
�醒 | -0.275 |
olit | -0.248 |
ult | -0.246 |
sted | -0.244 |
adr | -0.238 |
Token | oth |
Token ID | 849 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
�醒 | +0.033 |
olit | +0.029 |
sted | +0.029 |
ult | +0.029 |
adr | +0.028 |
Neg logit contributions | |
DX | -0.023 |
Fathers | -0.023 |
resolves | -0.022 |
DX | -0.022 |
cow | -0.022 |
Token | oles |
Token ID | 4316 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
�醒 | +0.659 |
ult | +0.602 |
sted | +0.600 |
olit | +0.599 |
adr | +0.581 |
Neg logit contributions | |
DX | -0.244 |
Fathers | -0.239 |
resolves | -0.236 |
DX | -0.233 |
cow | -0.228 |
Token | in |
Token ID | 287 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
�醒 | +2.123 |
olit | +1.928 |
ult | +1.925 |
sted | +1.907 |
adr | +1.854 |
Neg logit contributions | |
DX | -1.137 |
resolves | -1.112 |
Fathers | -1.112 |
DX | -1.103 |
cow | -1.092 |
Token | New |
Token ID | 968 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
�醒 | +0.153 |
olit | +0.137 |
ult | +0.137 |
sted | +0.135 |
adr | +0.131 |
Neg logit contributions | |
DX | -0.101 |
Fathers | -0.100 |
DX | -0.100 |
resolves | -0.099 |
cow | -0.098 |
Token | Jersey |
Token ID | 8221 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
�醒 | +0.866 |
ult | +0.782 |
olit | +0.781 |
sted | +0.772 |
adr | +0.747 |
Neg logit contributions | |
DX | -0.621 |
Fathers | -0.611 |
resolves | -0.607 |
DX | -0.605 |
cow | -0.597 |
Token | than |
Token ID | 621 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
�醒 | +0.361 |
olit | +0.325 |
ult | +0.323 |
sted | +0.318 |
adr | +0.313 |
Neg logit contributions | |
DX | -0.224 |
Fathers | -0.220 |
resolves | -0.220 |
DX | -0.219 |
cow | -0.218 |
Token | other |
Token ID | 584 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
�醒 | +0.047 |
olit | +0.043 |
ult | +0.042 |
sted | +0.042 |
adr | +0.041 |
Neg logit contributions | |
DX | -0.024 |
Fathers | -0.024 |
resolves | -0.024 |
cow | -0.024 |
DX | -0.024 |
Token | 25 |
Token ID | 1679 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
DX | +0.559 |
DX | +0.556 |
Fathers | +0.553 |
resolves | +0.553 |
changing | +0.546 |
Neg logit contributions | |
�醒 | -0.731 |
ult | -0.665 |
olit | -0.662 |
sted | -0.651 |
adr | -0.633 |
Token | 26 |
Token ID | 2608 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
resolves | +0.452 |
DX | +0.451 |
DX | +0.449 |
Fathers | +0.446 |
changing | +0.442 |
Neg logit contributions | |
�醒 | -0.638 |
ult | -0.578 |
olit | -0.572 |
sted | -0.569 |
adr | -0.547 |
Token | 27 |
Token ID | 2681 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
DX | +0.467 |
resolves | +0.462 |
DX | +0.461 |
Fathers | +0.460 |
cow | +0.453 |
Neg logit contributions | |
�醒 | -0.567 |
ult | -0.519 |
olit | -0.517 |
sted | -0.516 |
adr | -0.493 |
Token | # |
Token ID | 1303 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
DX | +0.319 |
resolves | +0.314 |
DX | +0.313 |
cow | +0.309 |
changing | +0.301 |
Neg logit contributions | |
�醒 | -0.472 |
olit | -0.432 |
sted | -0.427 |
ult | -0.417 |
adr | -0.400 |
Token | loop |
Token ID | 9052 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
�醒 | +1.347 |
olit | +1.221 |
sted | +1.216 |
ult | +1.215 |
adr | +1.164 |
Neg logit contributions | |
DX | -0.893 |
resolves | -0.872 |
Fathers | -0.871 |
DX | -0.865 |
cow | -0.850 |
Token | over |
Token ID | 625 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
�醒 | +1.149 |
olit | +1.045 |
ult | +1.040 |
sted | +1.031 |
adr | +1.001 |
Neg logit contributions | |
DX | -0.688 |
resolves | -0.675 |
DX | -0.672 |
Fathers | -0.671 |
cow | -0.660 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
�醒 | +1.978 |
ult | +1.802 |
olit | +1.799 |
sted | +1.791 |
adr | +1.722 |
Neg logit contributions | |
DX | -1.232 |
Fathers | -1.202 |
resolves | -1.196 |
DX | -1.188 |
cow | -1.168 |
Token | input |
Token ID | 5128 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
�醒 | +0.982 |
olit | +0.900 |
ult | +0.900 |
sted | +0.894 |
adr | +0.859 |
Neg logit contributions | |
DX | -0.531 |
Fathers | -0.519 |
resolves | -0.517 |
DX | -0.513 |
cow | -0.504 |
Token | image |
Token ID | 2939 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
�醒 | +0.373 |
olit | +0.339 |
ult | +0.338 |
sted | +0.337 |
adr | +0.322 |
Neg logit contributions | |
DX | -0.261 |
resolves | -0.255 |
Fathers | -0.254 |
DX | -0.254 |
cow | -0.250 |
Token | paths |
Token ID | 13532 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
�醒 | +1.615 |
ult | +1.471 |
olit | +1.469 |
sted | +1.460 |
adr | +1.403 |
Neg logit contributions | |
DX | -1.040 |
Fathers | -1.014 |
resolves | -1.008 |
DX | -1.004 |
cow | -0.987 |
Token | for |
Token ID | 329 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
�醒 | +1.210 |
olit | +1.114 |
ult | +1.112 |
sted | +1.106 |
adr | +1.066 |
Neg logit contributions | |
DX | -0.534 |
resolves | -0.521 |
Fathers | -0.520 |
DX | -0.517 |
cow | -0.506 |
Token | ? |
Token ID | 30 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
�醒 | +0.640 |
olit | +0.573 |
sted | +0.570 |
ult | +0.570 |
adr | +0.547 |
Neg logit contributions | |
DX | -0.451 |
DX | -0.439 |
Fathers | -0.437 |
resolves | -0.434 |
cow | -0.429 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
�醒 | +0.398 |
olit | +0.358 |
sted | +0.356 |
ult | +0.355 |
adr | +0.341 |
Neg logit contributions | |
DX | -0.269 |
DX | -0.261 |
Fathers | -0.259 |
resolves | -0.259 |
cow | -0.255 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
�醒 | +0.099 |
olit | +0.088 |
ult | +0.087 |
sted | +0.086 |
adr | +0.083 |
Neg logit contributions | |
DX | -0.084 |
Fathers | -0.082 |
DX | -0.081 |
resolves | -0.081 |
cow | -0.080 |
Token | Dark |
Token ID | 17367 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
�醒 | +0.116 |
olit | +0.101 |
sted | +0.100 |
ult | +0.098 |
adr | +0.095 |
Neg logit contributions | |
DX | -0.100 |
DX | -0.094 |
Fathers | -0.094 |
resolves | -0.093 |
cow | -0.093 |
Token | horse |
Token ID | 30527 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
�醒 | +0.772 |
olit | +0.679 |
sted | +0.674 |
ult | +0.672 |
adr | +0.643 |
Neg logit contributions | |
DX | -0.620 |
Fathers | -0.596 |
resolves | -0.593 |
DX | -0.591 |
cow | -0.584 |
Token | Profile |
Token ID | 13118 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
�醒 | +0.727 |
olit | +0.642 |
sted | +0.638 |
ult | +0.637 |
adr | +0.610 |
Neg logit contributions | |
DX | -0.568 |
Fathers | -0.547 |
DX | -0.544 |
resolves | -0.542 |
cow | -0.533 |
Token | Blog |
Token ID | 14001 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
�醒 | +1.413 |
ult | +1.226 |
olit | +1.226 |
sted | +1.215 |
adr | +1.146 |
Neg logit contributions | |
DX | -1.781 |
Fathers | -1.752 |
DX | -1.749 |
resolves | -1.742 |
cow | -1.723 |
Token | Joined |
Token ID | 16709 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
�醒 | +0.186 |
olit | +0.162 |
ult | +0.161 |
sted | +0.159 |
adr | +0.151 |
Neg logit contributions | |
DX | -0.199 |
Fathers | -0.197 |
DX | -0.196 |
resolves | -0.195 |
cow | -0.192 |
Token | December |
Token ID | 3426 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
�醒 | +0.524 |
olit | +0.471 |
ult | +0.469 |
sted | +0.465 |
adr | +0.450 |
Neg logit contributions | |
DX | -0.307 |
Fathers | -0.303 |
resolves | -0.299 |
DX | -0.299 |
cow | -0.292 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
�醒 | +0.552 |
olit | +0.492 |
ult | +0.487 |
sted | +0.485 |
adr | +0.467 |
Neg logit contributions | |
DX | -0.382 |
Fathers | -0.376 |
DX | -0.373 |
resolves | -0.371 |
cow | -0.364 |
Token | United |
Token ID | 1578 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
�醒 | +0.764 |
olit | +0.686 |
ult | +0.680 |
sted | +0.677 |
adr | +0.651 |
Neg logit contributions | |
DX | -0.482 |
DX | -0.475 |
Fathers | -0.474 |
resolves | -0.466 |
cow | -0.459 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
�醒 | +0.127 |
ult | +0.115 |
olit | +0.114 |
sted | +0.113 |
adr | +0.109 |
Neg logit contributions | |
DX | -0.076 |
DX | -0.075 |
cow | -0.074 |
resolves | -0.074 |
Fathers | -0.073 |
Token | motor |
Token ID | 5584 |
Feature activation | -9.90e-03 |
Pos logit contributions | |
DX | +0.022 |
DX | +0.021 |
cow | +0.021 |
resolves | +0.021 |
Fathers | +0.021 |
Neg logit contributions | |
�醒 | -0.038 |
olit | -0.034 |
ult | -0.034 |
sted | -0.034 |
adr | -0.032 |
Token | ized |
Token ID | 1143 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
DX | +0.005 |
DX | +0.005 |
cow | +0.005 |
resolves | +0.005 |
Fathers | +0.005 |
Neg logit contributions | |
�醒 | -0.009 |
olit | -0.008 |
ult | -0.008 |
sted | -0.008 |
adr | -0.008 |
Token | wheelchair |
Token ID | 27181 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
�醒 | +0.962 |
olit | +0.874 |
ult | +0.870 |
sted | +0.864 |
adr | +0.833 |
Neg logit contributions | |
DX | -0.574 |
DX | -0.563 |
cow | -0.556 |
resolves | -0.555 |
Fathers | -0.553 |
Token | ( |
Token ID | 357 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
�醒 | +0.115 |
ult | +0.105 |
olit | +0.105 |
sted | +0.104 |
adr | +0.100 |
Neg logit contributions | |
DX | -0.056 |
DX | -0.055 |
resolves | -0.054 |
Fathers | -0.054 |
cow | -0.054 |
Token | Figure |
Token ID | 11337 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
�醒 | +0.672 |
olit | +0.599 |
sted | +0.595 |
ult | +0.589 |
adr | +0.564 |
Neg logit contributions | |
DX | -0.571 |
DX | -0.544 |
Fathers | -0.543 |
resolves | -0.541 |
cow | -0.536 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
�醒 | +1.937 |
ult | +1.759 |
olit | +1.754 |
sted | +1.747 |
adr | +1.678 |
Neg logit contributions | |
DX | -1.235 |
Fathers | -1.205 |
resolves | -1.203 |
DX | -1.201 |
cow | -1.176 |
Token | A |
Token ID | 32 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
DX | +0.121 |
resolves | +0.117 |
DX | +0.117 |
Fathers | +0.117 |
cow | +0.116 |
Neg logit contributions | |
�醒 | -0.172 |
olit | -0.155 |
ult | -0.155 |
sted | -0.154 |
adr | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
DX | +0.084 |
resolves | +0.082 |
DX | +0.082 |
Fathers | +0.081 |
cow | +0.080 |
Neg logit contributions | |
�醒 | -0.160 |
olit | -0.146 |
ult | -0.145 |
sted | -0.144 |
adr | -0.139 |
Token | [ |
Token ID | 685 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
DX | +0.329 |
DX | +0.319 |
Fathers | +0.316 |
resolves | +0.316 |
cow | +0.315 |
Neg logit contributions | |
�醒 | -0.456 |
olit | -0.416 |
ult | -0.412 |
sted | -0.408 |
adr | -0.392 |
Token | Action |
Token ID | 12502 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
�醒 | +0.715 |
olit | +0.634 |
sted | +0.629 |
ult | +0.628 |
adr | +0.597 |
Neg logit contributions | |
DX | -0.613 |
Fathers | -0.591 |
resolves | -0.588 |
DX | -0.587 |
cow | -0.578 |
Token | questions |
Token ID | 2683 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
�醒 | +0.316 |
olit | +0.284 |
ult | +0.284 |
sted | +0.282 |
adr | +0.275 |
Neg logit contributions | |
Fathers | -0.168 |
DX | -0.167 |
cow | -0.166 |
DX | -0.164 |
resolves | -0.163 |
Token | gay |
Token ID | 5650 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
Fathers | +0.273 |
DX | +0.271 |
DX | +0.267 |
cow | +0.267 |
resolves | +0.264 |
Neg logit contributions | |
�醒 | -0.517 |
ult | -0.468 |
olit | -0.467 |
sted | -0.461 |
adr | -0.448 |
Token | girls |
Token ID | 4813 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
�醒 | +0.803 |
olit | +0.738 |
ult | +0.737 |
sted | +0.730 |
adr | +0.716 |
Neg logit contributions | |
Fathers | -0.271 |
DX | -0.269 |
DX | -0.259 |
resolves | -0.258 |
cow | -0.258 |
Token | still |
Token ID | 991 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
�醒 | +0.037 |
olit | +0.033 |
ult | +0.032 |
sted | +0.032 |
adr | +0.031 |
Neg logit contributions | |
Fathers | -0.030 |
DX | -0.030 |
cow | -0.029 |
resolves | -0.029 |
DX | -0.029 |
Token | get |
Token ID | 651 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
�醒 | +0.144 |
olit | +0.125 |
ult | +0.124 |
sted | +0.123 |
adr | +0.118 |
Neg logit contributions | |
resolves | -0.125 |
DX | -0.125 |
cow | -0.125 |
Fathers | -0.124 |
DX | -0.123 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
�醒 | +0.922 |
olit | +0.841 |
ult | +0.831 |
sted | +0.823 |
adr | +0.799 |
Neg logit contributions | |
DX | -0.546 |
Fathers | -0.538 |
resolves | -0.537 |
DX | -0.537 |
cow | -0.532 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
�醒 | +1.915 |
ult | +1.734 |
olit | +1.733 |
sted | +1.711 |
adr | +1.654 |
Neg logit contributions | |
DX | -1.249 |
Fathers | -1.234 |
DX | -1.221 |
resolves | -1.221 |
cow | -1.209 |
Token |
|
Token ID | 198 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
�醒 | +0.078 |
olit | +0.069 |
ult | +0.068 |
sted | +0.068 |
adr | +0.065 |
Neg logit contributions | |
DX | -0.065 |
Fathers | -0.064 |
DX | -0.064 |
resolves | -0.064 |
cow | -0.063 |
Token | MORE |
Token ID | 23346 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
DX | +0.121 |
Fathers | +0.116 |
DX | +0.114 |
resolves | +0.112 |
cow | +0.111 |
Neg logit contributions | |
�醒 | -0.145 |
olit | -0.128 |
ult | -0.126 |
sted | -0.126 |
adr | -0.119 |
Token | : |
Token ID | 25 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
�醒 | +0.293 |
olit | +0.264 |
ult | +0.264 |
sted | +0.261 |
adr | +0.252 |
Neg logit contributions | |
DX | -0.186 |
Fathers | -0.182 |
DX | -0.181 |
resolves | -0.180 |
cow | -0.177 |
Token | Restaurant |
Token ID | 26078 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Fathers | +0.226 |
DX | +0.221 |
DX | +0.219 |
resolves | +0.213 |
cow | +0.212 |
Neg logit contributions | |
�醒 | -0.298 |
olit | -0.266 |
ult | -0.266 |
sted | -0.259 |
adr | -0.251 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
�醒 | +0.352 |
olit | +0.311 |
ult | +0.311 |
sted | +0.307 |
adr | +0.297 |
Neg logit contributions | |
DX | -0.267 |
Fathers | -0.265 |
DX | -0.264 |
resolves | -0.262 |
cow | -0.261 |
Token | , |
Token ID | 11 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
DX | +0.132 |
Fathers | +0.128 |
DX | +0.128 |
resolves | +0.127 |
cow | +0.125 |
Neg logit contributions | |
�醒 | -0.267 |
olit | -0.246 |
ult | -0.245 |
sted | -0.244 |
adr | -0.236 |
Token | California |
Token ID | 3442 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
DX | +0.389 |
resolves | +0.380 |
DX | +0.379 |
cow | +0.379 |
Fathers | +0.379 |
Neg logit contributions | |
�醒 | -0.547 |
olit | -0.484 |
ult | -0.476 |
sted | -0.472 |
adr | -0.468 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
DX | +0.006 |
Fathers | +0.006 |
resolves | +0.006 |
DX | +0.006 |
cow | +0.006 |
Neg logit contributions | |
�醒 | -0.013 |
ult | -0.012 |
olit | -0.011 |
sted | -0.011 |
adr | -0.011 |
Token | Hide |
Token ID | 10415 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
DX | +0.011 |
Fathers | +0.011 |
DX | +0.011 |
resolves | +0.011 |
cow | +0.011 |
Neg logit contributions | |
�醒 | -0.020 |
ult | -0.018 |
olit | -0.018 |
sted | -0.018 |
adr | -0.017 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
�醒 | +0.693 |
ult | +0.634 |
olit | +0.631 |
sted | +0.630 |
adr | +0.602 |
Neg logit contributions | |
DX | -0.547 |
resolves | -0.533 |
Fathers | -0.532 |
DX | -0.526 |
cow | -0.522 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
�醒 | +1.418 |
olit | +1.317 |
ult | +1.299 |
sted | +1.298 |
adr | +1.247 |
Neg logit contributions | |
DX | -1.628 |
resolves | -1.586 |
cow | -1.575 |
Fathers | -1.566 |
advancements | -1.557 |
Token | of |
Token ID | 286 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
DX | +0.061 |
Fathers | +0.060 |
resolves | +0.060 |
DX | +0.059 |
cow | +0.058 |
Neg logit contributions | |
�醒 | -0.114 |
olit | -0.104 |
ult | -0.103 |
sted | -0.103 |
adr | -0.099 |
Token | 15 |
Token ID | 1315 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
�醒 | +0.162 |
ult | +0.146 |
olit | +0.145 |
sted | +0.145 |
adr | +0.138 |
Neg logit contributions | |
DX | -0.147 |
Fathers | -0.144 |
resolves | -0.143 |
DX | -0.142 |
cow | -0.141 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
�醒 | +0.387 |
olit | +0.345 |
ult | +0.345 |
sted | +0.343 |
adr | +0.323 |
Neg logit contributions | |
DX | -0.469 |
resolves | -0.459 |
Fathers | -0.459 |
DX | -0.455 |
cow | -0.452 |
Token | : |
Token ID | 25 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
�醒 | +1.026 |
ult | +0.947 |
olit | +0.941 |
sted | +0.940 |
adr | +0.898 |
Neg logit contributions | |
DX | -0.729 |
resolves | -0.712 |
Fathers | -0.712 |
DX | -0.703 |
cow | -0.696 |
Token | Hills |
Token ID | 14379 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
DX | +0.307 |
Fathers | +0.302 |
DX | +0.299 |
resolves | +0.298 |
cow | +0.292 |
Neg logit contributions | |
�醒 | -0.660 |
sted | -0.600 |
ult | -0.599 |
olit | -0.599 |
adr | -0.575 |
Token | , |
Token ID | 11 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
DX | +0.557 |
DX | +0.555 |
Fathers | +0.550 |
resolves | +0.539 |
cow | +0.536 |
Neg logit contributions | |
�醒 | -1.334 |
ult | -1.195 |
olit | -1.193 |
sted | -1.193 |
adr | -1.149 |
Token | California |
Token ID | 3442 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
DX | +0.332 |
Fathers | +0.329 |
resolves | +0.328 |
DX | +0.326 |
cow | +0.326 |
Neg logit contributions | |
�醒 | -0.471 |
olit | -0.413 |
sted | -0.406 |
ult | -0.406 |
adr | -0.398 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
DX | +0.023 |
Fathers | +0.023 |
resolves | +0.023 |
DX | +0.022 |
cow | +0.022 |
Neg logit contributions | |
�醒 | -0.047 |
ult | -0.043 |
olit | -0.043 |
sted | -0.043 |
adr | -0.042 |
Token | Hide |
Token ID | 10415 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Fathers | +0.163 |
DX | +0.161 |
DX | +0.160 |
resolves | +0.156 |
cow | +0.153 |
Neg logit contributions | |
�醒 | -0.303 |
ult | -0.272 |
sted | -0.272 |
olit | -0.272 |
adr | -0.262 |
Token | Caption |
Token ID | 11260 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
�醒 | +0.720 |
ult | +0.661 |
sted | +0.657 |
olit | +0.657 |
adr | +0.627 |
Neg logit contributions | |
DX | -0.576 |
resolves | -0.561 |
Fathers | -0.559 |
DX | -0.553 |
cow | -0.550 |
Token | 14 |
Token ID | 1478 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
�醒 | +1.483 |
ult | +1.363 |
olit | +1.353 |
sted | +1.352 |
adr | +1.288 |
Neg logit contributions | |
DX | -1.585 |
Fathers | -1.553 |
resolves | -1.547 |
cow | -1.532 |
DX | -1.527 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
DX | +0.351 |
Fathers | +0.344 |
resolves | +0.341 |
DX | +0.341 |
cow | +0.334 |
Neg logit contributions | |
�醒 | -0.682 |
olit | -0.617 |
ult | -0.614 |
sted | -0.611 |
adr | -0.591 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
DX | +0.098 |
Fathers | +0.096 |
resolves | +0.096 |
DX | +0.095 |
cow | +0.094 |
Neg logit contributions | |
�醒 | -0.111 |
ult | -0.099 |
olit | -0.099 |
sted | -0.098 |
adr | -0.094 |
Token | Photos |
Token ID | 9434 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
�醒 | +0.232 |
olit | +0.206 |
ult | +0.206 |
sted | +0.205 |
adr | +0.193 |
Neg logit contributions | |
DX | -0.274 |
Fathers | -0.269 |
resolves | -0.269 |
DX | -0.267 |
cow | -0.265 |
Token | : |
Token ID | 25 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
�醒 | +1.094 |
ult | +1.013 |
sted | +1.005 |
olit | +1.005 |
adr | +0.959 |
Neg logit contributions | |
DX | -0.786 |
resolves | -0.768 |
Fathers | -0.767 |
DX | -0.757 |
cow | -0.750 |
Token | high |
Token ID | 1029 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
�醒 | +0.284 |
olit | +0.252 |
ult | +0.251 |
sted | +0.246 |
adr | +0.236 |
Neg logit contributions | |
Fathers | -0.224 |
cow | -0.222 |
DX | -0.220 |
resolves | -0.220 |
DX | -0.218 |
Token | court |
Token ID | 2184 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
�醒 | +0.144 |
ult | +0.130 |
olit | +0.130 |
sted | +0.129 |
adr | +0.124 |
Neg logit contributions | |
DX | -0.087 |
resolves | -0.087 |
Fathers | -0.086 |
cow | -0.086 |
DX | -0.084 |
Token | � |
Token ID | 447 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
�醒 | +0.488 |
olit | +0.443 |
ult | +0.440 |
sted | +0.436 |
adr | +0.423 |
Neg logit contributions | |
Fathers | -0.275 |
DX | -0.274 |
resolves | -0.274 |
cow | -0.270 |
DX | -0.269 |
Token | � |
Token ID | 247 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
DX | +0.052 |
Fathers | +0.051 |
DX | +0.051 |
resolves | +0.050 |
cow | +0.050 |
Neg logit contributions | |
�醒 | -0.045 |
ult | -0.041 |
olit | -0.040 |
sted | -0.040 |
adr | -0.038 |
Token | s |
Token ID | 82 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
DX | +0.093 |
Fathers | +0.091 |
resolves | +0.091 |
cow | +0.090 |
DX | +0.090 |
Neg logit contributions | |
�醒 | -0.116 |
olit | -0.103 |
ult | -0.101 |
sted | -0.101 |
adr | -0.098 |
Token | door |
Token ID | 3420 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Fathers | +0.002 |
resolves | +0.002 |
cow | +0.002 |
DX | +0.002 |
DX | +0.002 |
Neg logit contributions | |
�醒 | -0.002 |
olit | -0.002 |
ult | -0.002 |
sted | -0.002 |
adr | -0.002 |
Token | expressing |
Token ID | 16621 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
cow | +1.140 |
Fathers | +1.139 |
resolves | +1.126 |
changing | +1.121 |
DX | +1.093 |
Neg logit contributions | |
�醒 | -2.362 |
olit | -2.156 |
ult | -2.138 |
sted | -2.112 |
adr | -2.062 |
Token | concern |
Token ID | 2328 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
�醒 | +0.167 |
olit | +0.150 |
ult | +0.149 |
sted | +0.148 |
adr | +0.143 |
Neg logit contributions | |
resolves | -0.106 |
cow | -0.106 |
DX | -0.106 |
Fathers | -0.106 |
DX | -0.104 |
Token | over |
Token ID | 625 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
�醒 | +0.719 |
olit | +0.651 |
ult | +0.646 |
sted | +0.643 |
adr | +0.625 |
Neg logit contributions | |
DX | -0.391 |
Fathers | -0.388 |
resolves | -0.386 |
cow | -0.382 |
DX | -0.382 |
Token | the |
Token ID | 262 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
�醒 | +0.235 |
olit | +0.214 |
ult | +0.214 |
sted | +0.212 |
adr | +0.204 |
Neg logit contributions | |
DX | -0.132 |
Fathers | -0.131 |
resolves | -0.130 |
DX | -0.129 |
cow | -0.129 |
Token | growing |
Token ID | 3957 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
DX | +0.216 |
Fathers | +0.216 |
cow | +0.215 |
resolves | +0.215 |
DX | +0.214 |
Neg logit contributions | |
�醒 | -0.412 |
olit | -0.372 |
ult | -0.372 |
sted | -0.368 |
adr | -0.354 |
Token | remaining |
Token ID | 5637 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Fathers | +0.075 |
DX | +0.073 |
DX | +0.073 |
resolves | +0.073 |
cow | +0.073 |
Neg logit contributions | |
�醒 | -0.132 |
sted | -0.119 |
olit | -0.118 |
ult | -0.117 |
adr | -0.114 |
Token | minutes |
Token ID | 2431 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Fathers | +0.207 |
DX | +0.204 |
resolves | +0.204 |
cow | +0.203 |
DX | +0.202 |
Neg logit contributions | |
�醒 | -0.317 |
olit | -0.282 |
sted | -0.280 |
ult | -0.279 |
adr | -0.269 |
Token | were |
Token ID | 547 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
�醒 | +0.547 |
olit | +0.490 |
sted | +0.486 |
ult | +0.483 |
adr | +0.469 |
Neg logit contributions | |
resolves | -0.320 |
cow | -0.319 |
DX | -0.318 |
DX | -0.318 |
Fathers | -0.318 |
Token | unable |
Token ID | 5906 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
DX | +0.012 |
Fathers | +0.012 |
resolves | +0.012 |
cow | +0.012 |
DX | +0.012 |
Neg logit contributions | |
�醒 | -0.018 |
olit | -0.016 |
ult | -0.016 |
sted | -0.016 |
adr | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
resolves | +0.180 |
DX | +0.180 |
DX | +0.179 |
Fathers | +0.178 |
cow | +0.174 |
Neg logit contributions | |
�醒 | -0.449 |
ult | -0.409 |
olit | -0.408 |
sted | -0.404 |
adr | -0.394 |
Token | break |
Token ID | 2270 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
resolves | +0.304 |
cow | +0.302 |
DX | +0.299 |
Fathers | +0.298 |
DX | +0.298 |
Neg logit contributions | |
�醒 | -0.435 |
ult | -0.387 |
olit | -0.386 |
sted | -0.384 |
adr | -0.373 |
Token | the |
Token ID | 262 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
resolves | +1.142 |
DX | +1.125 |
Fathers | +1.116 |
DX | +1.112 |
cow | +1.109 |
Neg logit contributions | |
�醒 | -2.369 |
olit | -2.143 |
ult | -2.091 |
sted | -2.069 |
adr | -2.051 |
Token | dead |
Token ID | 2636 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Fathers | +0.177 |
resolves | +0.176 |
DX | +0.175 |
cow | +0.175 |
DX | +0.174 |
Neg logit contributions | |
�醒 | -0.278 |
olit | -0.247 |
sted | -0.243 |
ult | -0.242 |
adr | -0.235 |
Token | lock |
Token ID | 5354 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
DX | +0.219 |
resolves | +0.218 |
cow | +0.217 |
DX | +0.216 |
Fathers | +0.215 |
Neg logit contributions | |
�醒 | -0.198 |
ult | -0.173 |
olit | -0.172 |
sted | -0.171 |
adr | -0.165 |
Token | and |
Token ID | 290 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
resolves | +0.167 |
Fathers | +0.166 |
DX | +0.165 |
DX | +0.163 |
cow | +0.162 |
Neg logit contributions | |
�醒 | -0.381 |
olit | -0.345 |
sted | -0.343 |
ult | -0.342 |
adr | -0.333 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Fathers | +0.127 |
resolves | +0.125 |
DX | +0.124 |
DX | +0.124 |
cow | +0.123 |
Neg logit contributions | |
�醒 | -0.201 |
olit | -0.177 |
sted | -0.177 |
ult | -0.176 |
adr | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
�醒 | +0.061 |
olit | +0.056 |
ult | +0.056 |
sted | +0.055 |
adr | +0.053 |
Neg logit contributions | |
DX | -0.037 |
cow | -0.037 |
DX | -0.036 |
Fathers | -0.036 |
resolves | -0.036 |
Token | shit |
Token ID | 7510 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
DX | +0.112 |
Fathers | +0.111 |
DX | +0.110 |
cow | +0.110 |
resolves | +0.110 |
Neg logit contributions | |
�醒 | -0.185 |
sted | -0.167 |
olit | -0.167 |
ult | -0.166 |
adr | -0.160 |
Token | , |
Token ID | 11 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
DX | +0.045 |
cow | +0.044 |
Fathers | +0.044 |
DX | +0.044 |
resolves | +0.043 |
Neg logit contributions | |
�醒 | -0.080 |
olit | -0.072 |
ult | -0.071 |
sted | -0.071 |
adr | -0.070 |
Token | piss |
Token ID | 18314 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
DX | +0.280 |
Fathers | +0.279 |
cow | +0.278 |
DX | +0.277 |
resolves | +0.276 |
Neg logit contributions | |
�醒 | -0.463 |
olit | -0.417 |
sted | -0.416 |
ult | -0.413 |
adr | -0.399 |
Token | , |
Token ID | 11 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
�醒 | +0.236 |
olit | +0.215 |
sted | +0.214 |
ult | +0.214 |
adr | +0.208 |
Neg logit contributions | |
DX | -0.116 |
DX | -0.114 |
cow | -0.114 |
Fathers | -0.113 |
resolves | -0.112 |
Token | brush |
Token ID | 14093 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
DX | +0.119 |
Fathers | +0.118 |
cow | +0.117 |
DX | +0.117 |
resolves | +0.117 |
Neg logit contributions | |
�醒 | -0.192 |
olit | -0.173 |
sted | -0.173 |
ult | -0.172 |
adr | -0.165 |
Token | teeth |
Token ID | 9941 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
cow | +1.237 |
DX | +1.228 |
DX | +1.224 |
Fathers | +1.210 |
resolves | +1.197 |
Neg logit contributions | |
�醒 | -2.173 |
ult | -1.979 |
olit | -1.957 |
sted | -1.931 |
adr | -1.903 |
Token | and |
Token ID | 290 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
DX | +0.324 |
cow | +0.322 |
resolves | +0.322 |
Fathers | +0.321 |
DX | +0.319 |
Neg logit contributions | |
�醒 | -0.742 |
olit | -0.674 |
ult | -0.669 |
sted | -0.669 |
adr | -0.647 |
Token | hair |
Token ID | 4190 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
DX | +0.022 |
Fathers | +0.022 |
DX | +0.022 |
resolves | +0.022 |
cow | +0.022 |
Neg logit contributions | |
�醒 | -0.033 |
ult | -0.029 |
olit | -0.029 |
sted | -0.029 |
adr | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
DX | +0.467 |
Fathers | +0.461 |
resolves | +0.459 |
changing | +0.458 |
DX | +0.457 |
Neg logit contributions | |
�醒 | -0.851 |
ult | -0.766 |
olit | -0.765 |
sted | -0.762 |
adr | -0.731 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
DX | +0.100 |
Fathers | +0.100 |
cow | +0.100 |
resolves | +0.100 |
DX | +0.099 |
Neg logit contributions | |
�醒 | -0.167 |
olit | -0.150 |
sted | -0.149 |
ult | -0.149 |
adr | -0.143 |
Token | in |
Token ID | 287 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
�醒 | +0.115 |
olit | +0.103 |
sted | +0.101 |
ult | +0.101 |
adr | +0.097 |
Neg logit contributions | |
Fathers | -0.088 |
DX | -0.087 |
DX | -0.086 |
cow | -0.086 |
resolves | -0.086 |
Token | 2002 |
Token ID | 6244 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
�醒 | +0.667 |
olit | +0.593 |
sted | +0.586 |
ult | +0.584 |
adr | +0.564 |
Neg logit contributions | |
DX | -0.430 |
Fathers | -0.429 |
DX | -0.425 |
cow | -0.424 |
resolves | -0.419 |
Token | , |
Token ID | 11 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
�醒 | +0.189 |
olit | +0.172 |
ult | +0.170 |
sted | +0.169 |
adr | +0.163 |
Neg logit contributions | |
Fathers | -0.103 |
DX | -0.102 |
cow | -0.100 |
DX | -0.100 |
resolves | -0.100 |
Token | his |
Token ID | 465 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
�醒 | +0.596 |
olit | +0.534 |
sted | +0.527 |
ult | +0.527 |
adr | +0.505 |
Neg logit contributions | |
Fathers | -0.422 |
DX | -0.420 |
DX | -0.413 |
cow | -0.412 |
resolves | -0.411 |
Token | net |
Token ID | 2010 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
�醒 | +1.047 |
olit | +0.925 |
ult | +0.914 |
sted | +0.913 |
adr | +0.875 |
Neg logit contributions | |
DX | -0.732 |
Fathers | -0.729 |
cow | -0.727 |
DX | -0.720 |
resolves | -0.719 |
Token | worth |
Token ID | 2861 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
resolves | +0.397 |
DX | +0.396 |
cow | +0.389 |
Fathers | +0.388 |
changing | +0.380 |
Neg logit contributions | |
�醒 | -0.889 |
ult | -0.800 |
olit | -0.795 |
sted | -0.782 |
adr | -0.764 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
cow | +1.364 |
resolves | +1.334 |
drops | +1.331 |
DX | +1.329 |
Fathers | +1.328 |
Neg logit contributions | |
�醒 | -2.087 |
olit | -1.856 |
ult | -1.778 |
sted | -1.770 |
adr | -1.761 |
Token | estimated |
Token ID | 6108 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
�醒 | +0.101 |
olit | +0.089 |
ult | +0.088 |
sted | +0.087 |
adr | +0.084 |
Neg logit contributions | |
DX | -0.076 |
Fathers | -0.076 |
resolves | -0.075 |
DX | -0.075 |
cow | -0.075 |
Token | at |
Token ID | 379 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
DX | +0.037 |
Fathers | +0.035 |
DX | +0.035 |
resolves | +0.035 |
cow | +0.035 |
Neg logit contributions | |
�醒 | -0.081 |
olit | -0.075 |
ult | -0.074 |
sted | -0.074 |
adr | -0.072 |
Token | $ |
Token ID | 720 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
�醒 | +0.045 |
olit | +0.041 |
ult | +0.040 |
sted | +0.040 |
adr | +0.039 |
Neg logit contributions | |
DX | -0.029 |
Fathers | -0.029 |
DX | -0.029 |
cow | -0.029 |
resolves | -0.028 |
Token | 850 |
Token ID | 25764 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
DX | +0.120 |
Fathers | +0.116 |
resolves | +0.115 |
DX | +0.114 |
cow | +0.113 |
Neg logit contributions | |
�醒 | -0.146 |
olit | -0.127 |
sted | -0.124 |
ult | -0.123 |
adr | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
DX | +0.052 |
Fathers | +0.050 |
resolves | +0.050 |
DX | +0.050 |
cow | +0.049 |
Neg logit contributions | |
�醒 | -0.121 |
olit | -0.111 |
ult | -0.110 |
sted | -0.110 |
adr | -0.106 |
Token | Hulu |
Token ID | 39739 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
�醒 | +0.416 |
olit | +0.370 |
sted | +0.368 |
ult | +0.366 |
adr | +0.353 |
Neg logit contributions | |
DX | -0.324 |
Fathers | -0.319 |
DX | -0.319 |
resolves | -0.316 |
cow | -0.312 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
�醒 | +0.332 |
olit | +0.304 |
ult | +0.303 |
sted | +0.302 |
adr | +0.292 |
Neg logit contributions | |
DX | -0.155 |
DX | -0.149 |
Fathers | -0.149 |
resolves | -0.149 |
cow | -0.145 |
Token | and |
Token ID | 290 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
�醒 | +0.115 |
olit | +0.105 |
sted | +0.104 |
ult | +0.103 |
adr | +0.101 |
Neg logit contributions | |
DX | -0.059 |
Fathers | -0.058 |
DX | -0.058 |
resolves | -0.057 |
cow | -0.056 |
Token | Amazon |
Token ID | 6186 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
�醒 | +0.507 |
olit | +0.452 |
sted | +0.450 |
ult | +0.449 |
adr | +0.435 |
Neg logit contributions | |
DX | -0.354 |
Fathers | -0.351 |
DX | -0.350 |
resolves | -0.347 |
cow | -0.342 |
Token | Prime |
Token ID | 5537 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
DX | +0.830 |
resolves | +0.810 |
Fathers | +0.810 |
DX | +0.804 |
cow | +0.793 |
Neg logit contributions | |
�醒 | -1.230 |
olit | -1.116 |
ult | -1.106 |
sted | -1.098 |
adr | -1.063 |
Token | among |
Token ID | 1871 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
DX | +1.280 |
Fathers | +1.248 |
DX | +1.233 |
resolves | +1.219 |
cow | +1.213 |
Neg logit contributions | |
�醒 | -2.152 |
olit | -1.937 |
ult | -1.925 |
sted | -1.903 |
adr | -1.877 |
Token | others |
Token ID | 1854 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
DX | +0.119 |
DX | +0.115 |
Fathers | +0.115 |
resolves | +0.115 |
cow | +0.113 |
Neg logit contributions | |
�醒 | -0.245 |
ult | -0.224 |
olit | -0.224 |
sted | -0.222 |
adr | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
�醒 | +0.372 |
olit | +0.341 |
ult | +0.339 |
sted | +0.338 |
adr | +0.328 |
Neg logit contributions | |
DX | -0.162 |
DX | -0.157 |
Fathers | -0.157 |
resolves | -0.156 |
cow | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
�醒 | +0.203 |
olit | +0.182 |
ult | +0.180 |
sted | +0.179 |
adr | +0.171 |
Neg logit contributions | |
Fathers | -0.162 |
DX | -0.160 |
DX | -0.160 |
resolves | -0.157 |
cow | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
�醒 | +0.227 |
olit | +0.201 |
ult | +0.200 |
sted | +0.198 |
adr | +0.190 |
Neg logit contributions | |
DX | -0.194 |
Fathers | -0.190 |
resolves | -0.189 |
DX | -0.189 |
cow | -0.185 |
Token | J |
Token ID | 449 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
�醒 | +0.438 |
olit | +0.392 |
ult | +0.390 |
sted | +0.385 |
adr | +0.368 |
Neg logit contributions | |
Fathers | -0.349 |
DX | -0.348 |
DX | -0.344 |
resolves | -0.339 |
cow | -0.332 |
Token | arl |
Token ID | 7063 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
DX | +0.144 |
Fathers | +0.141 |
DX | +0.140 |
resolves | +0.139 |
cow | +0.137 |
Neg logit contributions | |
�醒 | -0.148 |
sted | -0.127 |
ult | -0.127 |
olit | -0.127 |
adr | -0.118 |
Token | never |
Token ID | 1239 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
�醒 | +0.808 |
olit | +0.721 |
ult | +0.715 |
sted | +0.700 |
adr | +0.682 |
Neg logit contributions | |
Fathers | -0.635 |
DX | -0.633 |
resolves | -0.632 |
DX | -0.626 |
cow | -0.618 |
Token | thought |
Token ID | 1807 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
�醒 | +0.399 |
olit | +0.352 |
ult | +0.351 |
sted | +0.347 |
adr | +0.335 |
Neg logit contributions | |
resolves | -0.299 |
Fathers | -0.297 |
DX | -0.294 |
cow | -0.292 |
DX | -0.291 |
Token | he |
Token ID | 339 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Fathers | +0.480 |
DX | +0.479 |
DX | +0.478 |
resolves | +0.474 |
cow | +0.469 |
Neg logit contributions | |
�醒 | -0.847 |
olit | -0.762 |
sted | -0.752 |
ult | -0.751 |
adr | -0.736 |
Token | 'd |
Token ID | 1549 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
DX | +0.160 |
Fathers | +0.160 |
resolves | +0.159 |
cow | +0.157 |
DX | +0.156 |
Neg logit contributions | |
�醒 | -0.267 |
olit | -0.239 |
ult | -0.238 |
sted | -0.237 |
adr | -0.229 |
Token | be |
Token ID | 307 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Fathers | +1.473 |
cow | +1.471 |
resolves | +1.468 |
DX | +1.439 |
changing | +1.438 |
Neg logit contributions | |
�醒 | -1.937 |
olit | -1.672 |
ult | -1.649 |
sted | -1.638 |
adr | -1.605 |
Token | a |
Token ID | 257 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
�醒 | +0.321 |
olit | +0.289 |
ult | +0.288 |
sted | +0.284 |
adr | +0.275 |
Neg logit contributions | |
DX | -0.204 |
Fathers | -0.203 |
resolves | -0.201 |
DX | -0.201 |
cow | -0.200 |
Token | hockey |
Token ID | 12217 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Fathers | +0.017 |
DX | +0.016 |
DX | +0.016 |
cow | +0.016 |
resolves | +0.016 |
Neg logit contributions | |
�醒 | -0.027 |
olit | -0.024 |
ult | -0.024 |
sted | -0.024 |
adr | -0.023 |
Token | dad |
Token ID | 9955 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
�醒 | +0.132 |
olit | +0.119 |
ult | +0.119 |
sted | +0.118 |
adr | +0.114 |
Neg logit contributions | |
DX | -0.072 |
cow | -0.071 |
DX | -0.070 |
Fathers | -0.070 |
resolves | -0.068 |
Token | when |
Token ID | 618 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
�醒 | +0.800 |
olit | +0.729 |
ult | +0.727 |
sted | +0.723 |
adr | +0.702 |
Neg logit contributions | |
DX | -0.381 |
Fathers | -0.377 |
resolves | -0.374 |
DX | -0.371 |
cow | -0.369 |
Token | beneficial |
Token ID | 13205 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
�醒 | +0.086 |
olit | +0.077 |
ult | +0.077 |
sted | +0.076 |
adr | +0.074 |
Neg logit contributions | |
DX | -0.053 |
Fathers | -0.052 |
resolves | -0.052 |
DX | -0.052 |
cow | -0.051 |
Token | outcome |
Token ID | 8055 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
resolves | +0.411 |
Fathers | +0.409 |
DX | +0.409 |
DX | +0.407 |
cow | +0.401 |
Neg logit contributions | |
�醒 | -0.664 |
olit | -0.591 |
sted | -0.589 |
ult | -0.589 |
adr | -0.570 |
Token | would |
Token ID | 561 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
�醒 | +0.576 |
olit | +0.512 |
sted | +0.510 |
ult | +0.508 |
adr | +0.489 |
Neg logit contributions | |
resolves | -0.408 |
Fathers | -0.401 |
DX | -0.398 |
DX | -0.394 |
cow | -0.392 |
Token | be |
Token ID | 307 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
�醒 | +0.176 |
sted | +0.156 |
olit | +0.156 |
ult | +0.154 |
adr | +0.150 |
Neg logit contributions | |
DX | -0.145 |
resolves | -0.144 |
cow | -0.143 |
Fathers | -0.142 |
DX | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
�醒 | +0.077 |
olit | +0.069 |
ult | +0.069 |
sted | +0.068 |
adr | +0.066 |
Neg logit contributions | |
DX | -0.045 |
resolves | -0.044 |
Fathers | -0.044 |
DX | -0.044 |
cow | -0.043 |
Token | draw |
Token ID | 3197 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
�醒 | +0.048 |
ult | +0.043 |
olit | +0.043 |
sted | +0.043 |
adr | +0.041 |
Neg logit contributions | |
DX | -0.035 |
Fathers | -0.034 |
resolves | -0.034 |
DX | -0.034 |
cow | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
resolves | +1.017 |
DX | +1.003 |
DX | +0.996 |
Fathers | +0.993 |
cow | +0.986 |
Neg logit contributions | |
�醒 | -2.351 |
olit | -2.114 |
sted | -2.110 |
ult | -2.102 |
adr | -2.047 |
Token | In |
Token ID | 554 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
DX | +0.045 |
Fathers | +0.045 |
DX | +0.045 |
resolves | +0.044 |
cow | +0.043 |
Neg logit contributions | |
�醒 | -0.057 |
olit | -0.050 |
ult | -0.050 |
sted | -0.050 |
adr | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
�醒 | +0.055 |
olit | +0.049 |
ult | +0.049 |
sted | +0.049 |
adr | +0.047 |
Neg logit contributions | |
DX | -0.033 |
DX | -0.032 |
Fathers | -0.032 |
resolves | -0.032 |
cow | -0.031 |
Token | case |
Token ID | 1339 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
�醒 | +0.338 |
olit | +0.303 |
ult | +0.300 |
sted | +0.299 |
adr | +0.287 |
Neg logit contributions | |
DX | -0.253 |
Fathers | -0.251 |
DX | -0.251 |
resolves | -0.249 |
cow | -0.246 |
Token | of |
Token ID | 286 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
DX | +0.046 |
Fathers | +0.044 |
resolves | +0.044 |
DX | +0.044 |
cow | +0.043 |
Neg logit contributions | |
�醒 | -0.089 |
olit | -0.081 |
ult | -0.081 |
sted | -0.081 |
adr | -0.078 |
Token | presidential |
Token ID | 4787 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
Fathers | +0.160 |
DX | +0.160 |
resolves | +0.159 |
DX | +0.159 |
cow | +0.157 |
Neg logit contributions | |
�醒 | -0.272 |
olit | -0.245 |
ult | -0.244 |
sted | -0.243 |
adr | -0.235 |
Token | election |
Token ID | 3071 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Fathers | +0.047 |
resolves | +0.047 |
DX | +0.047 |
DX | +0.047 |
cow | +0.047 |
Neg logit contributions | |
�醒 | -0.065 |
olit | -0.058 |
ult | -0.058 |
sted | -0.058 |
adr | -0.056 |
Token | ( |
Token ID | 357 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
DX | +0.048 |
resolves | +0.048 |
Fathers | +0.047 |
DX | +0.047 |
cow | +0.046 |
Neg logit contributions | |
�醒 | -0.098 |
sted | -0.089 |
ult | -0.089 |
olit | -0.089 |
adr | -0.085 |
Token | or |
Token ID | 273 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
DX | +0.330 |
Fathers | +0.319 |
resolves | +0.317 |
DX | +0.316 |
cow | +0.315 |
Neg logit contributions | |
�醒 | -0.355 |
sted | -0.305 |
olit | -0.305 |
ult | -0.297 |
adr | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
DX | +0.100 |
Fathers | +0.100 |
resolves | +0.099 |
DX | +0.099 |
cow | +0.098 |
Neg logit contributions | |
�醒 | -0.162 |
olit | -0.146 |
ult | -0.145 |
sted | -0.145 |
adr | -0.140 |
Token | heck |
Token ID | 22574 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
DX | +0.078 |
Fathers | +0.077 |
resolves | +0.076 |
DX | +0.076 |
cow | +0.075 |
Neg logit contributions | |
�醒 | -0.147 |
ult | -0.133 |
olit | -0.133 |
sted | -0.132 |
adr | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
DX | +1.070 |
Fathers | +1.057 |
DX | +1.042 |
cow | +1.033 |
resolves | +1.032 |
Neg logit contributions | |
�醒 | -2.216 |
olit | -2.022 |
ult | -2.019 |
sted | -2.003 |
adr | -1.957 |
Token | any |
Token ID | 597 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
DX | +0.090 |
Fathers | +0.090 |
resolves | +0.089 |
DX | +0.089 |
cow | +0.088 |
Neg logit contributions | |
�醒 | -0.144 |
olit | -0.130 |
ult | -0.129 |
sted | -0.128 |
adr | -0.124 |
Token | political |
Token ID | 1964 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
DX | +0.012 |
Fathers | +0.012 |
resolves | +0.012 |
DX | +0.012 |
cow | +0.012 |
Neg logit contributions | |
�醒 | -0.021 |
olit | -0.019 |
ult | -0.019 |
sted | -0.019 |
adr | -0.019 |
Token | event |
Token ID | 1785 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
DX | +0.239 |
resolves | +0.238 |
Fathers | +0.238 |
DX | +0.237 |
cow | +0.237 |
Neg logit contributions | |
�醒 | -0.373 |
olit | -0.334 |
sted | -0.333 |
ult | -0.331 |
adr | -0.320 |
Token | of |
Token ID | 286 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
�醒 | +0.513 |
ult | +0.465 |
olit | +0.464 |
sted | +0.462 |
adr | +0.447 |
Neg logit contributions | |
DX | -0.258 |
Fathers | -0.254 |
resolves | -0.252 |
DX | -0.251 |
cow | -0.248 |
Token | speed |
Token ID | 12287 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
�醒 | +0.258 |
olit | +0.226 |
sted | +0.221 |
ult | +0.220 |
adr | +0.212 |
Neg logit contributions | |
DX | -0.250 |
DX | -0.244 |
resolves | -0.241 |
Fathers | -0.241 |
cow | -0.240 |
Token | pulse |
Token ID | 19445 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
DX | +0.055 |
DX | +0.054 |
resolves | +0.054 |
cow | +0.053 |
Fathers | +0.053 |
Neg logit contributions | |
�醒 | -0.084 |
olit | -0.075 |
sted | -0.075 |
ult | -0.074 |
adr | -0.072 |
Token | jet |
Token ID | 31173 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
DX | +0.274 |
resolves | +0.267 |
DX | +0.266 |
Fathers | +0.265 |
cow | +0.263 |
Neg logit contributions | |
�醒 | -0.352 |
olit | -0.315 |
ult | -0.313 |
sted | -0.312 |
adr | -0.299 |
Token | engine |
Token ID | 3113 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
DX | +0.015 |
resolves | +0.015 |
DX | +0.015 |
Fathers | +0.015 |
cow | +0.014 |
Neg logit contributions | |
�醒 | -0.021 |
olit | -0.019 |
ult | -0.019 |
sted | -0.019 |
adr | -0.018 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
DX | +0.251 |
resolves | +0.250 |
DX | +0.248 |
Fathers | +0.247 |
cow | +0.244 |
Neg logit contributions | |
�醒 | -0.353 |
olit | -0.314 |
sted | -0.312 |
ult | -0.311 |
adr | -0.297 |
Token | starts |
Token ID | 4940 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
resolves | +0.497 |
Fathers | +0.486 |
DX | +0.483 |
DX | +0.480 |
cow | +0.479 |
Neg logit contributions | |
�醒 | -0.788 |
olit | -0.701 |
ult | -0.694 |
sted | -0.689 |
adr | -0.669 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
changing | +1.068 |
DX | +1.055 |
cow | +1.051 |
resolves | +1.046 |
Fathers | +1.038 |
Neg logit contributions | |
�醒 | -2.230 |
olit | -2.038 |
ult | -1.980 |
sted | -1.975 |
adr | -1.962 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
DX | +0.196 |
Fathers | +0.192 |
resolves | +0.191 |
DX | +0.191 |
cow | +0.187 |
Neg logit contributions | |
�醒 | -0.237 |
olit | -0.208 |
ult | -0.206 |
sted | -0.205 |
adr | -0.196 |
Token | making |
Token ID | 8601 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
DX | +0.134 |
Fathers | +0.128 |
DX | +0.127 |
resolves | +0.127 |
changing | +0.126 |
Neg logit contributions | |
�醒 | -0.186 |
olit | -0.164 |
sted | -0.161 |
ult | -0.157 |
adr | -0.155 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
�醒 | +0.236 |
olit | +0.213 |
ult | +0.211 |
sted | +0.210 |
adr | +0.204 |
Neg logit contributions | |
DX | -0.156 |
DX | -0.154 |
Fathers | -0.153 |
resolves | -0.153 |
cow | -0.151 |
Token | lot |
Token ID | 1256 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
�醒 | +0.088 |
olit | +0.080 |
ult | +0.079 |
sted | +0.078 |
adr | +0.076 |
Neg logit contributions | |
DX | -0.057 |
DX | -0.056 |
Fathers | -0.056 |
resolves | -0.056 |
cow | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
�醒 | +0.107 |
ult | +0.097 |
olit | +0.097 |
sted | +0.097 |
adr | +0.093 |
Neg logit contributions | |
resolves | -0.055 |
DX | -0.055 |
DX | -0.054 |
Fathers | -0.054 |
cow | -0.053 |
Token | get |
Token ID | 651 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
resolves | +0.394 |
DX | +0.387 |
cow | +0.386 |
Fathers | +0.384 |
DX | +0.383 |
Neg logit contributions | |
�醒 | -0.536 |
olit | -0.474 |
sted | -0.470 |
ult | -0.469 |
adr | -0.454 |
Token | out |
Token ID | 503 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
DX | +0.152 |
Fathers | +0.150 |
resolves | +0.150 |
DX | +0.149 |
cow | +0.146 |
Neg logit contributions | |
�醒 | -0.267 |
olit | -0.243 |
ult | -0.242 |
sted | -0.240 |
adr | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Fathers | +0.094 |
resolves | +0.093 |
DX | +0.093 |
DX | +0.093 |
cow | +0.091 |
Neg logit contributions | |
�醒 | -0.203 |
olit | -0.183 |
ult | -0.182 |
sted | -0.181 |
adr | -0.176 |
Token | Either |
Token ID | 15467 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
DX | +0.390 |
Fathers | +0.382 |
DX | +0.377 |
resolves | +0.369 |
Allaah | +0.364 |
Neg logit contributions | |
�醒 | -0.454 |
olit | -0.404 |
ult | -0.401 |
sted | -0.401 |
adr | -0.379 |
Token | way |
Token ID | 835 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
�醒 | +0.135 |
olit | +0.116 |
ult | +0.116 |
sted | +0.114 |
adr | +0.110 |
Neg logit contributions | |
DX | -0.136 |
Fathers | -0.135 |
DX | -0.135 |
resolves | -0.135 |
cow | -0.134 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
resolves | +0.979 |
DX | +0.978 |
DX | +0.974 |
Fathers | +0.972 |
cow | +0.948 |
Neg logit contributions | |
�醒 | -2.278 |
olit | -2.071 |
ult | -2.060 |
sted | -2.042 |
adr | -2.001 |
Token | Kam |
Token ID | 12670 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
DX | +0.078 |
resolves | +0.077 |
Fathers | +0.077 |
DX | +0.076 |
cow | +0.075 |
Neg logit contributions | |
�醒 | -0.130 |
olit | -0.116 |
ult | -0.116 |
sted | -0.115 |
adr | -0.111 |
Token | al |
Token ID | 282 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
�醒 | +0.266 |
olit | +0.223 |
ult | +0.222 |
sted | +0.221 |
adr | +0.208 |
Neg logit contributions | |
DX | -0.317 |
resolves | -0.312 |
Fathers | -0.312 |
DX | -0.309 |
cow | -0.307 |
Token | had |
Token ID | 550 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
�醒 | +0.183 |
olit | +0.163 |
ult | +0.162 |
sted | +0.160 |
adr | +0.155 |
Neg logit contributions | |
resolves | -0.120 |
DX | -0.119 |
Fathers | -0.118 |
DX | -0.118 |
cow | -0.117 |
Token | spent |
Token ID | 3377 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
DX | +0.224 |
Fathers | +0.222 |
resolves | +0.222 |
DX | +0.222 |
cow | +0.219 |
Neg logit contributions | |
�醒 | -0.342 |
olit | -0.308 |
ult | -0.306 |
sted | -0.305 |
adr | -0.293 |
Token | as |
Token ID | 355 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
�醒 | +0.362 |
olit | +0.329 |
ult | +0.328 |
sted | +0.327 |
adr | +0.316 |
Neg logit contributions | |
DX | -0.173 |
Fathers | -0.169 |
resolves | -0.168 |
DX | -0.168 |
cow | -0.165 |
Token | well |
Token ID | 880 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
DX | +0.021 |
Fathers | +0.021 |
DX | +0.021 |
resolves | +0.021 |
cow | +0.021 |
Neg logit contributions | |
�醒 | -0.027 |
olit | -0.025 |
ult | -0.025 |
sted | -0.024 |
adr | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
DX | +0.170 |
Fathers | +0.168 |
resolves | +0.166 |
DX | +0.166 |
cow | +0.164 |
Neg logit contributions | |
�醒 | -0.369 |
olit | -0.336 |
ult | -0.333 |
sted | -0.333 |
adr | -0.323 |
Token | but |
Token ID | 475 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
�醒 | +0.274 |
olit | +0.250 |
sted | +0.247 |
ult | +0.246 |
adr | +0.238 |
Neg logit contributions | |
DX | -0.136 |
Fathers | -0.136 |
resolves | -0.134 |
DX | -0.134 |
cow | -0.132 |
Token | was |
Token ID | 373 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
�醒 | +0.047 |
olit | +0.042 |
ult | +0.041 |
sted | +0.041 |
adr | +0.040 |
Neg logit contributions | |
Fathers | -0.030 |
DX | -0.030 |
resolves | -0.030 |
DX | -0.030 |
cow | -0.029 |
Token | drawn |
Token ID | 7428 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
�醒 | +0.027 |
olit | +0.024 |
ult | +0.024 |
sted | +0.024 |
adr | +0.023 |
Neg logit contributions | |
DX | -0.018 |
Fathers | -0.018 |
resolves | -0.017 |
DX | -0.017 |
cow | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Fathers | +0.950 |
cow | +0.950 |
DX | +0.943 |
DX | +0.943 |
resolves | +0.932 |
Neg logit contributions | |
�醒 | -2.305 |
ult | -2.100 |
olit | -2.096 |
sted | -2.088 |
adr | -2.043 |
Token | the |
Token ID | 262 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Fathers | +0.619 |
DX | +0.616 |
DX | +0.615 |
cow | +0.612 |
resolves | +0.610 |
Neg logit contributions | |
�醒 | -1.129 |
olit | -1.022 |
sted | -1.012 |
ult | -1.009 |
adr | -0.977 |
Token | speed |
Token ID | 2866 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
Fathers | +0.224 |
DX | +0.222 |
DX | +0.222 |
cow | +0.219 |
resolves | +0.217 |
Neg logit contributions | |
�醒 | -0.421 |
olit | -0.380 |
sted | -0.377 |
ult | -0.376 |
adr | -0.363 |
Token | and |
Token ID | 290 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
DX | +0.336 |
Fathers | +0.328 |
DX | +0.325 |
resolves | +0.324 |
cow | +0.321 |
Neg logit contributions | |
�醒 | -0.672 |
olit | -0.611 |
ult | -0.608 |
sted | -0.607 |
adr | -0.585 |
Token | physical |
Token ID | 3518 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
�醒 | +0.367 |
olit | +0.326 |
ult | +0.325 |
sted | +0.324 |
adr | +0.310 |
Neg logit contributions | |
DX | -0.260 |
Fathers | -0.258 |
resolves | -0.258 |
DX | -0.257 |
cow | -0.255 |
Token | cultural |
Token ID | 30844 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
DX | +0.307 |
Fathers | +0.299 |
resolves | +0.294 |
DX | +0.294 |
cow | +0.293 |
Neg logit contributions | |
�醒 | -0.341 |
olit | -0.299 |
sted | -0.298 |
ult | -0.295 |
adr | -0.283 |
Token | issues |
Token ID | 2428 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
�醒 | +1.006 |
olit | +0.941 |
ult | +0.938 |
sted | +0.936 |
adr | +0.913 |
Neg logit contributions | |
DX | -0.134 |
resolves | -0.125 |
Fathers | -0.124 |
DX | -0.123 |
cow | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
DX | +0.035 |
Fathers | +0.035 |
resolves | +0.034 |
cow | +0.034 |
DX | +0.034 |
Neg logit contributions | |
�醒 | -0.087 |
olit | -0.079 |
ult | -0.079 |
sted | -0.079 |
adr | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
Fathers | +0.139 |
DX | +0.134 |
DX | +0.134 |
Downs | +0.130 |
resolves | +0.130 |
Neg logit contributions | |
�醒 | -0.171 |
olit | -0.153 |
ult | -0.152 |
sted | -0.149 |
adr | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
�醒 | +0.048 |
olit | +0.042 |
ult | +0.042 |
sted | +0.042 |
adr | +0.040 |
Neg logit contributions | |
DX | -0.040 |
Fathers | -0.040 |
resolves | -0.039 |
DX | -0.039 |
cow | -0.039 |
Token | Update |
Token ID | 10260 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
DX | +0.124 |
Fathers | +0.118 |
DX | +0.116 |
resolves | +0.115 |
cow | +0.114 |
Neg logit contributions | |
�醒 | -0.139 |
olit | -0.122 |
sted | -0.119 |
ult | -0.119 |
adr | -0.114 |
Token | : |
Token ID | 25 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
DX | +1.095 |
DX | +1.091 |
resolves | +1.084 |
Fathers | +1.081 |
cow | +1.066 |
Neg logit contributions | |
�醒 | -2.093 |
ult | -1.880 |
olit | -1.862 |
sted | -1.857 |
adr | -1.811 |
Token | The |
Token ID | 383 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Fathers | +0.612 |
DX | +0.605 |
DX | +0.604 |
resolves | +0.596 |
cow | +0.594 |
Neg logit contributions | |
�醒 | -0.737 |
ult | -0.651 |
olit | -0.647 |
sted | -0.637 |
adr | -0.619 |
Token | Hill |
Token ID | 3327 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
Fathers | +0.237 |
DX | +0.235 |
DX | +0.234 |
cow | +0.234 |
resolves | +0.230 |
Neg logit contributions | |
�醒 | -0.322 |
olit | -0.287 |
ult | -0.284 |
sted | -0.282 |
adr | -0.273 |
Token | reports |
Token ID | 3136 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
�醒 | +0.767 |
ult | +0.688 |
olit | +0.688 |
sted | +0.678 |
adr | +0.655 |
Neg logit contributions | |
DX | -0.571 |
resolves | -0.566 |
Fathers | -0.564 |
DX | -0.558 |
cow | -0.550 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Fathers | +0.377 |
DX | +0.374 |
DX | +0.373 |
resolves | +0.368 |
cow | +0.366 |
Neg logit contributions | |
�醒 | -0.794 |
ult | -0.727 |
olit | -0.725 |
sted | -0.721 |
adr | -0.704 |
Token | all |
Token ID | 477 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
�醒 | +0.158 |
olit | +0.144 |
ult | +0.143 |
sted | +0.142 |
adr | +0.140 |
Neg logit contributions | |
DX | -0.077 |
DX | -0.075 |
resolves | -0.075 |
Fathers | -0.075 |
cow | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
DX | +0.070 |
resolves | +0.069 |
Fathers | +0.069 |
DX | +0.069 |
cow | +0.068 |
Neg logit contributions | |
�醒 | -0.167 |
sted | -0.153 |
olit | -0.152 |
ult | -0.152 |
adr | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
Fathers | +0.164 |
DX | +0.163 |
DX | +0.163 |
resolves | +0.159 |
Downs | +0.156 |
Neg logit contributions | |
�醒 | -0.208 |
olit | -0.186 |
ult | -0.185 |
sted | -0.182 |
adr | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
DX | +0.060 |
Fathers | +0.059 |
resolves | +0.059 |
DX | +0.059 |
cow | +0.058 |
Neg logit contributions | |
�醒 | -0.071 |
olit | -0.063 |
ult | -0.062 |
sted | -0.062 |
adr | -0.059 |
Token | ( |
Token ID | 7 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
DX | +0.126 |
DX | +0.116 |
Fathers | +0.115 |
resolves | +0.114 |
cow | +0.111 |
Neg logit contributions | |
�醒 | -0.209 |
olit | -0.190 |
ult | -0.185 |
sted | -0.185 |
adr | -0.178 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
�醒 | +0.337 |
olit | +0.301 |
ult | +0.298 |
sted | +0.297 |
adr | +0.285 |
Neg logit contributions | |
DX | -0.289 |
Fathers | -0.278 |
DX | -0.276 |
resolves | -0.275 |
cow | -0.269 |
Token | : |
Token ID | 25 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
DX | +1.135 |
DX | +1.134 |
resolves | +1.102 |
Fathers | +1.094 |
cow | +1.078 |
Neg logit contributions | |
�醒 | -2.053 |
ult | -1.852 |
olit | -1.852 |
sted | -1.841 |
adr | -1.772 |
Token | Sherman |
Token ID | 23198 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
DX | +0.690 |
DX | +0.685 |
Fathers | +0.685 |
resolves | +0.675 |
cow | +0.659 |
Neg logit contributions | |
�醒 | -0.911 |
olit | -0.808 |
ult | -0.805 |
sted | -0.798 |
adr | -0.773 |
Token | suffered |
Token ID | 6989 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
resolves | +0.409 |
DX | +0.401 |
DX | +0.401 |
Fathers | +0.400 |
cow | +0.397 |
Neg logit contributions | |
�醒 | -0.590 |
olit | -0.527 |
ult | -0.520 |
sted | -0.518 |
adr | -0.505 |
Token | a |
Token ID | 257 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
DX | +0.307 |
resolves | +0.305 |
DX | +0.304 |
Fathers | +0.303 |
cow | +0.301 |
Neg logit contributions | |
�醒 | -0.404 |
olit | -0.362 |
ult | -0.362 |
sted | -0.359 |
adr | -0.345 |
Token | rupt |
Token ID | 31580 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
DX | +0.102 |
DX | +0.101 |
Fathers | +0.100 |
resolves | +0.100 |
cow | +0.100 |
Neg logit contributions | |
�醒 | -0.163 |
ult | -0.148 |
olit | -0.148 |
sted | -0.147 |
adr | -0.141 |
Token | remarks |
Token ID | 10252 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Fathers | +0.130 |
cow | +0.128 |
DX | +0.128 |
DX | +0.127 |
changing | +0.126 |
Neg logit contributions | |
�醒 | -0.184 |
olit | -0.165 |
sted | -0.163 |
ult | -0.162 |
adr | -0.157 |
Token | he |
Token ID | 339 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Fathers | +0.098 |
DX | +0.097 |
resolves | +0.096 |
DX | +0.096 |
cow | +0.096 |
Neg logit contributions | |
�醒 | -0.211 |
olit | -0.191 |
sted | -0.190 |
ult | -0.190 |
adr | -0.185 |
Token | made |
Token ID | 925 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
DX | +0.444 |
resolves | +0.442 |
cow | +0.440 |
Fathers | +0.439 |
DX | +0.438 |
Neg logit contributions | |
�醒 | -0.838 |
olit | -0.756 |
sted | -0.750 |
ult | -0.749 |
adr | -0.724 |
Token | about |
Token ID | 546 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
Fathers | +0.525 |
DX | +0.524 |
resolves | +0.524 |
DX | +0.524 |
cow | +0.521 |
Neg logit contributions | |
�醒 | -1.056 |
olit | -0.946 |
sted | -0.937 |
ult | -0.934 |
adr | -0.920 |
Token | his |
Token ID | 465 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Fathers | +0.453 |
cow | +0.451 |
DX | +0.449 |
changing | +0.443 |
DX | +0.443 |
Neg logit contributions | |
�醒 | -0.623 |
olit | -0.562 |
ult | -0.556 |
sted | -0.551 |
adr | -0.535 |
Token | fellow |
Token ID | 5891 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Fathers | +0.106 |
cow | +0.103 |
DX | +0.103 |
resolves | +0.103 |
DX | +0.103 |
Neg logit contributions | |
�醒 | -0.155 |
olit | -0.139 |
ult | -0.137 |
sted | -0.137 |
adr | -0.132 |
Token | GOP |
Token ID | 6796 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Fathers | +1.168 |
cow | +1.138 |
DX | +1.114 |
resolves | +1.084 |
DX | +1.081 |
Neg logit contributions | |
�醒 | -2.019 |
olit | -1.832 |
ult | -1.800 |
sted | -1.781 |
adr | -1.747 |
Token | presidential |
Token ID | 4787 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
�醒 | +0.091 |
olit | +0.082 |
sted | +0.082 |
ult | +0.082 |
adr | +0.080 |
Neg logit contributions | |
Fathers | -0.057 |
cow | -0.057 |
DX | -0.057 |
resolves | -0.056 |
DX | -0.056 |
Token | contender |
Token ID | 24190 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
�醒 | +0.924 |
olit | +0.826 |
sted | +0.820 |
ult | +0.819 |
adr | +0.790 |
Neg logit contributions | |
Fathers | -0.694 |
cow | -0.687 |
resolves | -0.686 |
DX | -0.685 |
DX | -0.682 |
Token | in |
Token ID | 287 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
�醒 | +0.442 |
olit | +0.406 |
ult | +0.400 |
sted | +0.400 |
adr | +0.391 |
Neg logit contributions | |
DX | -0.230 |
Fathers | -0.229 |
DX | -0.226 |
resolves | -0.226 |
cow | -0.223 |
Token | a |
Token ID | 257 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
�醒 | +0.328 |
olit | +0.296 |
sted | +0.292 |
ult | +0.291 |
adr | +0.281 |
Neg logit contributions | |
DX | -0.227 |
Fathers | -0.227 |
DX | -0.226 |
resolves | -0.224 |
cow | -0.223 |
Token | Hulu |
Token ID | 39739 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
�醒 | +0.012 |
olit | +0.010 |
sted | +0.010 |
ult | +0.010 |
adr | +0.010 |
Neg logit contributions | |
DX | -0.017 |
DX | -0.017 |
Fathers | -0.017 |
resolves | -0.016 |
cow | -0.016 |
Token | Plus |
Token ID | 8227 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
�醒 | +0.672 |
ult | +0.616 |
olit | +0.615 |
sted | +0.612 |
adr | +0.588 |
Neg logit contributions | |
DX | -0.361 |
Fathers | -0.352 |
resolves | -0.350 |
DX | -0.347 |
cow | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
�醒 | +0.436 |
ult | +0.400 |
olit | +0.399 |
sted | +0.397 |
adr | +0.382 |
Neg logit contributions | |
DX | -0.225 |
Fathers | -0.219 |
resolves | -0.218 |
DX | -0.216 |
cow | -0.212 |
Token | and |
Token ID | 290 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
�醒 | +0.162 |
olit | +0.146 |
sted | +0.145 |
ult | +0.145 |
adr | +0.140 |
Neg logit contributions | |
DX | -0.095 |
Fathers | -0.095 |
DX | -0.094 |
resolves | -0.093 |
cow | -0.091 |
Token | Amazon |
Token ID | 6186 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
�醒 | +0.477 |
olit | +0.424 |
ult | +0.422 |
sted | +0.421 |
adr | +0.406 |
Neg logit contributions | |
DX | -0.353 |
Fathers | -0.351 |
DX | -0.350 |
resolves | -0.347 |
cow | -0.342 |
Token | Prime |
Token ID | 5537 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
DX | +0.451 |
resolves | +0.444 |
DX | +0.441 |
Fathers | +0.441 |
cow | +0.434 |
Neg logit contributions | |
�醒 | -0.558 |
olit | -0.499 |
ult | -0.491 |
sted | -0.487 |
adr | -0.476 |
Token | offer |
Token ID | 2897 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
DX | +1.377 |
DX | +1.366 |
Fathers | +1.349 |
resolves | +1.346 |
cow | +1.336 |
Neg logit contributions | |
�醒 | -1.827 |
olit | -1.603 |
ult | -1.581 |
sted | -1.572 |
adr | -1.553 |
Token | much |
Token ID | 881 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
DX | +0.048 |
DX | +0.048 |
resolves | +0.048 |
Fathers | +0.048 |
cow | +0.047 |
Neg logit contributions | |
�醒 | -0.078 |
olit | -0.070 |
ult | -0.070 |
sted | -0.069 |
adr | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
DX | +0.039 |
Fathers | +0.038 |
DX | +0.038 |
resolves | +0.038 |
cow | +0.037 |
Neg logit contributions | |
�醒 | -0.094 |
ult | -0.086 |
olit | -0.085 |
sted | -0.085 |
adr | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
�醒 | +0.632 |
olit | +0.574 |
ult | +0.571 |
sted | +0.568 |
adr | +0.553 |
Neg logit contributions | |
DX | -0.325 |
DX | -0.319 |
Fathers | -0.316 |
resolves | -0.313 |
cow | -0.310 |
Token | same |
Token ID | 976 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
DX | +0.046 |
DX | +0.046 |
Fathers | +0.046 |
resolves | +0.045 |
cow | +0.045 |
Neg logit contributions | |
�醒 | -0.067 |
olit | -0.060 |
ult | -0.059 |
sted | -0.059 |
adr | -0.056 |
Token | be |
Token ID | 307 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
cow | +0.295 |
Fathers | +0.294 |
DX | +0.292 |
resolves | +0.292 |
DX | +0.289 |
Neg logit contributions | |
�醒 | -0.368 |
olit | -0.328 |
ult | -0.324 |
sted | -0.323 |
adr | -0.310 |
Token | able |
Token ID | 1498 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
�醒 | +0.342 |
olit | +0.306 |
ult | +0.305 |
sted | +0.300 |
adr | +0.289 |
Neg logit contributions | |
Fathers | -0.260 |
DX | -0.260 |
cow | -0.259 |
resolves | -0.258 |
DX | -0.258 |
Token | to |
Token ID | 284 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
DX | +0.330 |
Fathers | +0.329 |
resolves | +0.326 |
cow | +0.323 |
DX | +0.322 |
Neg logit contributions | |
�醒 | -0.778 |
ult | -0.701 |
olit | -0.700 |
sted | -0.694 |
adr | -0.672 |
Token | get |
Token ID | 651 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
cow | +0.254 |
DX | +0.254 |
Fathers | +0.254 |
resolves | +0.253 |
DX | +0.251 |
Neg logit contributions | |
�醒 | -0.289 |
olit | -0.257 |
ult | -0.255 |
sted | -0.253 |
adr | -0.242 |
Token | green |
Token ID | 4077 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Fathers | +0.271 |
DX | +0.267 |
DX | +0.266 |
cow | +0.265 |
resolves | +0.265 |
Neg logit contributions | |
�醒 | -0.404 |
olit | -0.366 |
ult | -0.364 |
sted | -0.358 |
adr | -0.348 |
Token | cards |
Token ID | 4116 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Fathers | +0.054 |
cow | +0.053 |
DX | +0.052 |
resolves | +0.052 |
DX | +0.052 |
Neg logit contributions | |
�醒 | -0.209 |
olit | -0.196 |
ult | -0.195 |
sted | -0.193 |
adr | -0.189 |
Token | for |
Token ID | 329 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
resolves | +0.989 |
Fathers | +0.989 |
cow | +0.979 |
DX | +0.976 |
DX | +0.971 |
Neg logit contributions | |
�醒 | -2.134 |
olit | -1.922 |
ult | -1.912 |
sted | -1.895 |
adr | -1.852 |
Token | their |
Token ID | 511 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Fathers | +0.486 |
resolves | +0.478 |
cow | +0.476 |
DX | +0.475 |
DX | +0.475 |
Neg logit contributions | |
�醒 | -0.822 |
olit | -0.738 |
ult | -0.732 |
sted | -0.722 |
adr | -0.705 |
Token | spouses |
Token ID | 30250 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Fathers | +0.229 |
resolves | +0.224 |
DX | +0.223 |
DX | +0.222 |
cow | +0.222 |
Neg logit contributions | |
�醒 | -0.492 |
olit | -0.442 |
ult | -0.442 |
sted | -0.439 |
adr | -0.426 |
Token | and |
Token ID | 290 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Fathers | +0.076 |
resolves | +0.075 |
DX | +0.075 |
cow | +0.075 |
DX | +0.074 |
Neg logit contributions | |
�醒 | -0.179 |
olit | -0.162 |
ult | -0.161 |
sted | -0.160 |
adr | -0.156 |
Token | minor |
Token ID | 4159 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
�醒 | +0.268 |
ult | +0.241 |
olit | +0.239 |
sted | +0.239 |
adr | +0.233 |
Neg logit contributions | |
Fathers | -0.108 |
resolves | -0.107 |
DX | -0.105 |
cow | -0.105 |
DX | -0.104 |
Token | to |
Token ID | 1462 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
DX | +0.053 |
Fathers | +0.051 |
DX | +0.051 |
resolves | +0.051 |
cow | +0.049 |
Neg logit contributions | |
�醒 | -0.131 |
olit | -0.120 |
ult | -0.119 |
sted | -0.118 |
adr | -0.116 |
Token | - |
Token ID | 12 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
�醒 | +0.571 |
ult | +0.517 |
olit | +0.517 |
sted | +0.513 |
adr | +0.492 |
Neg logit contributions | |
DX | -0.408 |
Fathers | -0.399 |
resolves | -0.397 |
DX | -0.395 |
cow | -0.389 |
Token | female |
Token ID | 24724 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
�醒 | +0.486 |
olit | +0.434 |
ult | +0.432 |
sted | +0.431 |
adr | +0.412 |
Neg logit contributions | |
DX | -0.418 |
Fathers | -0.408 |
resolves | -0.405 |
DX | -0.405 |
cow | -0.399 |
Token | ( |
Token ID | 357 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
DX | +0.536 |
resolves | +0.534 |
DX | +0.530 |
Fathers | +0.530 |
cow | +0.514 |
Neg logit contributions | |
�醒 | -0.831 |
olit | -0.746 |
ult | -0.740 |
sted | -0.735 |
adr | -0.718 |
Token | M |
Token ID | 44 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
DX | +0.141 |
Fathers | +0.136 |
DX | +0.134 |
resolves | +0.133 |
cow | +0.130 |
Neg logit contributions | |
�醒 | -0.158 |
olit | -0.141 |
sted | -0.141 |
ult | -0.139 |
adr | -0.133 |
Token | TF |
Token ID | 10234 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
DX | +0.688 |
DX | +0.664 |
Fathers | +0.661 |
resolves | +0.659 |
cow | +0.644 |
Neg logit contributions | |
�醒 | -0.708 |
olit | -0.608 |
sted | -0.608 |
ult | -0.607 |
adr | -0.576 |
Token | ) |
Token ID | 8 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
DX | +0.957 |
DX | +0.918 |
Fathers | +0.917 |
resolves | +0.914 |
cow | +0.889 |
Neg logit contributions | |
�醒 | -2.132 |
ult | -1.950 |
olit | -1.950 |
sted | -1.939 |
adr | -1.875 |
Token | transgender |
Token ID | 10637 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
DX | +0.045 |
resolves | +0.044 |
Fathers | +0.044 |
DX | +0.044 |
cow | +0.043 |
Neg logit contributions | |
�醒 | -0.064 |
olit | -0.057 |
ult | -0.057 |
sted | -0.057 |
adr | -0.055 |
Token | people |
Token ID | 661 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
DX | +0.400 |
Fathers | +0.391 |
resolves | +0.390 |
DX | +0.390 |
cow | +0.378 |
Neg logit contributions | |
�醒 | -0.893 |
ult | -0.813 |
olit | -0.811 |
sted | -0.806 |
adr | -0.788 |
Token | are |
Token ID | 389 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
DX | +0.149 |
resolves | +0.148 |
Fathers | +0.148 |
DX | +0.146 |
cow | +0.145 |
Neg logit contributions | |
�醒 | -0.194 |
ult | -0.172 |
olit | -0.171 |
sted | -0.171 |
adr | -0.164 |
Token | born |
Token ID | 4642 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
DX | +0.452 |
Fathers | +0.450 |
DX | +0.448 |
resolves | +0.445 |
cow | +0.440 |
Neg logit contributions | |
�醒 | -0.548 |
ult | -0.479 |
olit | -0.476 |
sted | -0.472 |
adr | -0.457 |
Token | that |
Token ID | 326 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Fathers | +0.065 |
DX | +0.065 |
DX | +0.064 |
resolves | +0.064 |
cow | +0.063 |
Neg logit contributions | |
�醒 | -0.111 |
olit | -0.100 |
ult | -0.099 |
sted | -0.099 |
adr | -0.096 |
Token | � |
Token ID | 564 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
�醒 | +0.245 |
olit | +0.222 |
sted | +0.219 |
ult | +0.218 |
adr | +0.212 |
Neg logit contributions | |
DX | -0.144 |
Fathers | -0.142 |
DX | -0.142 |
resolves | -0.140 |
cow | -0.139 |
Token | � |
Token ID | 250 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
DX | +0.543 |
DX | +0.530 |
Fathers | +0.529 |
resolves | +0.524 |
cow | +0.523 |
Neg logit contributions | |
�醒 | -0.541 |
olit | -0.495 |
sted | -0.494 |
ult | -0.493 |
adr | -0.465 |
Token | Tal |
Token ID | 31466 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
DX | +0.009 |
DX | +0.009 |
Fathers | +0.009 |
resolves | +0.009 |
cow | +0.009 |
Neg logit contributions | |
�醒 | -0.011 |
olit | -0.009 |
sted | -0.009 |
ult | -0.009 |
adr | -0.009 |
Token | ent |
Token ID | 298 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
DX | +0.107 |
DX | +0.105 |
Fathers | +0.105 |
resolves | +0.103 |
cow | +0.102 |
Neg logit contributions | |
�醒 | -0.115 |
olit | -0.100 |
ult | -0.100 |
sted | -0.099 |
adr | -0.094 |
Token | hits |
Token ID | 7127 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
DX | +0.474 |
Fathers | +0.458 |
resolves | +0.458 |
DX | +0.457 |
cow | +0.449 |
Neg logit contributions | |
�醒 | -0.615 |
olit | -0.546 |
ult | -0.544 |
sted | -0.538 |
adr | -0.520 |
Token | a |
Token ID | 257 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
DX | +1.183 |
cow | +1.173 |
DX | +1.171 |
resolves | +1.159 |
Fathers | +1.153 |
Neg logit contributions | |
�醒 | -1.930 |
olit | -1.698 |
ult | -1.670 |
sted | -1.654 |
adr | -1.624 |
Token | target |
Token ID | 2496 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
DX | +0.164 |
Fathers | +0.162 |
DX | +0.162 |
cow | +0.162 |
resolves | +0.159 |
Neg logit contributions | |
�醒 | -0.249 |
olit | -0.225 |
ult | -0.225 |
sted | -0.220 |
adr | -0.213 |
Token | no |
Token ID | 645 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
DX | +0.269 |
DX | +0.263 |
cow | +0.259 |
resolves | +0.258 |
Fathers | +0.257 |
Neg logit contributions | |
�醒 | -0.448 |
olit | -0.405 |
ult | -0.404 |
sted | -0.397 |
adr | -0.387 |
Token | one |
Token ID | 530 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
DX | +0.051 |
DX | +0.050 |
cow | +0.050 |
resolves | +0.049 |
Fathers | +0.049 |
Neg logit contributions | |
�醒 | -0.067 |
olit | -0.061 |
sted | -0.061 |
ult | -0.060 |
adr | -0.058 |
Token | else |
Token ID | 2073 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
resolves | +0.358 |
Fathers | +0.351 |
DX | +0.348 |
cow | +0.347 |
DX | +0.346 |
Neg logit contributions | |
�醒 | -0.559 |
olit | -0.493 |
ult | -0.491 |
sted | -0.487 |
adr | -0.468 |
Token | at |
Token ID | 379 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
�醒 | +0.729 |
ult | +0.660 |
olit | +0.659 |
sted | +0.654 |
adr | +0.632 |
Neg logit contributions | |
DX | -0.391 |
resolves | -0.383 |
Fathers | -0.382 |
DX | -0.381 |
cow | -0.376 |
Token | 2 |
Token ID | 362 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
DX | +0.089 |
DX | +0.088 |
Fathers | +0.088 |
resolves | +0.088 |
cow | +0.087 |
Neg logit contributions | |
�醒 | -0.168 |
ult | -0.152 |
olit | -0.152 |
sted | -0.149 |
adr | -0.147 |
Token | : |
Token ID | 25 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
�醒 | +0.028 |
olit | +0.025 |
ult | +0.025 |
sted | +0.025 |
adr | +0.024 |
Neg logit contributions | |
DX | -0.017 |
resolves | -0.016 |
Fathers | -0.016 |
DX | -0.016 |
cow | -0.016 |
Token | 21 |
Token ID | 2481 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
�醒 | +0.048 |
olit | +0.042 |
ult | +0.041 |
sted | +0.041 |
adr | +0.039 |
Neg logit contributions | |
DX | -0.040 |
Fathers | -0.039 |
DX | -0.039 |
resolves | -0.039 |
cow | -0.038 |
Token | ? |
Token ID | 30 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
�醒 | +0.060 |
olit | +0.055 |
ult | +0.055 |
sted | +0.054 |
adr | +0.052 |
Neg logit contributions | |
DX | -0.031 |
resolves | -0.030 |
DX | -0.030 |
Fathers | -0.029 |
cow | -0.029 |
Token | Depending |
Token ID | 23591 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
DX | +0.400 |
Fathers | +0.391 |
DX | +0.391 |
resolves | +0.389 |
cow | +0.382 |
Neg logit contributions | |
�醒 | -0.474 |
olit | -0.423 |
ult | -0.417 |
sted | -0.417 |
adr | -0.395 |
Token | on |
Token ID | 319 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
DX | +1.049 |
resolves | +1.019 |
DX | +1.008 |
cow | +1.005 |
Fathers | +1.002 |
Neg logit contributions | |
�醒 | -2.011 |
olit | -1.815 |
ult | -1.795 |
sted | -1.793 |
adr | -1.727 |
Token | where |
Token ID | 810 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
DX | +0.101 |
DX | +0.099 |
Fathers | +0.099 |
resolves | +0.099 |
cow | +0.096 |
Neg logit contributions | |
�醒 | -0.186 |
olit | -0.168 |
ult | -0.167 |
sted | -0.165 |
adr | -0.160 |
Token | the |
Token ID | 262 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
DX | +0.152 |
DX | +0.148 |
Fathers | +0.148 |
resolves | +0.148 |
cow | +0.145 |
Neg logit contributions | |
�醒 | -0.306 |
olit | -0.276 |
ult | -0.275 |
sted | -0.274 |
adr | -0.264 |
Token | diss |
Token ID | 6249 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
DX | +0.324 |
resolves | +0.322 |
Fathers | +0.321 |
DX | +0.320 |
cow | +0.318 |
Neg logit contributions | |
�醒 | -0.518 |
olit | -0.466 |
ult | -0.465 |
sted | -0.461 |
adr | -0.443 |
Token | ents |
Token ID | 658 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
DX | +0.545 |
resolves | +0.542 |
Fathers | +0.538 |
DX | +0.525 |
cow | +0.522 |
Neg logit contributions | |
�醒 | -0.671 |
sted | -0.591 |
olit | -0.582 |
ult | -0.571 |
adr | -0.560 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
DX | +0.165 |
DX | +0.161 |
Fathers | +0.159 |
resolves | +0.158 |
cow | +0.156 |
Neg logit contributions | |
�醒 | -0.394 |
olit | -0.362 |
ult | -0.360 |
sted | -0.358 |
adr | -0.346 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
DX | +0.200 |
DX | +0.198 |
Fathers | +0.198 |
resolves | +0.192 |
cow | +0.190 |
Neg logit contributions | |
�醒 | -0.244 |
olit | -0.216 |
ult | -0.214 |
sted | -0.211 |
adr | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
�醒 | +0.168 |
olit | +0.150 |
ult | +0.149 |
sted | +0.148 |
adr | +0.143 |
Neg logit contributions | |
DX | -0.114 |
DX | -0.112 |
Fathers | -0.111 |
resolves | -0.111 |
cow | -0.109 |
Token | groups |
Token ID | 2628 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
DX | +0.149 |
Fathers | +0.147 |
DX | +0.146 |
resolves | +0.145 |
cow | +0.144 |
Neg logit contributions | |
�醒 | -0.238 |
olit | -0.213 |
sted | -0.212 |
ult | -0.211 |
adr | -0.203 |
Token | were |
Token ID | 547 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
�醒 | +0.157 |
olit | +0.141 |
ult | +0.141 |
sted | +0.140 |
adr | +0.135 |
Neg logit contributions | |
DX | -0.094 |
DX | -0.093 |
Fathers | -0.092 |
resolves | -0.091 |
cow | -0.091 |
Token | drawn |
Token ID | 7428 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
DX | +0.210 |
resolves | +0.206 |
Fathers | +0.206 |
DX | +0.205 |
cow | +0.202 |
Neg logit contributions | |
�醒 | -0.383 |
ult | -0.349 |
olit | -0.348 |
sted | -0.345 |
adr | -0.333 |
Token | , |
Token ID | 11 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
DX | +0.942 |
DX | +0.937 |
resolves | +0.933 |
Fathers | +0.919 |
cow | +0.910 |
Neg logit contributions | |
�醒 | -2.117 |
olit | -1.905 |
ult | -1.901 |
sted | -1.872 |
adr | -1.839 |
Token | and |
Token ID | 290 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
DX | +0.170 |
DX | +0.167 |
Fathers | +0.166 |
resolves | +0.166 |
cow | +0.161 |
Neg logit contributions | |
�醒 | -0.350 |
olit | -0.318 |
ult | -0.317 |
sted | -0.315 |
adr | -0.304 |
Token | it |
Token ID | 340 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
DX | +0.236 |
DX | +0.235 |
Fathers | +0.232 |
resolves | +0.230 |
cow | +0.228 |
Neg logit contributions | |
�醒 | -0.369 |
olit | -0.329 |
ult | -0.327 |
sted | -0.324 |
adr | -0.311 |
Token | got |
Token ID | 1392 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
�醒 | +0.067 |
olit | +0.060 |
ult | +0.058 |
sted | +0.058 |
adr | +0.057 |
Neg logit contributions | |
resolves | -0.052 |
DX | -0.051 |
cow | -0.051 |
Fathers | -0.051 |
DX | -0.050 |
Token | way |
Token ID | 835 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
�醒 | +0.603 |
ult | +0.545 |
olit | +0.545 |
sted | +0.540 |
adr | +0.522 |
Neg logit contributions | |
DX | -0.392 |
Fathers | -0.384 |
resolves | -0.382 |
DX | -0.382 |
cow | -0.375 |
Token | who |
Token ID | 508 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
�醒 | +0.183 |
olit | +0.163 |
ult | +0.162 |
sted | +0.162 |
adr | +0.156 |
Neg logit contributions | |
Fathers | -0.129 |
DX | -0.129 |
resolves | -0.128 |
DX | -0.128 |
cow | -0.127 |
Token | played |
Token ID | 2826 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
resolves | +0.063 |
Fathers | +0.062 |
DX | +0.062 |
cow | +0.062 |
DX | +0.061 |
Neg logit contributions | |
�醒 | -0.090 |
olit | -0.080 |
sted | -0.079 |
ult | -0.079 |
adr | -0.076 |
Token | behind |
Token ID | 2157 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
�醒 | +0.050 |
ult | +0.045 |
olit | +0.045 |
sted | +0.045 |
adr | +0.044 |
Neg logit contributions | |
DX | -0.029 |
DX | -0.028 |
resolves | -0.028 |
Fathers | -0.028 |
cow | -0.028 |
Token | Hall |
Token ID | 4789 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
DX | +0.196 |
DX | +0.195 |
Fathers | +0.194 |
resolves | +0.193 |
cow | +0.192 |
Neg logit contributions | |
�醒 | -0.274 |
olit | -0.247 |
ult | -0.246 |
sted | -0.245 |
adr | -0.236 |
Token | on |
Token ID | 319 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
�醒 | +1.013 |
olit | +0.919 |
ult | +0.918 |
sted | +0.910 |
adr | +0.886 |
Neg logit contributions | |
DX | -0.479 |
Fathers | -0.472 |
DX | -0.467 |
resolves | -0.464 |
cow | -0.463 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
�醒 | +0.345 |
olit | +0.312 |
ult | +0.311 |
sted | +0.309 |
adr | +0.301 |
Neg logit contributions | |
DX | -0.195 |
Fathers | -0.192 |
DX | -0.192 |
resolves | -0.189 |
cow | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
�醒 | +1.338 |
olit | +1.223 |
ult | +1.218 |
sted | +1.216 |
adr | +1.175 |
Neg logit contributions | |
DX | -0.663 |
Fathers | -0.649 |
resolves | -0.645 |
DX | -0.643 |
cow | -0.633 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
�醒 | +0.239 |
olit | +0.210 |
ult | +0.209 |
sted | +0.208 |
adr | +0.201 |
Neg logit contributions | |
resolves | -0.182 |
Fathers | -0.180 |
DX | -0.180 |
DX | -0.179 |
cow | -0.178 |
Token | � |
Token ID | 447 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
�醒 | +0.275 |
olit | +0.225 |
ult | +0.222 |
sted | +0.220 |
adr | +0.207 |
Neg logit contributions | |
DX | -0.448 |
Fathers | -0.444 |
resolves | -0.440 |
DX | -0.439 |
cow | -0.435 |
Token | � |
Token ID | 247 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
�醒 | +0.266 |
olit | +0.230 |
sted | +0.228 |
ult | +0.228 |
adr | +0.212 |
Neg logit contributions | |
DX | -0.389 |
Fathers | -0.384 |
resolves | -0.382 |
DX | -0.380 |
cow | -0.377 |
Token | t |
Token ID | 83 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
�醒 | +0.416 |
olit | +0.369 |
ult | +0.366 |
sted | +0.364 |
adr | +0.350 |
Neg logit contributions | |
DX | -0.332 |
Fathers | -0.325 |
resolves | -0.324 |
DX | -0.321 |
cow | -0.317 |
Token | their |
Token ID | 511 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
DX | +0.066 |
resolves | +0.064 |
DX | +0.064 |
Fathers | +0.064 |
cow | +0.063 |
Neg logit contributions | |
�醒 | -0.115 |
olit | -0.104 |
ult | -0.104 |
sted | -0.103 |
adr | -0.100 |
Token | final |
Token ID | 2457 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
�醒 | +0.130 |
ult | +0.117 |
olit | +0.117 |
sted | +0.116 |
adr | +0.112 |
Neg logit contributions | |
DX | -0.084 |
Fathers | -0.083 |
resolves | -0.083 |
DX | -0.083 |
cow | -0.081 |
Token | game |
Token ID | 983 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
DX | +0.193 |
DX | +0.191 |
resolves | +0.190 |
Fathers | +0.190 |
cow | +0.188 |
Neg logit contributions | |
�醒 | -0.360 |
olit | -0.328 |
ult | -0.327 |
sted | -0.325 |
adr | -0.314 |
Token | against |
Token ID | 1028 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
DX | +0.060 |
resolves | +0.060 |
DX | +0.060 |
Fathers | +0.059 |
cow | +0.059 |
Neg logit contributions | |
�醒 | -0.129 |
olit | -0.117 |
ult | -0.117 |
sted | -0.116 |
adr | -0.113 |
Token | Saudi |
Token ID | 7420 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
�醒 | +0.570 |
olit | +0.512 |
ult | +0.509 |
sted | +0.506 |
adr | +0.486 |
Neg logit contributions | |
DX | -0.363 |
Fathers | -0.359 |
DX | -0.359 |
resolves | -0.357 |
cow | -0.352 |
Token | Arabia |
Token ID | 9671 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
�醒 | +0.380 |
olit | +0.354 |
ult | +0.351 |
sted | +0.349 |
adr | +0.339 |
Neg logit contributions | |
DX | -0.115 |
resolves | -0.112 |
Fathers | -0.111 |
DX | -0.111 |
cow | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
�醒 | +1.384 |
olit | +1.265 |
ult | +1.264 |
sted | +1.258 |
adr | +1.214 |
Neg logit contributions | |
DX | -0.677 |
Fathers | -0.662 |
resolves | -0.660 |
DX | -0.655 |
cow | -0.643 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
�醒 | +0.045 |
olit | +0.040 |
ult | +0.039 |
sted | +0.039 |
adr | +0.037 |
Neg logit contributions | |
DX | -0.036 |
Fathers | -0.036 |
DX | -0.036 |
resolves | -0.036 |
cow | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
�醒 | +0.275 |
olit | +0.244 |
ult | +0.244 |
sted | +0.242 |
adr | +0.231 |
Neg logit contributions | |
DX | -0.242 |
Fathers | -0.238 |
resolves | -0.236 |
DX | -0.236 |
cow | -0.232 |
Token | If |
Token ID | 1532 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
�醒 | +0.050 |
olit | +0.044 |
sted | +0.043 |
ult | +0.043 |
adr | +0.041 |
Neg logit contributions | |
DX | -0.042 |
Fathers | -0.040 |
DX | -0.040 |
resolves | -0.040 |
cow | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
DX | +0.328 |
resolves | +0.325 |
DX | +0.324 |
Fathers | +0.323 |
cow | +0.318 |
Neg logit contributions | |
�醒 | -0.541 |
olit | -0.487 |
ult | -0.483 |
sted | -0.481 |
adr | -0.467 |
Token | President |
Token ID | 1992 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Fathers | +0.020 |
DX | +0.020 |
resolves | +0.020 |
DX | +0.020 |
cow | +0.019 |
Neg logit contributions | |
�醒 | -0.028 |
olit | -0.025 |
ult | -0.025 |
sted | -0.025 |
adr | -0.024 |
Token | Men |
Token ID | 6065 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Fathers | +0.226 |
DX | +0.224 |
resolves | +0.224 |
DX | +0.222 |
cow | +0.220 |
Neg logit contributions | |
�醒 | -0.244 |
olit | -0.210 |
sted | -0.210 |
ult | -0.209 |
adr | -0.202 |
Token | em |
Token ID | 368 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
�醒 | +0.191 |
ult | +0.159 |
sted | +0.157 |
olit | +0.156 |
adr | +0.148 |
Neg logit contributions | |
DX | -0.242 |
Fathers | -0.242 |
resolves | -0.239 |
cow | -0.239 |
DX | -0.238 |
Token | ( |
Token ID | 357 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
�醒 | +0.266 |
ult | +0.234 |
sted | +0.233 |
olit | +0.233 |
adr | +0.223 |
Neg logit contributions | |
DX | -0.174 |
resolves | -0.173 |
DX | -0.172 |
Fathers | -0.170 |
cow | -0.170 |
Token | 1989 |
Token ID | 25475 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
�醒 | +0.028 |
olit | +0.024 |
sted | +0.024 |
ult | +0.024 |
adr | +0.023 |
Neg logit contributions | |
DX | -0.026 |
Fathers | -0.025 |
DX | -0.025 |
resolves | -0.025 |
cow | -0.025 |
Token | – |
Token ID | 1906 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
�醒 | +0.500 |
olit | +0.455 |
ult | +0.453 |
sted | +0.450 |
adr | +0.436 |
Neg logit contributions | |
DX | -0.249 |
Fathers | -0.242 |
DX | -0.242 |
resolves | -0.241 |
cow | -0.237 |
Token | 99 |
Token ID | 2079 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
�醒 | +1.056 |
olit | +0.934 |
ult | +0.930 |
sted | +0.926 |
adr | +0.884 |
Neg logit contributions | |
DX | -0.871 |
Fathers | -0.847 |
resolves | -0.843 |
DX | -0.841 |
cow | -0.828 |
Token | ) |
Token ID | 8 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
�醒 | +0.623 |
ult | +0.568 |
olit | +0.568 |
sted | +0.564 |
adr | +0.546 |
Neg logit contributions | |
DX | -0.288 |
Fathers | -0.280 |
DX | -0.279 |
resolves | -0.278 |
cow | -0.273 |
Token | turned |
Token ID | 2900 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
�醒 | +0.700 |
olit | +0.621 |
ult | +0.617 |
sted | +0.613 |
adr | +0.592 |
Neg logit contributions | |
resolves | -0.482 |
DX | -0.481 |
Fathers | -0.481 |
DX | -0.475 |
cow | -0.472 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
�醒 | +0.352 |
olit | +0.317 |
ult | +0.315 |
sted | +0.312 |
adr | +0.305 |
Neg logit contributions | |
DX | -0.218 |
Fathers | -0.217 |
resolves | -0.215 |
cow | -0.215 |
DX | -0.215 |
Token | a |
Token ID | 257 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Fathers | +0.070 |
DX | +0.070 |
DX | +0.069 |
resolves | +0.069 |
cow | +0.069 |
Neg logit contributions | |
�醒 | -0.111 |
olit | -0.100 |
ult | -0.099 |
sted | -0.098 |
adr | -0.095 |
Token | One |
Token ID | 1881 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
DX | +0.095 |
Fathers | +0.094 |
DX | +0.094 |
resolves | +0.092 |
cow | +0.091 |
Neg logit contributions | |
�醒 | -0.118 |
olit | -0.105 |
ult | -0.104 |
sted | -0.103 |
adr | -0.099 |
Token | photo |
Token ID | 4590 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
�醒 | +0.170 |
olit | +0.154 |
ult | +0.153 |
sted | +0.152 |
adr | +0.148 |
Neg logit contributions | |
DX | -0.093 |
resolves | -0.092 |
DX | -0.091 |
Fathers | -0.091 |
cow | -0.090 |
Token | shows |
Token ID | 2523 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
DX | +0.342 |
resolves | +0.342 |
DX | +0.338 |
Fathers | +0.337 |
cow | +0.331 |
Neg logit contributions | |
�醒 | -0.579 |
olit | -0.523 |
sted | -0.516 |
ult | -0.515 |
adr | -0.499 |
Token | Be |
Token ID | 1355 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
DX | +0.173 |
DX | +0.171 |
Fathers | +0.171 |
cow | +0.169 |
resolves | +0.168 |
Neg logit contributions | |
�醒 | -0.247 |
olit | -0.223 |
ult | -0.220 |
sted | -0.219 |
adr | -0.211 |
Token | b |
Token ID | 65 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
�醒 | +0.619 |
olit | +0.535 |
ult | +0.527 |
sted | +0.524 |
adr | +0.500 |
Neg logit contributions | |
DX | -0.572 |
Fathers | -0.562 |
DX | -0.558 |
resolves | -0.557 |
cow | -0.555 |
Token | op |
Token ID | 404 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
�醒 | +0.553 |
olit | +0.481 |
ult | +0.480 |
sted | +0.475 |
adr | +0.457 |
Neg logit contributions | |
DX | -0.533 |
Fathers | -0.530 |
DX | -0.526 |
resolves | -0.523 |
cow | -0.521 |
Token | and |
Token ID | 290 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
�醒 | +1.370 |
olit | +1.238 |
ult | +1.232 |
sted | +1.226 |
adr | +1.188 |
Neg logit contributions | |
DX | -0.812 |
Fathers | -0.790 |
DX | -0.788 |
resolves | -0.783 |
cow | -0.777 |
Token | Rock |
Token ID | 4631 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
�醒 | +0.321 |
olit | +0.287 |
ult | +0.285 |
sted | +0.284 |
adr | +0.274 |
Neg logit contributions | |
DX | -0.226 |
Fathers | -0.225 |
DX | -0.224 |
resolves | -0.221 |
cow | -0.221 |
Token | stead |
Token ID | 28044 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
�醒 | +0.342 |
olit | +0.294 |
ult | +0.292 |
sted | +0.286 |
adr | +0.280 |
Neg logit contributions | |
DX | -0.316 |
Fathers | -0.311 |
resolves | -0.309 |
DX | -0.308 |
cow | -0.307 |
Token | y |
Token ID | 88 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
�醒 | +0.247 |
olit | +0.218 |
ult | +0.213 |
sted | +0.213 |
adr | +0.207 |
Neg logit contributions | |
DX | -0.202 |
DX | -0.199 |
Fathers | -0.199 |
cow | -0.198 |
resolves | -0.198 |
Token | � |
Token ID | 447 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
DX | +0.338 |
Fathers | +0.333 |
DX | +0.332 |
cow | +0.332 |
resolves | +0.328 |
Neg logit contributions | |
�醒 | -0.587 |
olit | -0.527 |
ult | -0.520 |
sted | -0.517 |
adr | -0.501 |
Token | : |
Token ID | 25 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
�醒 | +0.229 |
olit | +0.205 |
ult | +0.204 |
sted | +0.203 |
adr | +0.196 |
Neg logit contributions | |
DX | -0.141 |
Fathers | -0.138 |
DX | -0.137 |
resolves | -0.137 |
cow | -0.134 |
Token | [/ |
Token ID | 13412 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
�醒 | +1.145 |
ult | +1.026 |
olit | +1.026 |
sted | +1.019 |
adr | +0.973 |
Neg logit contributions | |
DX | -0.950 |
Fathers | -0.932 |
resolves | -0.928 |
DX | -0.924 |
cow | -0.910 |
Token | b |
Token ID | 65 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
DX | +0.529 |
Fathers | +0.516 |
resolves | +0.515 |
DX | +0.513 |
cow | +0.507 |
Neg logit contributions | |
�醒 | -0.473 |
olit | -0.402 |
ult | -0.400 |
sted | -0.397 |
adr | -0.375 |
Token | ] |
Token ID | 60 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
�醒 | +0.472 |
olit | +0.430 |
ult | +0.429 |
sted | +0.426 |
adr | +0.412 |
Neg logit contributions | |
DX | -0.219 |
Fathers | -0.213 |
resolves | -0.211 |
DX | -0.210 |
cow | -0.205 |
Token | 00 |
Token ID | 3571 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
�醒 | +0.760 |
olit | +0.681 |
ult | +0.678 |
sted | +0.675 |
adr | +0.653 |
Neg logit contributions | |
DX | -0.405 |
DX | -0.398 |
Fathers | -0.397 |
resolves | -0.393 |
cow | -0.385 |
Token | : |
Token ID | 25 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
�醒 | +0.599 |
olit | +0.542 |
ult | +0.542 |
sted | +0.538 |
adr | +0.517 |
Neg logit contributions | |
DX | -0.394 |
Fathers | -0.385 |
resolves | -0.384 |
DX | -0.382 |
cow | -0.375 |
Token | 47 |
Token ID | 2857 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
�醒 | +1.127 |
olit | +0.991 |
ult | +0.991 |
sted | +0.982 |
adr | +0.931 |
Neg logit contributions | |
DX | -1.249 |
Fathers | -1.228 |
resolves | -1.223 |
DX | -1.218 |
cow | -1.202 |
Token | : |
Token ID | 25 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
�醒 | +0.068 |
ult | +0.062 |
olit | +0.062 |
sted | +0.062 |
adr | +0.059 |
Neg logit contributions | |
DX | -0.046 |
Fathers | -0.045 |
resolves | -0.044 |
DX | -0.044 |
cow | -0.043 |
Token | 03 |
Token ID | 3070 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
�醒 | +0.849 |
olit | +0.750 |
ult | +0.746 |
sted | +0.741 |
adr | +0.707 |
Neg logit contributions | |
DX | -0.741 |
Fathers | -0.724 |
resolves | -0.720 |
DX | -0.718 |
cow | -0.704 |
Token | , |
Token ID | 11 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
�醒 | +0.099 |
ult | +0.091 |
olit | +0.091 |
sted | +0.090 |
adr | +0.087 |
Neg logit contributions | |
DX | -0.051 |
Fathers | -0.050 |
resolves | -0.050 |
DX | -0.049 |
cow | -0.048 |
Token | 78 |
Token ID | 3695 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
DX | +0.020 |
Fathers | +0.020 |
DX | +0.019 |
resolves | +0.019 |
cow | +0.019 |
Neg logit contributions | |
�醒 | -0.022 |
olit | -0.019 |
ult | -0.019 |
sted | -0.019 |
adr | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
�醒 | +0.432 |
sted | +0.385 |
ult | +0.383 |
olit | +0.381 |
adr | +0.368 |
Neg logit contributions | |
DX | -0.334 |
resolves | -0.332 |
Fathers | -0.330 |
cow | -0.330 |
DX | -0.325 |
Token | taken |
Token ID | 2077 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
�醒 | +0.341 |
ult | +0.308 |
olit | +0.308 |
sted | +0.307 |
adr | +0.294 |
Neg logit contributions | |
DX | -0.179 |
Fathers | -0.179 |
resolves | -0.177 |
DX | -0.177 |
cow | -0.177 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
�醒 | +0.163 |
ult | +0.146 |
sted | +0.146 |
olit | +0.146 |
adr | +0.140 |
Neg logit contributions | |
DX | -0.087 |
Fathers | -0.087 |
resolves | -0.087 |
DX | -0.086 |
cow | -0.086 |
Token | that |
Token ID | 326 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
�醒 | +0.160 |
ult | +0.143 |
olit | +0.143 |
sted | +0.142 |
adr | +0.137 |
Neg logit contributions | |
resolves | -0.088 |
DX | -0.088 |
Fathers | -0.088 |
DX | -0.087 |
cow | -0.086 |
Token | such |
Token ID | 884 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
�醒 | +0.467 |
olit | +0.416 |
ult | +0.414 |
sted | +0.411 |
adr | +0.399 |
Neg logit contributions | |
DX | -0.302 |
Fathers | -0.302 |
resolves | -0.300 |
DX | -0.296 |
cow | -0.296 |
Token | adjud |
Token ID | 33719 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
�醒 | +0.546 |
olit | +0.489 |
ult | +0.486 |
sted | +0.484 |
adr | +0.467 |
Neg logit contributions | |
Fathers | -0.330 |
DX | -0.329 |
resolves | -0.328 |
DX | -0.324 |
cow | -0.323 |
Token | ication |
Token ID | 3299 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
�醒 | +0.240 |
olit | +0.218 |
ult | +0.217 |
sted | +0.216 |
adr | +0.209 |
Neg logit contributions | |
DX | -0.100 |
resolves | -0.098 |
Fathers | -0.097 |
DX | -0.095 |
cow | -0.094 |
Token | can |
Token ID | 460 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
resolves | +0.129 |
Fathers | +0.128 |
DX | +0.127 |
DX | +0.125 |
cow | +0.125 |
Neg logit contributions | |
�醒 | -0.168 |
sted | -0.147 |
ult | -0.146 |
olit | -0.144 |
adr | -0.139 |
Token | be |
Token ID | 307 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
�醒 | +0.548 |
sted | +0.488 |
ult | +0.485 |
olit | +0.484 |
adr | +0.468 |
Neg logit contributions | |
DX | -0.411 |
resolves | -0.407 |
Fathers | -0.405 |
cow | -0.404 |
DX | -0.400 |
Token | acceptable |
Token ID | 10909 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
�醒 | +0.454 |
ult | +0.412 |
olit | +0.410 |
sted | +0.409 |
adr | +0.395 |
Neg logit contributions | |
DX | -0.223 |
Fathers | -0.222 |
resolves | -0.220 |
DX | -0.219 |
cow | -0.218 |
Token | in |
Token ID | 287 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
�醒 | +0.527 |
sted | +0.468 |
olit | +0.468 |
ult | +0.467 |
adr | +0.449 |
Neg logit contributions | |
DX | -0.353 |
Fathers | -0.346 |
resolves | -0.346 |
DX | -0.346 |
cow | -0.345 |
Token | the |
Token ID | 262 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
�醒 | +0.021 |
olit | +0.019 |
ult | +0.019 |
sted | +0.019 |
adr | +0.018 |
Neg logit contributions | |
DX | -0.014 |
DX | -0.013 |
Fathers | -0.013 |
resolves | -0.013 |
cow | -0.013 |
Token | past |
Token ID | 1613 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
DX | +0.230 |
Fathers | +0.229 |
DX | +0.229 |
resolves | +0.225 |
cow | +0.225 |
Neg logit contributions | |
�醒 | -0.399 |
olit | -0.358 |
ult | -0.356 |
sted | -0.355 |
adr | -0.343 |
Token | four |
Token ID | 1440 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
�醒 | +0.021 |
olit | +0.019 |
ult | +0.019 |
sted | +0.019 |
adr | +0.018 |
Neg logit contributions | |
DX | -0.013 |
Fathers | -0.013 |
DX | -0.013 |
resolves | -0.013 |
cow | -0.013 |
Token | decades |
Token ID | 4647 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
DX | +0.030 |
resolves | +0.029 |
Fathers | +0.029 |
DX | +0.029 |
cow | +0.029 |
Neg logit contributions | |
�醒 | -0.037 |
olit | -0.033 |
ult | -0.033 |
sted | -0.033 |
adr | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
�醒 | +0.306 |
olit | +0.277 |
ult | +0.275 |
sted | +0.275 |
adr | +0.266 |
Neg logit contributions | |
DX | -0.141 |
Fathers | -0.138 |
resolves | -0.138 |
DX | -0.137 |
cow | -0.136 |
Token | estimate |
Token ID | 8636 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
DX | +0.042 |
resolves | +0.041 |
Fathers | +0.041 |
DX | +0.041 |
cow | +0.041 |
Neg logit contributions | |
�醒 | -0.064 |
olit | -0.057 |
ult | -0.056 |
sted | -0.056 |
adr | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
DX | +0.108 |
resolves | +0.105 |
DX | +0.105 |
Fathers | +0.104 |
cow | +0.103 |
Neg logit contributions | |
�醒 | -0.188 |
olit | -0.171 |
ult | -0.169 |
sted | -0.169 |
adr | -0.163 |
Token | lake |
Token ID | 13546 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
�醒 | +0.036 |
ult | +0.032 |
olit | +0.032 |
sted | +0.032 |
adr | +0.031 |
Neg logit contributions | |
DX | -0.023 |
Fathers | -0.023 |
resolves | -0.023 |
DX | -0.023 |
cow | -0.023 |
Token | � |
Token ID | 447 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
DX | +0.236 |
resolves | +0.230 |
Fathers | +0.228 |
DX | +0.228 |
cow | +0.225 |
Neg logit contributions | |
�醒 | -0.524 |
ult | -0.475 |
olit | -0.473 |
sted | -0.471 |
adr | -0.461 |
Token | � |
Token ID | 247 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
�醒 | +0.142 |
olit | +0.127 |
ult | +0.127 |
sted | +0.127 |
adr | +0.119 |
Neg logit contributions | |
DX | -0.147 |
Fathers | -0.144 |
DX | -0.144 |
resolves | -0.143 |
cow | -0.142 |
Token | s |
Token ID | 82 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
�醒 | +0.084 |
olit | +0.074 |
ult | +0.073 |
sted | +0.073 |
adr | +0.070 |
Neg logit contributions | |
DX | -0.072 |
resolves | -0.070 |
Fathers | -0.070 |
DX | -0.070 |
cow | -0.069 |
Token | old |
Token ID | 1468 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
DX | +0.252 |
Fathers | +0.247 |
resolves | +0.246 |
DX | +0.245 |
cow | +0.242 |
Neg logit contributions | |
�醒 | -0.254 |
ult | -0.226 |
olit | -0.226 |
sted | -0.224 |
adr | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
�醒 | +0.302 |
ult | +0.275 |
olit | +0.275 |
sted | +0.274 |
adr | +0.265 |
Neg logit contributions | |
DX | -0.135 |
Fathers | -0.133 |
resolves | -0.131 |
DX | -0.131 |
cow | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Fathers | +0.104 |
DX | +0.103 |
DX | +0.102 |
resolves | +0.100 |
cow | +0.099 |
Neg logit contributions | |
�醒 | -0.127 |
olit | -0.113 |
ult | -0.112 |
sted | -0.111 |
adr | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
�醒 | +0.107 |
olit | +0.095 |
ult | +0.094 |
sted | +0.093 |
adr | +0.090 |
Neg logit contributions | |
DX | -0.092 |
Fathers | -0.091 |
resolves | -0.090 |
DX | -0.090 |
cow | -0.088 |
Token | More |
Token ID | 5167 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
DX | +0.047 |
Fathers | +0.046 |
DX | +0.045 |
resolves | +0.044 |
cow | +0.044 |
Neg logit contributions | |
�醒 | -0.056 |
olit | -0.050 |
sted | -0.049 |
ult | -0.049 |
adr | -0.047 |
Token | about |
Token ID | 546 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Fathers | +0.368 |
DX | +0.366 |
DX | +0.362 |
cow | +0.360 |
resolves | +0.360 |
Neg logit contributions | |
�醒 | -0.659 |
olit | -0.591 |
ult | -0.587 |
sted | -0.585 |
adr | -0.573 |
Token | this |
Token ID | 428 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
�醒 | +0.431 |
olit | +0.389 |
ult | +0.388 |
sted | +0.385 |
adr | +0.372 |
Neg logit contributions | |
DX | -0.273 |
Fathers | -0.271 |
DX | -0.267 |
resolves | -0.267 |
cow | -0.264 |
Token | story |
Token ID | 1621 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
�醒 | +0.332 |
olit | +0.298 |
ult | +0.298 |
sted | +0.296 |
adr | +0.285 |
Neg logit contributions | |
DX | -0.221 |
Fathers | -0.219 |
DX | -0.217 |
resolves | -0.216 |
cow | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
�醒 | +0.088 |
olit | +0.079 |
ult | +0.079 |
sted | +0.078 |
adr | +0.076 |
Neg logit contributions | |
Fathers | -0.056 |
DX | -0.055 |
DX | -0.055 |
resolves | -0.054 |
cow | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
�醒 | +0.209 |
olit | +0.186 |
ult | +0.186 |
sted | +0.185 |
adr | +0.176 |
Neg logit contributions | |
DX | -0.188 |
Fathers | -0.185 |
resolves | -0.184 |
DX | -0.183 |
cow | -0.180 |
Token | After |
Token ID | 3260 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
DX | +0.149 |
Fathers | +0.144 |
DX | +0.140 |
resolves | +0.139 |
cow | +0.138 |
Neg logit contributions | |
�醒 | -0.183 |
olit | -0.162 |
sted | -0.159 |
ult | -0.159 |
adr | -0.152 |
Token | around |
Token ID | 1088 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
DX | +0.314 |
Fathers | +0.311 |
resolves | +0.310 |
DX | +0.308 |
cow | +0.307 |
Neg logit contributions | |
�醒 | -0.588 |
ult | -0.530 |
olit | -0.525 |
sted | -0.521 |
adr | -0.507 |
Token | arbitrarily |
Token ID | 40647 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
DX | +0.163 |
resolves | +0.161 |
Fathers | +0.160 |
DX | +0.160 |
cow | +0.158 |
Neg logit contributions | |
�醒 | -0.305 |
olit | -0.275 |
ult | -0.275 |
sted | -0.272 |
adr | -0.262 |
Token | ; |
Token ID | 26 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
resolves | +0.166 |
DX | +0.165 |
Fathers | +0.163 |
changing | +0.162 |
DX | +0.162 |
Neg logit contributions | |
�醒 | -0.360 |
ult | -0.323 |
olit | -0.322 |
sted | -0.318 |
adr | -0.309 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
DX | +0.139 |
Fathers | +0.139 |
resolves | +0.138 |
DX | +0.138 |
cow | +0.138 |
Neg logit contributions | |
�醒 | -0.258 |
olit | -0.233 |
ult | -0.232 |
sted | -0.231 |
adr | -0.222 |
Token | separation |
Token ID | 14139 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
�醒 | +0.116 |
ult | +0.105 |
olit | +0.104 |
sted | +0.104 |
adr | +0.100 |
Neg logit contributions | |
Fathers | -0.065 |
DX | -0.064 |
DX | -0.063 |
cow | -0.063 |
resolves | -0.063 |
Token | wall |
Token ID | 3355 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
�醒 | +0.025 |
sted | +0.023 |
ult | +0.022 |
olit | +0.022 |
adr | +0.021 |
Neg logit contributions | |
resolves | -0.016 |
Fathers | -0.016 |
DX | -0.016 |
cow | -0.016 |
DX | -0.016 |
Token | cuts |
Token ID | 6630 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
resolves | +0.026 |
Fathers | +0.026 |
DX | +0.026 |
cow | +0.025 |
DX | +0.025 |
Neg logit contributions | |
�醒 | -0.040 |
sted | -0.035 |
ult | -0.035 |
olit | -0.035 |
adr | -0.033 |
Token | people |
Token ID | 661 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
�醒 | +0.093 |
ult | +0.083 |
olit | +0.083 |
sted | +0.083 |
adr | +0.080 |
Neg logit contributions | |
DX | -0.056 |
Fathers | -0.055 |
resolves | -0.055 |
DX | -0.055 |
cow | -0.055 |
Token | off |
Token ID | 572 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
�醒 | +0.623 |
ult | +0.559 |
olit | +0.558 |
sted | +0.554 |
adr | +0.534 |
Neg logit contributions | |
DX | -0.369 |
Fathers | -0.367 |
resolves | -0.365 |
cow | -0.361 |
DX | -0.361 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
�醒 | +0.999 |
ult | +0.910 |
olit | +0.910 |
sted | +0.906 |
adr | +0.877 |
Neg logit contributions | |
DX | -0.403 |
Fathers | -0.395 |
resolves | -0.395 |
DX | -0.391 |
cow | -0.386 |
Token | and |
Token ID | 290 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Fathers | +0.088 |
resolves | +0.088 |
DX | +0.088 |
cow | +0.087 |
DX | +0.087 |
Neg logit contributions | |
�醒 | -0.149 |
ult | -0.133 |
olit | -0.133 |
sted | -0.133 |
adr | -0.128 |
Token | understands |
Token ID | 14759 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
resolves | +0.310 |
DX | +0.309 |
Fathers | +0.306 |
cow | +0.302 |
DX | +0.302 |
Neg logit contributions | |
�醒 | -0.443 |
ult | -0.390 |
olit | -0.389 |
sted | -0.387 |
adr | -0.372 |
Token | our |
Token ID | 674 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
�醒 | +0.618 |
ult | +0.558 |
olit | +0.557 |
sted | +0.553 |
adr | +0.532 |
Neg logit contributions | |
DX | -0.388 |
Fathers | -0.382 |
resolves | -0.379 |
DX | -0.379 |
cow | -0.373 |
Token | unique |
Token ID | 3748 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
�醒 | +0.149 |
ult | +0.134 |
olit | +0.134 |
sted | +0.133 |
adr | +0.128 |
Neg logit contributions | |
DX | -0.089 |
Fathers | -0.088 |
resolves | -0.087 |
DX | -0.086 |
cow | -0.085 |
Token | campus |
Token ID | 7611 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
DX | +0.242 |
Fathers | +0.239 |
DX | +0.237 |
resolves | +0.236 |
cow | +0.235 |
Neg logit contributions | |
�醒 | -0.393 |
ult | -0.350 |
olit | -0.349 |
sted | -0.346 |
adr | -0.337 |
Token | culture |
Token ID | 3968 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
�醒 | +0.357 |
ult | +0.324 |
sted | +0.321 |
olit | +0.321 |
adr | +0.312 |
Neg logit contributions | |
DX | -0.179 |
Fathers | -0.175 |
resolves | -0.174 |
DX | -0.173 |
cow | -0.171 |
Token | as |
Token ID | 355 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
DX | +0.063 |
Fathers | +0.061 |
resolves | +0.061 |
DX | +0.061 |
cow | +0.060 |
Neg logit contributions | |
�醒 | -0.128 |
ult | -0.116 |
olit | -0.116 |
sted | -0.116 |
adr | -0.112 |
Token | opposed |
Token ID | 6886 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
�醒 | +0.151 |
olit | +0.136 |
ult | +0.136 |
sted | +0.135 |
adr | +0.131 |
Neg logit contributions | |
DX | -0.094 |
Fathers | -0.092 |
resolves | -0.092 |
DX | -0.092 |
cow | -0.091 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
�醒 | +0.090 |
olit | +0.081 |
ult | +0.081 |
sted | +0.081 |
adr | +0.078 |
Neg logit contributions | |
DX | -0.042 |
Fathers | -0.041 |
resolves | -0.041 |
DX | -0.041 |
cow | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
DX | +0.105 |
Fathers | +0.104 |
DX | +0.104 |
resolves | +0.104 |
cow | +0.103 |
Neg logit contributions | |
�醒 | -0.166 |
olit | -0.149 |
ult | -0.148 |
sted | -0.148 |
adr | -0.142 |
Token | national |
Token ID | 2260 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
DX | +0.084 |
DX | +0.082 |
Fathers | +0.082 |
cow | +0.082 |
resolves | +0.081 |
Neg logit contributions | |
�醒 | -0.146 |
ult | -0.132 |
olit | -0.131 |
sted | -0.131 |
adr | -0.126 |
Token | [ |
Token ID | 685 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
DX | +0.136 |
DX | +0.134 |
cow | +0.133 |
Fathers | +0.133 |
resolves | +0.132 |
Neg logit contributions | |
�醒 | -0.206 |
ult | -0.185 |
olit | -0.184 |
sted | -0.182 |
adr | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
DX | +0.297 |
Fathers | +0.291 |
resolves | +0.289 |
DX | +0.287 |
cow | +0.284 |
Neg logit contributions | |
�醒 | -0.558 |
olit | -0.508 |
ult | -0.507 |
sted | -0.505 |
adr | -0.490 |
Token | Inner |
Token ID | 24877 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
�醒 | +0.104 |
olit | +0.094 |
ult | +0.094 |
sted | +0.093 |
adr | +0.090 |
Neg logit contributions | |
DX | -0.055 |
Fathers | -0.054 |
resolves | -0.054 |
DX | -0.054 |
cow | -0.053 |
Token | Mongolia |
Token ID | 44364 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Fathers | +0.058 |
DX | +0.058 |
DX | +0.057 |
resolves | +0.055 |
cow | +0.053 |
Neg logit contributions | |
�醒 | -0.233 |
ult | -0.213 |
olit | -0.212 |
sted | -0.211 |
adr | -0.208 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
DX | +0.236 |
Fathers | +0.233 |
resolves | +0.231 |
DX | +0.229 |
cow | +0.227 |
Neg logit contributions | |
�醒 | -0.441 |
olit | -0.401 |
ult | -0.400 |
sted | -0.398 |
adr | -0.386 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
�醒 | +0.194 |
olit | +0.177 |
ult | +0.176 |
sted | +0.175 |
adr | +0.169 |
Neg logit contributions | |
DX | -0.111 |
Fathers | -0.110 |
resolves | -0.109 |
DX | -0.108 |
cow | -0.107 |
Token | Mong |
Token ID | 18428 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
�醒 | +0.022 |
olit | +0.020 |
ult | +0.020 |
sted | +0.020 |
adr | +0.019 |
Neg logit contributions | |
Fathers | -0.013 |
DX | -0.013 |
resolves | -0.013 |
cow | -0.013 |
DX | -0.012 |
Token | ols |
Token ID | 10220 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Fathers | +0.393 |
DX | +0.392 |
resolves | +0.379 |
DX | +0.372 |
cow | +0.370 |
Neg logit contributions | |
�醒 | -1.022 |
sted | -0.898 |
ult | -0.887 |
olit | -0.879 |
adr | -0.873 |
Token | also |
Token ID | 635 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
�醒 | +0.099 |
olit | +0.089 |
ult | +0.089 |
sted | +0.088 |
adr | +0.085 |
Neg logit contributions | |
DX | -0.067 |
Fathers | -0.066 |
resolves | -0.066 |
DX | -0.065 |
cow | -0.065 |
Token | use |
Token ID | 779 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
�醒 | +0.218 |
olit | +0.196 |
ult | +0.196 |
sted | +0.195 |
adr | +0.187 |
Neg logit contributions | |
DX | -0.147 |
Fathers | -0.145 |
resolves | -0.144 |
DX | -0.143 |
cow | -0.142 |
Token | clan |
Token ID | 19065 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
DX | +0.113 |
Fathers | +0.112 |
resolves | +0.111 |
DX | +0.110 |
cow | +0.110 |
Neg logit contributions | |
�醒 | -0.185 |
olit | -0.167 |
ult | -0.167 |
sted | -0.166 |
adr | -0.160 |
Token | names |
Token ID | 3891 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
DX | +0.192 |
Fathers | +0.190 |
resolves | +0.190 |
DX | +0.188 |
cow | +0.186 |
Neg logit contributions | |
�醒 | -0.289 |
olit | -0.259 |
ult | -0.258 |
sted | -0.256 |
adr | -0.247 |
Token | their |
Token ID | 511 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Fathers | +0.025 |
resolves | +0.025 |
DX | +0.025 |
DX | +0.025 |
cow | +0.025 |
Neg logit contributions | |
�醒 | -0.036 |
olit | -0.033 |
ult | -0.032 |
sted | -0.032 |
adr | -0.031 |
Token | client |
Token ID | 5456 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
DX | +0.158 |
Fathers | +0.158 |
resolves | +0.158 |
DX | +0.157 |
cow | +0.157 |
Neg logit contributions | |
�醒 | -0.174 |
olit | -0.155 |
ult | -0.153 |
sted | -0.152 |
adr | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
Fathers | +0.345 |
DX | +0.344 |
resolves | +0.340 |
cow | +0.339 |
DX | +0.338 |
Neg logit contributions | |
�醒 | -0.599 |
olit | -0.543 |
sted | -0.537 |
ult | -0.535 |
adr | -0.517 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
�醒 | +0.032 |
olit | +0.029 |
ult | +0.029 |
sted | +0.029 |
adr | +0.027 |
Neg logit contributions | |
Fathers | -0.027 |
DX | -0.027 |
DX | -0.026 |
resolves | -0.026 |
cow | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
�醒 | +0.167 |
olit | +0.148 |
ult | +0.147 |
sted | +0.146 |
adr | +0.140 |
Neg logit contributions | |
DX | -0.144 |
Fathers | -0.141 |
resolves | -0.140 |
DX | -0.140 |
cow | -0.138 |
Token | Asked |
Token ID | 18932 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
DX | +0.049 |
Fathers | +0.047 |
resolves | +0.046 |
DX | +0.046 |
cow | +0.045 |
Neg logit contributions | |
�醒 | -0.059 |
olit | -0.052 |
sted | -0.051 |
ult | -0.050 |
adr | -0.048 |
Token | why |
Token ID | 1521 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
DX | +0.549 |
Fathers | +0.548 |
DX | +0.541 |
resolves | +0.540 |
cow | +0.539 |
Neg logit contributions | |
�醒 | -0.936 |
olit | -0.839 |
ult | -0.833 |
sted | -0.833 |
adr | -0.809 |
Token | she |
Token ID | 673 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Fathers | +0.466 |
resolves | +0.461 |
cow | +0.460 |
DX | +0.457 |
DX | +0.457 |
Neg logit contributions | |
�醒 | -0.738 |
sted | -0.658 |
olit | -0.658 |
ult | -0.657 |
adr | -0.636 |
Token | thought |
Token ID | 1807 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
resolves | +0.200 |
Fathers | +0.196 |
cow | +0.195 |
DX | +0.195 |
DX | +0.191 |
Neg logit contributions | |
�醒 | -0.265 |
olit | -0.233 |
ult | -0.233 |
sted | -0.232 |
adr | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Fathers | +0.197 |
resolves | +0.194 |
DX | +0.194 |
cow | +0.194 |
DX | +0.193 |
Neg logit contributions | |
�醒 | -0.335 |
olit | -0.302 |
sted | -0.300 |
ult | -0.300 |
adr | -0.292 |
Token | prosecutors |
Token ID | 11947 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Fathers | +0.103 |
cow | +0.100 |
resolves | +0.100 |
DX | +0.099 |
DX | +0.099 |
Neg logit contributions | |
�醒 | -0.154 |
olit | -0.139 |
ult | -0.138 |
sted | -0.137 |
adr | -0.131 |
Token | Engineering |
Token ID | 14044 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
�醒 | +0.121 |
olit | +0.106 |
ult | +0.106 |
sted | +0.104 |
adr | +0.102 |
Neg logit contributions | |
Fathers | -0.099 |
DX | -0.098 |
DX | -0.098 |
resolves | -0.098 |
cow | -0.096 |
Token | office |
Token ID | 2607 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
�醒 | +0.216 |
olit | +0.197 |
ult | +0.196 |
sted | +0.194 |
adr | +0.190 |
Neg logit contributions | |
DX | -0.102 |
Fathers | -0.100 |
DX | -0.099 |
resolves | -0.099 |
cow | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
DX | +0.391 |
DX | +0.383 |
resolves | +0.379 |
Fathers | +0.378 |
cow | +0.376 |
Neg logit contributions | |
�醒 | -0.913 |
olit | -0.834 |
ult | -0.828 |
sted | -0.818 |
adr | -0.805 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Fathers | +0.196 |
DX | +0.196 |
DX | +0.194 |
resolves | +0.191 |
cow | +0.187 |
Neg logit contributions | |
�醒 | -0.235 |
olit | -0.210 |
ult | -0.208 |
sted | -0.205 |
adr | -0.197 |
Token |
|
Token ID | 198 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
DX | +0.145 |
Fathers | +0.142 |
resolves | +0.141 |
DX | +0.141 |
cow | +0.138 |
Neg logit contributions | |
�醒 | -0.176 |
olit | -0.154 |
ult | -0.153 |
sted | -0.152 |
adr | -0.146 |
Token | If |
Token ID | 1532 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
DX | +0.293 |
Fathers | +0.279 |
resolves | +0.276 |
DX | +0.275 |
cow | +0.270 |
Neg logit contributions | |
�醒 | -0.337 |
olit | -0.298 |
ult | -0.292 |
sted | -0.291 |
adr | -0.278 |
Token | a |
Token ID | 257 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
resolves | +0.514 |
DX | +0.512 |
Fathers | +0.511 |
DX | +0.506 |
cow | +0.500 |
Neg logit contributions | |
�醒 | -0.822 |
olit | -0.745 |
ult | -0.744 |
sted | -0.733 |
adr | -0.711 |
Token | homeowner |
Token ID | 40130 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
�醒 | +0.175 |
ult | +0.160 |
olit | +0.160 |
sted | +0.157 |
adr | +0.152 |
Neg logit contributions | |
DX | -0.110 |
Fathers | -0.109 |
resolves | -0.109 |
DX | -0.108 |
cow | -0.108 |
Token | � |
Token ID | 447 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
resolves | +0.048 |
DX | +0.048 |
Fathers | +0.048 |
DX | +0.047 |
cow | +0.047 |
Neg logit contributions | |
�醒 | -0.074 |
olit | -0.067 |
ult | -0.066 |
sted | -0.066 |
adr | -0.063 |
Token | � |
Token ID | 247 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
DX | +0.152 |
Fathers | +0.149 |
DX | +0.148 |
resolves | +0.147 |
cow | +0.147 |
Neg logit contributions | |
�醒 | -0.114 |
olit | -0.100 |
ult | -0.100 |
sted | -0.099 |
adr | -0.092 |
Token | s |
Token ID | 82 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
resolves | +0.130 |
DX | +0.128 |
Fathers | +0.127 |
cow | +0.125 |
DX | +0.125 |
Neg logit contributions | |
�醒 | -0.158 |
olit | -0.139 |
ult | -0.136 |
sted | -0.136 |
adr | -0.132 |
Token | Kernel |
Token ID | 32169 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
�醒 | +0.126 |
olit | +0.113 |
sted | +0.113 |
ult | +0.113 |
adr | +0.108 |
Neg logit contributions | |
DX | -0.082 |
resolves | -0.081 |
DX | -0.081 |
Fathers | -0.080 |
cow | -0.080 |
Token | cannot |
Token ID | 2314 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
�醒 | +0.212 |
olit | +0.190 |
ult | +0.189 |
sted | +0.189 |
adr | +0.182 |
Neg logit contributions | |
DX | -0.150 |
resolves | -0.150 |
Fathers | -0.147 |
DX | -0.147 |
cow | -0.144 |
Token | correctly |
Token ID | 9380 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
�醒 | +0.342 |
sted | +0.304 |
ult | +0.304 |
olit | +0.304 |
adr | +0.291 |
Neg logit contributions | |
DX | -0.261 |
resolves | -0.258 |
DX | -0.255 |
Fathers | -0.254 |
cow | -0.252 |
Token | mount |
Token ID | 3817 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
DX | +0.123 |
resolves | +0.122 |
DX | +0.120 |
Fathers | +0.119 |
cow | +0.119 |
Neg logit contributions | |
�醒 | -0.200 |
sted | -0.178 |
ult | -0.178 |
olit | -0.178 |
adr | -0.172 |
Token | it |
Token ID | 340 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
DX | +0.113 |
resolves | +0.111 |
DX | +0.110 |
Fathers | +0.110 |
cow | +0.108 |
Neg logit contributions | |
�醒 | -0.200 |
olit | -0.180 |
ult | -0.180 |
sted | -0.180 |
adr | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
DX | +0.097 |
resolves | +0.096 |
DX | +0.094 |
Fathers | +0.094 |
cow | +0.092 |
Neg logit contributions | |
�醒 | -0.199 |
olit | -0.180 |
sted | -0.179 |
ult | -0.179 |
adr | -0.172 |
Token | it |
Token ID | 340 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
DX | +0.476 |
resolves | +0.468 |
DX | +0.466 |
Fathers | +0.463 |
cow | +0.456 |
Neg logit contributions | |
�醒 | -0.866 |
olit | -0.780 |
sted | -0.777 |
ult | -0.773 |
adr | -0.749 |
Token | will |
Token ID | 481 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
resolves | +0.097 |
DX | +0.096 |
Fathers | +0.095 |
DX | +0.094 |
cow | +0.094 |
Neg logit contributions | |
�醒 | -0.133 |
olit | -0.118 |
sted | -0.118 |
ult | -0.117 |
adr | -0.113 |
Token | panic |
Token ID | 13619 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
�醒 | +0.167 |
olit | +0.150 |
sted | +0.150 |
ult | +0.149 |
adr | +0.145 |
Neg logit contributions | |
DX | -0.103 |
resolves | -0.102 |
Fathers | -0.101 |
DX | -0.101 |
cow | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
�醒 | +0.486 |
olit | +0.444 |
ult | +0.441 |
sted | +0.439 |
adr | +0.427 |
Neg logit contributions | |
DX | -0.236 |
resolves | -0.230 |
Fathers | -0.229 |
DX | -0.229 |
cow | -0.224 |
Token | reboot |
Token ID | 20149 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
�醒 | +0.021 |
olit | +0.019 |
sted | +0.019 |
ult | +0.019 |
adr | +0.018 |
Neg logit contributions | |
DX | -0.012 |
resolves | -0.012 |
Fathers | -0.012 |
DX | -0.012 |
cow | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
DX | +0.089 |
Fathers | +0.087 |
resolves | +0.086 |
DX | +0.086 |
cow | +0.085 |
Neg logit contributions | |
�醒 | -0.102 |
olit | -0.091 |
ult | -0.090 |
sted | -0.089 |
adr | -0.086 |
Token | L |
Token ID | 43 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
DX | +0.166 |
resolves | +0.160 |
Fathers | +0.158 |
DX | +0.158 |
cow | +0.154 |
Neg logit contributions | |
�醒 | -0.218 |
olit | -0.195 |
ult | -0.192 |
sted | -0.192 |
adr | -0.184 |
Token | anda |
Token ID | 5282 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
DX | +0.110 |
resolves | +0.108 |
DX | +0.106 |
Fathers | +0.106 |
cow | +0.105 |
Neg logit contributions | |
�醒 | -0.110 |
sted | -0.092 |
ult | -0.092 |
olit | -0.090 |
adr | -0.087 |
Token | says |
Token ID | 1139 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
resolves | +0.082 |
DX | +0.081 |
Fathers | +0.080 |
DX | +0.080 |
cow | +0.079 |
Neg logit contributions | |
�醒 | -0.122 |
olit | -0.109 |
ult | -0.107 |
sted | -0.107 |
adr | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
DX | +0.257 |
resolves | +0.256 |
Fathers | +0.254 |
DX | +0.252 |
cow | +0.250 |
Neg logit contributions | |
�醒 | -0.533 |
olit | -0.485 |
ult | -0.483 |
sted | -0.481 |
adr | -0.468 |
Token | ' |
Token ID | 705 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
DX | +0.152 |
Fathers | +0.150 |
resolves | +0.149 |
DX | +0.148 |
cow | +0.147 |
Neg logit contributions | |
�醒 | -0.198 |
olit | -0.179 |
ult | -0.178 |
sted | -0.177 |
adr | -0.170 |
Token | We |
Token ID | 775 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
DX | +0.594 |
Fathers | +0.587 |
resolves | +0.586 |
DX | +0.580 |
cow | +0.569 |
Neg logit contributions | |
�醒 | -0.720 |
olit | -0.634 |
ult | -0.629 |
sted | -0.628 |
adr | -0.606 |
Token | don |
Token ID | 836 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Fathers | +0.173 |
DX | +0.173 |
resolves | +0.173 |
cow | +0.171 |
DX | +0.170 |
Neg logit contributions | |
�醒 | -0.210 |
olit | -0.181 |
ult | -0.180 |
sted | -0.178 |
adr | -0.173 |
Token | 't |
Token ID | 470 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
DX | +0.405 |
Fathers | +0.397 |
resolves | +0.395 |
DX | +0.393 |
cow | +0.387 |
Neg logit contributions | |
�醒 | -0.493 |
olit | -0.437 |
ult | -0.436 |
sted | -0.433 |
adr | -0.414 |
Token | have |
Token ID | 423 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
cow | +0.138 |
resolves | +0.138 |
Fathers | +0.138 |
DX | +0.138 |
DX | +0.137 |
Neg logit contributions | |
�醒 | -0.127 |
olit | -0.107 |
ult | -0.106 |
sted | -0.106 |
adr | -0.102 |
Token | any |
Token ID | 597 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
�醒 | +0.497 |
ult | +0.448 |
olit | +0.448 |
sted | +0.442 |
adr | +0.430 |
Neg logit contributions | |
DX | -0.285 |
Fathers | -0.283 |
resolves | -0.282 |
DX | -0.280 |
cow | -0.276 |