Token | issue |
Token ID | 2071 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
AST | +0.099 |
elaide | +0.095 |
igree | +0.094 |
ovember | +0.093 |
outh | +0.093 |
Neg logit contributions | |
wash | -0.124 |
↑ | -0.122 |
pak | -0.116 |
gross | -0.113 |
kat | -0.113 |
Token | informal |
Token ID | 22176 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
AST | +0.376 |
elaide | +0.356 |
igree | +0.352 |
outh | +0.352 |
ovember | +0.349 |
Neg logit contributions | |
wash | -0.459 |
↑ | -0.453 |
pak | -0.431 |
kat | -0.421 |
gross | -0.419 |
Token | guidance |
Token ID | 11154 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
AST | +0.312 |
elaide | +0.298 |
igree | +0.294 |
outh | +0.294 |
ovember | +0.292 |
Neg logit contributions | |
wash | -0.361 |
↑ | -0.357 |
pak | -0.339 |
kat | -0.330 |
gross | -0.329 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
wash | +0.241 |
↑ | +0.237 |
pak | +0.226 |
kat | +0.219 |
gross | +0.219 |
Neg logit contributions | |
AST | -0.227 |
elaide | -0.217 |
igree | -0.214 |
outh | -0.214 |
ovember | -0.213 |
Token | policy |
Token ID | 2450 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
AST | +0.022 |
elaide | +0.021 |
igree | +0.021 |
outh | +0.021 |
ovember | +0.021 |
Neg logit contributions | |
wash | -0.025 |
↑ | -0.024 |
pak | -0.023 |
kat | -0.023 |
gross | -0.022 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
AST | +0.298 |
elaide | +0.284 |
igree | +0.281 |
outh | +0.281 |
ovember | +0.279 |
Neg logit contributions | |
wash | -0.305 |
↑ | -0.301 |
pak | -0.286 |
kat | -0.277 |
gross | -0.277 |
Token | anda |
Token ID | 5282 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
wash | +2.479 |
↑ | +2.429 |
pak | +2.316 |
kat | +2.265 |
gross | +2.244 |
Neg logit contributions | |
AST | -2.179 |
elaide | -2.107 |
igree | -2.059 |
outh | -2.050 |
ovember | -2.049 |
Token | intended |
Token ID | 5292 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
wash | +0.427 |
↑ | +0.420 |
pak | +0.399 |
kat | +0.387 |
gross | +0.386 |
Neg logit contributions | |
AST | -0.418 |
elaide | -0.400 |
igree | -0.395 |
outh | -0.395 |
ovember | -0.393 |
Token | to |
Token ID | 284 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
wash | +0.349 |
↑ | +0.343 |
pak | +0.323 |
kat | +0.313 |
gross | +0.312 |
Neg logit contributions | |
AST | -0.425 |
elaide | -0.408 |
igree | -0.403 |
outh | -0.403 |
ovember | -0.401 |
Token | help |
Token ID | 1037 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
wash | +0.113 |
↑ | +0.112 |
pak | +0.107 |
kat | +0.104 |
gross | +0.104 |
Neg logit contributions | |
AST | -0.083 |
elaide | -0.080 |
igree | -0.079 |
outh | -0.078 |
ovember | -0.078 |
Token | minority |
Token ID | 9137 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
wash | +0.382 |
↑ | +0.377 |
pak | +0.357 |
kat | +0.347 |
gross | +0.346 |
Neg logit contributions | |
AST | -0.359 |
elaide | -0.346 |
igree | -0.342 |
outh | -0.340 |
ovember | -0.340 |
Token | * |
Token ID | 1635 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
AST | +0.333 |
elaide | +0.317 |
outh | +0.313 |
igree | +0.313 |
ovember | +0.311 |
Neg logit contributions | |
wash | -0.369 |
↑ | -0.364 |
pak | -0.345 |
kat | -0.336 |
gross | -0.335 |
Token | - |
Token ID | 12 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
wash | +0.917 |
↑ | +0.902 |
pak | +0.855 |
kat | +0.831 |
gross | +0.830 |
Neg logit contributions | |
AST | -0.914 |
elaide | -0.881 |
igree | -0.872 |
outh | -0.866 |
ovember | -0.865 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
wash | +0.237 |
↑ | +0.233 |
pak | +0.221 |
kat | +0.215 |
gross | +0.215 |
Neg logit contributions | |
AST | -0.221 |
elaide | -0.213 |
igree | -0.210 |
outh | -0.209 |
ovember | -0.209 |
Token | Sean |
Token ID | 11465 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
wash | +0.046 |
↑ | +0.045 |
pak | +0.043 |
kat | +0.042 |
gross | +0.041 |
Neg logit contributions | |
AST | -0.046 |
elaide | -0.044 |
igree | -0.044 |
outh | -0.043 |
ovember | -0.043 |
Token | Con |
Token ID | 1482 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
wash | +0.200 |
↑ | +0.198 |
pak | +0.189 |
kat | +0.184 |
gross | +0.184 |
Neg logit contributions | |
AST | -0.145 |
elaide | -0.137 |
igree | -0.136 |
outh | -0.136 |
ovember | -0.135 |
Token | nery |
Token ID | 35865 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
AST | +0.522 |
elaide | +0.504 |
igree | +0.499 |
outh | +0.498 |
ovember | +0.497 |
Neg logit contributions | |
wash | -0.328 |
↑ | -0.322 |
pak | -0.300 |
kat | -0.289 |
gross | -0.288 |
Token | films |
Token ID | 7328 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
wash | +2.485 |
↑ | +2.440 |
pak | +2.332 |
kat | +2.263 |
gross | +2.262 |
Neg logit contributions | |
AST | -2.102 |
elaide | -2.050 |
igree | -2.021 |
ovember | -2.001 |
outh | -2.001 |
Token | , |
Token ID | 11 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
wash | +0.131 |
↑ | +0.130 |
pak | +0.123 |
kat | +0.120 |
gross | +0.119 |
Neg logit contributions | |
AST | -0.117 |
elaide | -0.112 |
igree | -0.110 |
outh | -0.110 |
ovember | -0.109 |
Token | 1962 |
Token ID | 20033 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
AST | +0.156 |
elaide | +0.148 |
igree | +0.146 |
outh | +0.146 |
ovember | +0.145 |
Neg logit contributions | |
wash | -0.171 |
↑ | -0.169 |
pak | -0.160 |
kat | -0.156 |
gross | -0.155 |
Token | - |
Token ID | 12 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
wash | +0.427 |
↑ | +0.422 |
pak | +0.403 |
kat | +0.393 |
gross | +0.391 |
Neg logit contributions | |
AST | -0.317 |
elaide | -0.301 |
outh | -0.296 |
igree | -0.296 |
ovember | -0.294 |
Token | 1971 |
Token ID | 41208 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
wash | +0.036 |
↑ | +0.035 |
pak | +0.032 |
kat | +0.031 |
gross | +0.031 |
Neg logit contributions | |
AST | -0.068 |
elaide | -0.065 |
outh | -0.064 |
ovember | -0.064 |
igree | -0.064 |
Token | atch |
Token ID | 963 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
wash | +0.447 |
↑ | +0.441 |
pak | +0.417 |
kat | +0.405 |
gross | +0.404 |
Neg logit contributions | |
AST | -0.462 |
elaide | -0.442 |
outh | -0.437 |
igree | -0.437 |
ovember | -0.434 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
wash | +1.121 |
↑ | +1.104 |
pak | +1.059 |
kat | +1.029 |
gross | +1.024 |
Neg logit contributions | |
AST | -0.832 |
elaide | -0.795 |
igree | -0.786 |
ovember | -0.779 |
outh | -0.778 |
Token | blue |
Token ID | 4171 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
wash | +0.205 |
↑ | +0.203 |
pak | +0.193 |
kat | +0.188 |
gross | +0.188 |
Neg logit contributions | |
AST | -0.158 |
elaide | -0.151 |
igree | -0.148 |
outh | -0.148 |
ovember | -0.147 |
Token | - |
Token ID | 12 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
wash | +0.897 |
↑ | +0.884 |
pak | +0.844 |
kat | +0.822 |
gross | +0.820 |
Neg logit contributions | |
AST | -0.665 |
elaide | -0.634 |
igree | -0.624 |
outh | -0.623 |
ovember | -0.620 |
Token | painted |
Token ID | 47351 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
wash | +0.189 |
↑ | +0.187 |
pak | +0.175 |
kat | +0.171 |
gross | +0.170 |
Neg logit contributions | |
AST | -0.214 |
elaide | -0.206 |
igree | -0.204 |
outh | -0.204 |
ovember | -0.202 |
Token | box |
Token ID | 3091 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
wash | +0.329 |
↑ | +0.324 |
pak | +0.310 |
kat | +0.302 |
gross | +0.300 |
Neg logit contributions | |
AST | -0.249 |
elaide | -0.239 |
igree | -0.235 |
outh | -0.234 |
ovember | -0.234 |
Token | before |
Token ID | 878 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
wash | +2.333 |
↑ | +2.281 |
pak | +2.183 |
kat | +2.133 |
gross | +2.107 |
Neg logit contributions | |
AST | -1.940 |
elaide | -1.884 |
igree | -1.842 |
ovember | -1.833 |
outh | -1.821 |
Token | it |
Token ID | 340 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
wash | +0.614 |
↑ | +0.606 |
pak | +0.576 |
kat | +0.560 |
gross | +0.558 |
Neg logit contributions | |
AST | -0.532 |
elaide | -0.512 |
igree | -0.504 |
outh | -0.502 |
ovember | -0.500 |
Token | touches |
Token ID | 18105 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
wash | +0.378 |
↑ | +0.372 |
pak | +0.351 |
kat | +0.341 |
gross | +0.340 |
Neg logit contributions | |
AST | -0.427 |
elaide | -0.408 |
igree | -0.404 |
outh | -0.404 |
ovember | -0.402 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
wash | +1.366 |
↑ | +1.350 |
pak | +1.288 |
kat | +1.254 |
gross | +1.248 |
Neg logit contributions | |
AST | -0.942 |
elaide | -0.903 |
outh | -0.887 |
igree | -0.885 |
ovember | -0.884 |
Token | ground |
Token ID | 2323 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
wash | +0.607 |
↑ | +0.601 |
pak | +0.576 |
kat | +0.562 |
gross | +0.560 |
Neg logit contributions | |
AST | -0.356 |
elaide | -0.340 |
igree | -0.333 |
outh | -0.332 |
ovember | -0.331 |
Token | text |
Token ID | 2420 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
wash | +0.227 |
↑ | +0.225 |
pak | +0.213 |
kat | +0.208 |
gross | +0.206 |
Neg logit contributions | |
AST | -0.202 |
elaide | -0.195 |
igree | -0.192 |
outh | -0.192 |
ovember | -0.191 |
Token | or |
Token ID | 393 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
wash | +0.366 |
↑ | +0.362 |
pak | +0.343 |
kat | +0.335 |
gross | +0.333 |
Neg logit contributions | |
AST | -0.327 |
elaide | -0.314 |
igree | -0.310 |
outh | -0.309 |
ovember | -0.308 |
Token | empty |
Token ID | 6565 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
wash | +0.144 |
↑ | +0.142 |
pak | +0.134 |
kat | +0.131 |
gross | +0.130 |
Neg logit contributions | |
AST | -0.146 |
elaide | -0.141 |
igree | -0.139 |
outh | -0.139 |
ovember | -0.138 |
Token | Example |
Token ID | 17934 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
wash | +1.109 |
↑ | +1.102 |
pak | +1.046 |
kat | +1.023 |
gross | +1.011 |
Neg logit contributions | |
AST | -0.774 |
elaide | -0.751 |
igree | -0.736 |
ovember | -0.732 |
outh | -0.729 |
Token | : |
Token ID | 25 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
wash | +0.337 |
↑ | +0.333 |
pak | +0.314 |
kat | +0.304 |
gross | +0.303 |
Neg logit contributions | |
AST | -0.373 |
elaide | -0.360 |
igree | -0.355 |
outh | -0.354 |
ovember | -0.353 |
Token | /* |
Token ID | 11900 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
AST | +0.128 |
elaide | +0.121 |
igree | +0.119 |
outh | +0.119 |
ovember | +0.118 |
Neg logit contributions | |
wash | -0.213 |
↑ | -0.211 |
pak | -0.202 |
kat | -0.198 |
gross | -0.197 |
Token | vim |
Token ID | 43907 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
wash | +2.281 |
↑ | +2.264 |
pak | +2.132 |
kat | +2.085 |
gross | +2.072 |
Neg logit contributions | |
AST | -1.861 |
elaide | -1.798 |
igree | -1.767 |
ovember | -1.747 |
outh | -1.741 |
Token | : |
Token ID | 25 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
wash | +0.229 |
↑ | +0.226 |
pak | +0.214 |
kat | +0.208 |
gross | +0.207 |
Neg logit contributions | |
AST | -0.238 |
elaide | -0.228 |
outh | -0.225 |
igree | -0.225 |
ovember | -0.224 |
Token | set |
Token ID | 900 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
AST | +0.251 |
elaide | +0.240 |
outh | +0.237 |
igree | +0.237 |
ovember | +0.236 |
Neg logit contributions | |
wash | -0.233 |
↑ | -0.229 |
pak | -0.217 |
kat | -0.211 |
gross | -0.211 |
Token | a |
Token ID | 257 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
AST | +0.512 |
elaide | +0.489 |
igree | +0.483 |
outh | +0.482 |
ovember | +0.480 |
Neg logit contributions | |
wash | -0.565 |
↑ | -0.558 |
pak | -0.530 |
kat | -0.516 |
gross | -0.514 |
Token | i |
Token ID | 72 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
AST | +0.141 |
elaide | +0.135 |
igree | +0.133 |
outh | +0.132 |
ovember | +0.132 |
Neg logit contributions | |
wash | -0.187 |
↑ | -0.185 |
pak | -0.176 |
kat | -0.172 |
gross | -0.171 |
Token | { |
Token ID | 90 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
AST | +0.165 |
elaide | +0.159 |
igree | +0.157 |
outh | +0.157 |
ovember | +0.156 |
Neg logit contributions | |
wash | -0.142 |
↑ | -0.140 |
pak | -0.131 |
kat | -0.127 |
gross | -0.127 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
wash | +0.389 |
↑ | +0.386 |
pak | +0.365 |
kat | +0.356 |
gross | +0.355 |
Neg logit contributions | |
AST | -0.345 |
elaide | -0.330 |
igree | -0.326 |
outh | -0.325 |
ovember | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
wash | +0.164 |
↑ | +0.163 |
pak | +0.155 |
kat | +0.151 |
gross | +0.151 |
Neg logit contributions | |
AST | -0.123 |
elaide | -0.118 |
igree | -0.116 |
outh | -0.116 |
ovember | -0.115 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
AST | +0.230 |
elaide | +0.220 |
outh | +0.218 |
igree | +0.218 |
ovember | +0.217 |
Neg logit contributions | |
wash | -0.206 |
↑ | -0.202 |
pak | -0.191 |
kat | -0.185 |
gross | -0.185 |
Token | } |
Token ID | 92 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
wash | +0.263 |
↑ | +0.259 |
pak | +0.245 |
kat | +0.239 |
gross | +0.238 |
Neg logit contributions | |
AST | -0.256 |
elaide | -0.245 |
igree | -0.242 |
outh | -0.241 |
ovember | -0.241 |
Token | < |
Token ID | 1279 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
AST | +0.853 |
elaide | +0.808 |
igree | +0.800 |
outh | +0.799 |
ovember | +0.795 |
Neg logit contributions | |
wash | -0.975 |
↑ | -0.956 |
pak | -0.914 |
kat | -0.890 |
gross | -0.888 |
Token | -> |
Token ID | 3784 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
↑ | +1.984 |
wash | +1.975 |
pak | +1.846 |
kat | +1.785 |
gross | +1.779 |
Neg logit contributions | |
AST | -2.106 |
elaide | -2.059 |
ovember | -2.014 |
igree | -2.012 |
outh | -2.009 |
Token | { |
Token ID | 1391 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
wash | +0.695 |
↑ | +0.691 |
pak | +0.655 |
kat | +0.639 |
gross | +0.637 |
Neg logit contributions | |
AST | -0.529 |
elaide | -0.509 |
igree | -0.500 |
ovember | -0.499 |
outh | -0.498 |
Token | 1 |
Token ID | 16 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
wash | +0.368 |
↑ | +0.363 |
pak | +0.339 |
kat | +0.328 |
gross | +0.327 |
Neg logit contributions | |
AST | -0.501 |
elaide | -0.484 |
igree | -0.479 |
outh | -0.478 |
ovember | -0.476 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
wash | +0.196 |
↑ | +0.193 |
pak | +0.185 |
kat | +0.180 |
gross | +0.180 |
Neg logit contributions | |
AST | -0.140 |
elaide | -0.131 |
outh | -0.130 |
igree | -0.130 |
ovember | -0.129 |
Token | 7 |
Token ID | 767 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
AST | +0.239 |
elaide | +0.228 |
outh | +0.226 |
igree | +0.225 |
ovember | +0.224 |
Neg logit contributions | |
wash | -0.236 |
↑ | -0.232 |
pak | -0.220 |
kat | -0.214 |
gross | -0.213 |
Token | {{ |
Token ID | 27007 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
AST | +0.261 |
elaide | +0.252 |
igree | +0.249 |
outh | +0.249 |
ovember | +0.248 |
Neg logit contributions | |
wash | -0.203 |
↑ | -0.200 |
pak | -0.188 |
kat | -0.182 |
gross | -0.181 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
wash | +0.712 |
↑ | +0.706 |
pak | +0.656 |
gross | +0.636 |
kat | +0.635 |
Neg logit contributions | |
AST | -0.935 |
elaide | -0.902 |
igree | -0.894 |
ovember | -0.889 |
outh | -0.888 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
wash | +0.224 |
↑ | +0.221 |
pak | +0.211 |
kat | +0.206 |
gross | +0.205 |
Neg logit contributions | |
AST | -0.164 |
elaide | -0.156 |
igree | -0.154 |
outh | -0.154 |
ovember | -0.153 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
AST | +0.208 |
elaide | +0.199 |
igree | +0.196 |
outh | +0.196 |
ovember | +0.195 |
Neg logit contributions | |
wash | -0.205 |
↑ | -0.201 |
pak | -0.191 |
kat | -0.186 |
gross | -0.185 |
Token | } |
Token ID | 92 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
wash | +0.276 |
↑ | +0.272 |
pak | +0.257 |
kat | +0.250 |
gross | +0.250 |
Neg logit contributions | |
AST | -0.280 |
elaide | -0.268 |
igree | -0.265 |
outh | -0.264 |
ovember | -0.263 |
Token | < |
Token ID | 1279 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
AST | +0.679 |
elaide | +0.643 |
outh | +0.635 |
igree | +0.635 |
ovember | +0.630 |
Neg logit contributions | |
wash | -0.824 |
↑ | -0.808 |
pak | -0.774 |
kat | -0.755 |
gross | -0.753 |
Token | -> |
Token ID | 3784 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
wash | +1.543 |
↑ | +1.540 |
pak | +1.421 |
kat | +1.371 |
gross | +1.336 |
Neg logit contributions | |
AST | -2.551 |
elaide | -2.478 |
igree | -2.446 |
outh | -2.439 |
ovember | -2.432 |
Token | { |
Token ID | 1391 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
wash | +0.801 |
↑ | +0.796 |
pak | +0.757 |
kat | +0.741 |
gross | +0.739 |
Neg logit contributions | |
AST | -0.503 |
elaide | -0.481 |
igree | -0.472 |
outh | -0.471 |
ovember | -0.471 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
wash | +0.320 |
↑ | +0.314 |
pak | +0.294 |
kat | +0.283 |
gross | +0.282 |
Neg logit contributions | |
AST | -0.466 |
elaide | -0.449 |
igree | -0.445 |
outh | -0.444 |
ovember | -0.442 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
wash | +0.190 |
↑ | +0.186 |
pak | +0.179 |
gross | +0.175 |
kat | +0.174 |
Neg logit contributions | |
AST | -0.131 |
outh | -0.122 |
elaide | -0.122 |
igree | -0.120 |
Monarch | -0.120 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
AST | +0.265 |
elaide | +0.254 |
igree | +0.251 |
outh | +0.250 |
ovember | +0.249 |
Neg logit contributions | |
wash | -0.259 |
↑ | -0.255 |
pak | -0.241 |
kat | -0.234 |
gross | -0.234 |
Token | Oh |
Token ID | 5812 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
AST | +0.048 |
elaide | +0.046 |
igree | +0.046 |
outh | +0.046 |
ovember | +0.045 |
Neg logit contributions | |
wash | -0.041 |
↑ | -0.040 |
pak | -0.038 |
kat | -0.036 |
gross | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
AST | +0.459 |
elaide | +0.438 |
igree | +0.432 |
outh | +0.431 |
ovember | +0.429 |
Neg logit contributions | |
wash | -0.569 |
↑ | -0.561 |
pak | -0.535 |
kat | -0.521 |
gross | -0.520 |
Token | and |
Token ID | 290 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
wash | +0.042 |
↑ | +0.041 |
pak | +0.039 |
kat | +0.038 |
gross | +0.038 |
Neg logit contributions | |
AST | -0.034 |
elaide | -0.032 |
igree | -0.032 |
outh | -0.032 |
ovember | -0.031 |
Token | forget |
Token ID | 6044 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
wash | +0.109 |
↑ | +0.107 |
pak | +0.102 |
kat | +0.099 |
gross | +0.099 |
Neg logit contributions | |
AST | -0.088 |
elaide | -0.085 |
igree | -0.084 |
outh | -0.083 |
ovember | -0.083 |
Token | about |
Token ID | 546 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
wash | +0.346 |
↑ | +0.342 |
pak | +0.325 |
kat | +0.317 |
gross | +0.316 |
Neg logit contributions | |
AST | -0.285 |
elaide | -0.273 |
igree | -0.269 |
outh | -0.268 |
ovember | -0.267 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
AST | +0.031 |
elaide | +0.030 |
igree | +0.029 |
outh | +0.029 |
ovember | +0.029 |
Neg logit contributions | |
wash | -0.040 |
↑ | -0.040 |
pak | -0.038 |
kat | -0.037 |
gross | -0.037 |
Token | izing |
Token ID | 2890 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
wash | +2.100 |
↑ | +2.069 |
pak | +1.962 |
kat | +1.910 |
gross | +1.900 |
Neg logit contributions | |
AST | -2.000 |
elaide | -1.926 |
igree | -1.894 |
outh | -1.893 |
ovember | -1.877 |
Token | times |
Token ID | 1661 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
wash | +0.076 |
↑ | +0.075 |
pak | +0.071 |
kat | +0.070 |
gross | +0.069 |
Neg logit contributions | |
AST | -0.062 |
elaide | -0.059 |
igree | -0.058 |
outh | -0.058 |
ovember | -0.058 |
Token | tables |
Token ID | 8893 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
wash | +0.190 |
↑ | +0.187 |
pak | +0.178 |
kat | +0.173 |
gross | +0.173 |
Neg logit contributions | |
AST | -0.165 |
elaide | -0.157 |
igree | -0.155 |
outh | -0.155 |
ovember | -0.154 |
Token | or |
Token ID | 393 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
AST | +1.350 |
elaide | +1.284 |
outh | +1.273 |
igree | +1.261 |
ovember | +1.254 |
Neg logit contributions | |
wash | -1.649 |
↑ | -1.629 |
pak | -1.550 |
kat | -1.515 |
gross | -1.509 |
Token | mastering |
Token ID | 45116 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
wash | +0.119 |
↑ | +0.118 |
pak | +0.112 |
kat | +0.109 |
gross | +0.109 |
Neg logit contributions | |
AST | -0.099 |
elaide | -0.095 |
igree | -0.094 |
outh | -0.093 |
ovember | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
AST | +0.416 |
elaide | +0.395 |
igree | +0.390 |
outh | +0.389 |
ovember | +0.387 |
Neg logit contributions | |
wash | -0.545 |
↑ | -0.539 |
pak | -0.514 |
kat | -0.500 |
gross | -0.500 |
Token | books |
Token ID | 3835 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
wash | +0.285 |
↑ | +0.282 |
pak | +0.268 |
kat | +0.262 |
gross | +0.261 |
Neg logit contributions | |
AST | -0.220 |
elaide | -0.210 |
igree | -0.207 |
outh | -0.206 |
ovember | -0.205 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
wash | +0.841 |
↑ | +0.830 |
pak | +0.789 |
kat | +0.772 |
gross | +0.768 |
Neg logit contributions | |
AST | -0.709 |
elaide | -0.680 |
igree | -0.671 |
outh | -0.669 |
ovember | -0.666 |
Token | and |
Token ID | 290 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
wash | +0.229 |
↑ | +0.226 |
pak | +0.215 |
kat | +0.209 |
gross | +0.208 |
Neg logit contributions | |
AST | -0.216 |
elaide | -0.207 |
igree | -0.204 |
outh | -0.204 |
ovember | -0.203 |
Token | other |
Token ID | 584 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
wash | +0.150 |
↑ | +0.148 |
pak | +0.141 |
kat | +0.137 |
gross | +0.137 |
Neg logit contributions | |
AST | -0.131 |
elaide | -0.125 |
igree | -0.124 |
outh | -0.123 |
ovember | -0.123 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
wash | +0.330 |
↑ | +0.324 |
pak | +0.307 |
kat | +0.299 |
gross | +0.298 |
Neg logit contributions | |
AST | -0.335 |
elaide | -0.321 |
igree | -0.317 |
outh | -0.316 |
ovember | -0.315 |
Token | abilia |
Token ID | 48249 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
wash | +2.763 |
↑ | +2.735 |
pak | +2.635 |
kat | +2.588 |
gross | +2.573 |
Neg logit contributions | |
AST | -1.253 |
elaide | -1.181 |
outh | -1.150 |
igree | -1.145 |
ovember | -1.145 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
AST | +0.097 |
elaide | +0.092 |
igree | +0.091 |
outh | +0.091 |
ovember | +0.090 |
Neg logit contributions | |
wash | -0.117 |
↑ | -0.115 |
pak | -0.110 |
gross | -0.107 |
kat | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
wash | +0.250 |
↑ | +0.247 |
pak | +0.234 |
kat | +0.228 |
gross | +0.227 |
Neg logit contributions | |
AST | -0.227 |
elaide | -0.218 |
igree | -0.215 |
outh | -0.214 |
ovember | -0.214 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
wash | +0.264 |
↑ | +0.259 |
pak | +0.248 |
gross | +0.242 |
kat | +0.241 |
Neg logit contributions | |
AST | -0.223 |
outh | -0.210 |
elaide | -0.206 |
Monarch | -0.206 |
ADHD | -0.205 |
Token | About |
Token ID | 8585 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
wash | +0.208 |
↑ | +0.204 |
pak | +0.193 |
kat | +0.187 |
gross | +0.187 |
Neg logit contributions | |
AST | -0.235 |
elaide | -0.225 |
outh | -0.224 |
igree | -0.223 |
ovember | -0.222 |
Token | with |
Token ID | 351 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
wash | +0.271 |
↑ | +0.268 |
pak | +0.255 |
kat | +0.249 |
gross | +0.248 |
Neg logit contributions | |
AST | -0.212 |
elaide | -0.202 |
igree | -0.199 |
outh | -0.199 |
ovember | -0.198 |
Token | former |
Token ID | 1966 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
wash | +0.158 |
↑ | +0.156 |
pak | +0.149 |
kat | +0.146 |
gross | +0.145 |
Neg logit contributions | |
AST | -0.119 |
elaide | -0.113 |
igree | -0.112 |
outh | -0.111 |
ovember | -0.111 |
Token | Cuban |
Token ID | 18147 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
AST | +0.436 |
elaide | +0.408 |
Monarch | +0.406 |
outh | +0.404 |
igree | +0.401 |
Neg logit contributions | |
wash | -0.553 |
↑ | -0.545 |
pak | -0.517 |
kat | -0.507 |
gross | -0.506 |
Token | President |
Token ID | 1992 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
wash | +0.680 |
↑ | +0.672 |
pak | +0.641 |
kat | +0.623 |
gross | +0.622 |
Neg logit contributions | |
AST | -0.565 |
elaide | -0.546 |
igree | -0.539 |
ovember | -0.536 |
outh | -0.533 |
Token | Fidel |
Token ID | 42320 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
wash | +0.029 |
↑ | +0.029 |
pak | +0.027 |
kat | +0.027 |
gross | +0.027 |
Neg logit contributions | |
AST | -0.023 |
elaide | -0.022 |
igree | -0.022 |
ovember | -0.022 |
outh | -0.022 |
Token | Castro |
Token ID | 21193 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
wash | +1.361 |
↑ | +1.345 |
pak | +1.276 |
kat | +1.241 |
gross | +1.236 |
Neg logit contributions | |
AST | -1.274 |
elaide | -1.225 |
igree | -1.209 |
ovember | -1.205 |
outh | -1.203 |
Token | , |
Token ID | 11 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
wash | +2.196 |
↑ | +2.175 |
pak | +2.066 |
kat | +2.024 |
gross | +2.004 |
Neg logit contributions | |
AST | -1.797 |
elaide | -1.715 |
igree | -1.708 |
ovember | -1.700 |
outh | -1.687 |
Token | Cuban |
Token ID | 18147 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
wash | +0.297 |
↑ | +0.294 |
pak | +0.280 |
gross | +0.272 |
kat | +0.272 |
Neg logit contributions | |
AST | -0.226 |
elaide | -0.218 |
igree | -0.215 |
ovember | -0.214 |
outh | -0.213 |
Token | dissidents |
Token ID | 49913 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
wash | +0.743 |
↑ | +0.733 |
pak | +0.700 |
Net | +0.679 |
gross | +0.677 |
Neg logit contributions | |
AST | -0.696 |
elaide | -0.680 |
igree | -0.674 |
ovember | -0.667 |
outh | -0.657 |
Token | who |
Token ID | 508 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
wash | +0.913 |
↑ | +0.900 |
pak | +0.856 |
kat | +0.833 |
gross | +0.831 |
Neg logit contributions | |
AST | -0.824 |
elaide | -0.792 |
igree | -0.781 |
outh | -0.777 |
ovember | -0.776 |
Token | advocate |
Token ID | 12811 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
wash | +0.181 |
↑ | +0.179 |
pak | +0.169 |
kat | +0.164 |
gross | +0.164 |
Neg logit contributions | |
AST | -0.184 |
elaide | -0.177 |
igree | -0.175 |
outh | -0.174 |
ovember | -0.173 |
Token | dens |
Token ID | 29509 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
wash | +0.100 |
↑ | +0.098 |
pak | +0.094 |
kat | +0.091 |
gross | +0.091 |
Neg logit contributions | |
AST | -0.090 |
elaide | -0.085 |
igree | -0.084 |
outh | -0.084 |
ovember | -0.084 |
Token | er |
Token ID | 263 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
wash | +0.779 |
↑ | +0.770 |
pak | +0.735 |
kat | +0.718 |
gross | +0.716 |
Neg logit contributions | |
AST | -0.569 |
elaide | -0.542 |
igree | -0.532 |
outh | -0.532 |
ovember | -0.531 |
Token | than |
Token ID | 621 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
AST | +0.334 |
elaide | +0.318 |
igree | +0.314 |
outh | +0.313 |
ovember | +0.311 |
Neg logit contributions | |
wash | -0.399 |
↑ | -0.394 |
pak | -0.375 |
kat | -0.366 |
gross | -0.364 |
Token | zinc |
Token ID | 31861 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
wash | +0.611 |
↑ | +0.603 |
pak | +0.574 |
kat | +0.561 |
gross | +0.558 |
Neg logit contributions | |
AST | -0.479 |
elaide | -0.461 |
igree | -0.452 |
outh | -0.452 |
ovember | -0.451 |
Token | sulf |
Token ID | 22443 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
AST | +0.068 |
elaide | +0.065 |
igree | +0.064 |
ovember | +0.063 |
outh | +0.063 |
Neg logit contributions | |
wash | -0.091 |
↑ | -0.090 |
pak | -0.086 |
kat | -0.084 |
gross | -0.083 |
Token | ate |
Token ID | 378 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
wash | +0.669 |
↑ | +0.648 |
pak | +0.605 |
kat | +0.584 |
gross | +0.578 |
Neg logit contributions | |
AST | -1.130 |
elaide | -1.096 |
igree | -1.083 |
ovember | -1.079 |
outh | -1.075 |
Token | , |
Token ID | 11 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
wash | +2.152 |
↑ | +2.137 |
pak | +2.024 |
kat | +1.966 |
gross | +1.934 |
Neg logit contributions | |
AST | -1.772 |
elaide | -1.733 |
ovember | -1.698 |
igree | -1.693 |
outh | -1.677 |
Token | the |
Token ID | 262 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
wash | +0.076 |
↑ | +0.075 |
pak | +0.072 |
kat | +0.070 |
gross | +0.070 |
Neg logit contributions | |
AST | -0.054 |
elaide | -0.051 |
igree | -0.050 |
outh | -0.050 |
ovember | -0.050 |
Token | zinc |
Token ID | 31861 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
wash | +0.173 |
↑ | +0.170 |
pak | +0.162 |
kat | +0.158 |
gross | +0.158 |
Neg logit contributions | |
AST | -0.138 |
elaide | -0.130 |
igree | -0.129 |
outh | -0.129 |
ovember | -0.128 |
Token | solution |
Token ID | 4610 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
AST | +0.136 |
elaide | +0.130 |
igree | +0.128 |
outh | +0.127 |
ovember | +0.127 |
Neg logit contributions | |
wash | -0.195 |
↑ | -0.193 |
pak | -0.184 |
kat | -0.180 |
gross | -0.179 |
Token | floated |
Token ID | 29742 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
AST | +0.682 |
elaide | +0.648 |
outh | +0.641 |
igree | +0.641 |
ovember | +0.635 |
Neg logit contributions | |
wash | -0.721 |
↑ | -0.711 |
pak | -0.676 |
kat | -0.657 |
gross | -0.654 |
Token | The |
Token ID | 383 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
wash | +0.285 |
↑ | +0.281 |
pak | +0.268 |
kat | +0.262 |
gross | +0.261 |
Neg logit contributions | |
AST | -0.219 |
elaide | -0.209 |
igree | -0.206 |
outh | -0.205 |
ovember | -0.205 |
Token | Dice |
Token ID | 34381 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
AST | +0.196 |
elaide | +0.186 |
igree | +0.183 |
outh | +0.183 |
ovember | +0.182 |
Neg logit contributions | |
wash | -0.264 |
↑ | -0.261 |
pak | -0.249 |
kat | -0.243 |
gross | -0.242 |
Token | Tower |
Token ID | 8765 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
wash | +0.643 |
↑ | +0.635 |
pak | +0.606 |
kat | +0.591 |
gross | +0.588 |
Neg logit contributions | |
AST | -0.506 |
elaide | -0.483 |
igree | -0.476 |
outh | -0.474 |
ovember | -0.473 |
Token |
|
Token ID | 198 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
wash | +1.287 |
↑ | +1.271 |
pak | +1.206 |
kat | +1.175 |
gross | +1.169 |
Neg logit contributions | |
AST | -1.151 |
elaide | -1.105 |
igree | -1.090 |
outh | -1.085 |
ovember | -1.083 |
Token |
|
Token ID | 198 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
wash | +0.190 |
↑ | +0.186 |
pak | +0.179 |
gross | +0.175 |
kat | +0.174 |
Neg logit contributions | |
AST | -0.157 |
outh | -0.147 |
Monarch | -0.144 |
ADHD | -0.144 |
Lyme | -0.144 |
Token | http |
Token ID | 4023 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
wash | +0.086 |
↑ | +0.085 |
pak | +0.080 |
kat | +0.077 |
gross | +0.077 |
Neg logit contributions | |
AST | -0.098 |
elaide | -0.094 |
outh | -0.093 |
igree | -0.093 |
ovember | -0.093 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
wash | +1.785 |
↑ | +1.763 |
pak | +1.657 |
kat | +1.608 |
gross | +1.596 |
Neg logit contributions | |
AST | -2.160 |
elaide | -2.094 |
igree | -2.070 |
ovember | -2.051 |
outh | -2.049 |
Token | www |
Token ID | 2503 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
wash | +1.182 |
↑ | +1.145 |
pak | +1.070 |
kat | +1.031 |
gross | +1.024 |
Neg logit contributions | |
AST | -2.155 |
elaide | -2.085 |
igree | -2.056 |
ovember | -2.051 |
outh | -2.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
wash | +0.592 |
↑ | +0.583 |
pak | +0.556 |
gross | +0.542 |
kat | +0.540 |
Neg logit contributions | |
AST | -0.499 |
outh | -0.470 |
elaide | -0.469 |
igree | -0.463 |
ovember | -0.462 |
Token | board |
Token ID | 3526 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
wash | +0.029 |
↑ | +0.028 |
pak | +0.027 |
kat | +0.026 |
gross | +0.026 |
Neg logit contributions | |
AST | -0.034 |
elaide | -0.033 |
igree | -0.033 |
outh | -0.033 |
ovember | -0.033 |
Token | game |
Token ID | 6057 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
wash | +0.411 |
↑ | +0.405 |
pak | +0.386 |
kat | +0.380 |
gross | +0.378 |
Neg logit contributions | |
AST | -0.291 |
elaide | -0.278 |
igree | -0.273 |
outh | -0.272 |
ovember | -0.270 |
Token | [[ |
Token ID | 30109 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
AST | +0.065 |
elaide | +0.062 |
igree | +0.062 |
outh | +0.061 |
ovember | +0.061 |
Neg logit contributions | |
wash | -0.083 |
↑ | -0.082 |
pak | -0.078 |
kat | -0.076 |
gross | -0.076 |
Token | # |
Token ID | 2 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
wash | +0.806 |
↑ | +0.797 |
pak | +0.751 |
kat | +0.728 |
gross | +0.728 |
Neg logit contributions | |
AST | -0.836 |
elaide | -0.805 |
igree | -0.795 |
outh | -0.789 |
ovember | -0.789 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
wash | +0.484 |
↑ | +0.480 |
pak | +0.455 |
kat | +0.444 |
gross | +0.442 |
Neg logit contributions | |
AST | -0.399 |
elaide | -0.383 |
igree | -0.378 |
outh | -0.375 |
ovember | -0.374 |
Token | 1 |
Token ID | 352 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
AST | +0.231 |
elaide | +0.221 |
igree | +0.218 |
outh | +0.218 |
ovember | +0.217 |
Neg logit contributions | |
wash | -0.257 |
↑ | -0.253 |
pak | -0.241 |
kat | -0.234 |
gross | -0.234 |
Token | ]] |
Token ID | 11907 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
wash | +0.122 |
↑ | +0.121 |
pak | +0.116 |
kat | +0.113 |
gross | +0.113 |
Neg logit contributions | |
AST | -0.078 |
elaide | -0.074 |
igree | -0.073 |
outh | -0.073 |
ovember | -0.072 |
Token | < |
Token ID | 1279 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
AST | +0.425 |
elaide | +0.403 |
igree | +0.397 |
outh | +0.396 |
ovember | +0.394 |
Neg logit contributions | |
wash | -0.642 |
↑ | -0.634 |
pak | -0.606 |
kat | -0.592 |
gross | -0.591 |
Token | -> |
Token ID | 3784 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
↑ | +1.805 |
wash | +1.803 |
pak | +1.686 |
kat | +1.622 |
gross | +1.612 |
Neg logit contributions | |
AST | -2.101 |
elaide | -2.050 |
igree | -2.013 |
ovember | -2.004 |
outh | -1.991 |
Token | graph |
Token ID | 4823 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
wash | +0.490 |
↑ | +0.487 |
pak | +0.461 |
kat | +0.449 |
gross | +0.448 |
Neg logit contributions | |
AST | -0.384 |
elaide | -0.372 |
igree | -0.365 |
ovember | -0.363 |
outh | -0.363 |
Token | List |
Token ID | 8053 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
AST | +0.076 |
elaide | +0.072 |
igree | +0.072 |
outh | +0.071 |
ovember | +0.071 |
Neg logit contributions | |
wash | -0.081 |
↑ | -0.080 |
pak | -0.076 |
kat | -0.074 |
gross | -0.074 |
Token | [[ |
Token ID | 30109 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
AST | +0.206 |
elaide | +0.200 |
igree | +0.199 |
outh | +0.198 |
ovember | +0.198 |
Neg logit contributions | |
wash | -0.088 |
↑ | -0.087 |
pak | -0.079 |
kat | -0.075 |
gross | -0.074 |
Token | # |
Token ID | 2 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
wash | +0.736 |
↑ | +0.728 |
pak | +0.692 |
kat | +0.675 |
gross | +0.674 |
Neg logit contributions | |
AST | -0.565 |
elaide | -0.538 |
igree | -0.531 |
outh | -0.527 |
ovember | -0.525 |
Token | Ru |
Token ID | 11667 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
AST | +0.089 |
elaide | +0.082 |
igree | +0.081 |
outh | +0.081 |
ovember | +0.080 |
Neg logit contributions | |
wash | -0.196 |
↑ | -0.194 |
pak | -0.187 |
kat | -0.183 |
gross | -0.182 |
Token | iz |
Token ID | 528 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
AST | +0.754 |
outh | +0.741 |
elaide | +0.733 |
ovember | +0.726 |
igree | +0.725 |
Neg logit contributions | |
↑ | -0.554 |
wash | -0.552 |
pak | -0.518 |
gross | -0.493 |
kat | -0.490 |
Token | , |
Token ID | 11 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
wash | +0.754 |
↑ | +0.744 |
pak | +0.702 |
kat | +0.683 |
gross | +0.681 |
Neg logit contributions | |
AST | -0.786 |
elaide | -0.756 |
igree | -0.746 |
outh | -0.743 |
ovember | -0.741 |
Token | who |
Token ID | 508 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
AST | +0.063 |
elaide | +0.060 |
igree | +0.059 |
outh | +0.059 |
ovember | +0.059 |
Neg logit contributions | |
wash | -0.070 |
↑ | -0.069 |
pak | -0.065 |
kat | -0.063 |
gross | -0.063 |
Token | had |
Token ID | 550 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
AST | +0.134 |
elaide | +0.128 |
igree | +0.126 |
outh | +0.126 |
ovember | +0.126 |
Neg logit contributions | |
wash | -0.132 |
↑ | -0.130 |
pak | -0.124 |
kat | -0.120 |
gross | -0.120 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
wash | +0.337 |
↑ | +0.332 |
pak | +0.315 |
kat | +0.307 |
gross | +0.306 |
Neg logit contributions | |
AST | -0.316 |
elaide | -0.304 |
igree | -0.300 |
outh | -0.299 |
ovember | -0.298 |
Token | ized |
Token ID | 1143 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
wash | +1.780 |
↑ | +1.753 |
pak | +1.649 |
kat | +1.603 |
gross | +1.594 |
Neg logit contributions | |
AST | -2.128 |
elaide | -2.065 |
outh | -2.035 |
igree | -2.033 |
ovember | -2.025 |
Token | all |
Token ID | 477 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
AST | +0.219 |
elaide | +0.207 |
igree | +0.205 |
outh | +0.204 |
ovember | +0.203 |
Neg logit contributions | |
wash | -0.317 |
↑ | -0.313 |
pak | -0.300 |
kat | -0.293 |
gross | -0.292 |
Token | of |
Token ID | 286 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
wash | +0.009 |
↑ | +0.009 |
pak | +0.009 |
kat | +0.008 |
gross | +0.008 |
Neg logit contributions | |
AST | -0.006 |
elaide | -0.006 |
igree | -0.006 |
outh | -0.006 |
ovember | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
AST | +0.103 |
elaide | +0.097 |
igree | +0.096 |
outh | +0.096 |
ovember | +0.095 |
Neg logit contributions | |
wash | -0.157 |
↑ | -0.155 |
pak | -0.149 |
kat | -0.145 |
gross | -0.145 |
Token | winners |
Token ID | 14591 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
AST | +0.087 |
elaide | +0.082 |
igree | +0.082 |
outh | +0.081 |
Monarch | +0.081 |
Neg logit contributions | |
wash | -0.087 |
↑ | -0.085 |
pak | -0.081 |
kat | -0.079 |
gross | -0.078 |
Token | { |
Token ID | 1391 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
AST | +0.268 |
elaide | +0.251 |
igree | +0.247 |
outh | +0.246 |
ovember | +0.244 |
Neg logit contributions | |
wash | -0.464 |
↑ | -0.457 |
pak | -0.440 |
kat | -0.430 |
gross | -0.429 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
wash | +0.279 |
↑ | +0.274 |
pak | +0.257 |
kat | +0.248 |
gross | +0.247 |
Neg logit contributions | |
AST | -0.400 |
elaide | -0.386 |
igree | -0.382 |
outh | -0.382 |
ovember | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
wash | +0.187 |
↑ | +0.183 |
pak | +0.176 |
gross | +0.172 |
kat | +0.171 |
Neg logit contributions | |
AST | -0.128 |
outh | -0.119 |
elaide | -0.118 |
igree | -0.117 |
Monarch | -0.117 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
AST | +0.226 |
elaide | +0.216 |
igree | +0.213 |
outh | +0.213 |
ovember | +0.212 |
Neg logit contributions | |
wash | -0.222 |
↑ | -0.218 |
pak | -0.206 |
kat | -0.201 |
gross | -0.200 |
Token | } |
Token ID | 92 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
wash | +0.411 |
↑ | +0.405 |
pak | +0.387 |
kat | +0.378 |
gross | +0.377 |
Neg logit contributions | |
AST | -0.306 |
elaide | -0.289 |
igree | -0.286 |
outh | -0.286 |
ovember | -0.284 |
Token | < |
Token ID | 1279 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
AST | +0.763 |
elaide | +0.721 |
igree | +0.711 |
outh | +0.710 |
ovember | +0.704 |
Neg logit contributions | |
wash | -0.988 |
↑ | -0.967 |
pak | -0.928 |
kat | -0.907 |
gross | -0.903 |
Token | -> |
Token ID | 3784 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
wash | +1.473 |
↑ | +1.458 |
pak | +1.353 |
kat | +1.305 |
gross | +1.284 |
Neg logit contributions | |
AST | -2.335 |
elaide | -2.274 |
igree | -2.247 |
outh | -2.230 |
ovember | -2.229 |
Token | { |
Token ID | 1391 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
wash | +0.681 |
↑ | +0.673 |
pak | +0.646 |
kat | +0.632 |
gross | +0.631 |
Neg logit contributions | |
AST | -0.380 |
elaide | -0.357 |
igree | -0.351 |
outh | -0.351 |
ovember | -0.348 |
Token | 1 |
Token ID | 16 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
wash | +0.179 |
↑ | +0.176 |
pak | +0.164 |
kat | +0.158 |
gross | +0.158 |
Neg logit contributions | |
AST | -0.267 |
elaide | -0.258 |
igree | -0.255 |
outh | -0.255 |
ovember | -0.254 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
wash | +0.218 |
↑ | +0.214 |
pak | +0.205 |
gross | +0.201 |
kat | +0.200 |
Neg logit contributions | |
AST | -0.150 |
outh | -0.140 |
elaide | -0.140 |
igree | -0.138 |
Monarch | -0.138 |
Token | 7 |
Token ID | 767 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
AST | +0.272 |
elaide | +0.260 |
igree | +0.257 |
outh | +0.256 |
ovember | +0.255 |
Neg logit contributions | |
wash | -0.264 |
↑ | -0.260 |
pak | -0.246 |
kat | -0.239 |
gross | -0.239 |
Token | added |
Token ID | 2087 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
wash | +0.032 |
↑ | +0.031 |
pak | +0.029 |
kat | +0.029 |
gross | +0.028 |
Neg logit contributions | |
AST | -0.031 |
elaide | -0.030 |
igree | -0.030 |
outh | -0.030 |
ovember | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
wash | +0.343 |
↑ | +0.337 |
pak | +0.319 |
kat | +0.310 |
gross | +0.309 |
Neg logit contributions | |
AST | -0.353 |
elaide | -0.339 |
igree | -0.335 |
outh | -0.333 |
ovember | -0.333 |
Token | Because |
Token ID | 4362 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
AST | +0.202 |
elaide | +0.192 |
outh | +0.190 |
igree | +0.190 |
ovember | +0.189 |
Neg logit contributions | |
wash | -0.224 |
↑ | -0.221 |
pak | -0.210 |
kat | -0.205 |
gross | -0.204 |
Token | copper |
Token ID | 15317 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
AST | +0.325 |
elaide | +0.306 |
igree | +0.303 |
outh | +0.302 |
ovember | +0.300 |
Neg logit contributions | |
wash | -0.468 |
↑ | -0.463 |
pak | -0.442 |
kat | -0.433 |
gross | -0.431 |
Token | sulf |
Token ID | 22443 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
AST | +0.068 |
elaide | +0.065 |
igree | +0.064 |
outh | +0.064 |
ovember | +0.063 |
Neg logit contributions | |
wash | -0.099 |
↑ | -0.098 |
pak | -0.093 |
kat | -0.091 |
gross | -0.091 |
Token | ate |
Token ID | 378 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
wash | +0.555 |
↑ | +0.546 |
pak | +0.508 |
kat | +0.488 |
gross | +0.487 |
Neg logit contributions | |
AST | -0.900 |
elaide | -0.869 |
igree | -0.861 |
outh | -0.861 |
ovember | -0.857 |
Token | is |
Token ID | 318 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
wash | +1.889 |
↑ | +1.870 |
pak | +1.751 |
kat | +1.705 |
gross | +1.687 |
Neg logit contributions | |
AST | -1.896 |
elaide | -1.854 |
ovember | -1.824 |
igree | -1.822 |
outh | -1.810 |
Token | dens |
Token ID | 29509 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
wash | +0.100 |
↑ | +0.098 |
pak | +0.094 |
kat | +0.091 |
gross | +0.091 |
Neg logit contributions | |
AST | -0.090 |
elaide | -0.085 |
igree | -0.084 |
outh | -0.084 |
ovember | -0.084 |
Token | er |
Token ID | 263 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
wash | +0.779 |
↑ | +0.770 |
pak | +0.735 |
kat | +0.718 |
gross | +0.716 |
Neg logit contributions | |
AST | -0.569 |
elaide | -0.542 |
igree | -0.532 |
outh | -0.532 |
ovember | -0.531 |
Token | than |
Token ID | 621 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
AST | +0.334 |
elaide | +0.318 |
igree | +0.314 |
outh | +0.313 |
ovember | +0.311 |
Neg logit contributions | |
wash | -0.399 |
↑ | -0.394 |
pak | -0.375 |
kat | -0.366 |
gross | -0.364 |
Token | zinc |
Token ID | 31861 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
wash | +0.611 |
↑ | +0.603 |
pak | +0.574 |
kat | +0.561 |
gross | +0.558 |
Neg logit contributions | |
AST | -0.479 |
elaide | -0.461 |
igree | -0.452 |
outh | -0.452 |
ovember | -0.451 |
Token | in |
Token ID | 287 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
AST | +0.361 |
elaide | +0.344 |
igree | +0.339 |
outh | +0.339 |
ovember | +0.337 |
Neg logit contributions | |
wash | -0.431 |
↑ | -0.426 |
pak | -0.405 |
kat | -0.395 |
gross | -0.395 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
wash | +0.161 |
↑ | +0.159 |
pak | +0.152 |
kat | +0.149 |
gross | +0.148 |
Neg logit contributions | |
AST | -0.114 |
elaide | -0.108 |
igree | -0.106 |
outh | -0.106 |
ovember | -0.106 |
Token | background |
Token ID | 4469 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
wash | +0.072 |
↑ | +0.071 |
pak | +0.067 |
gross | +0.065 |
kat | +0.064 |
Neg logit contributions | |
AST | -0.089 |
elaide | -0.086 |
igree | -0.085 |
outh | -0.085 |
ovember | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
wash | +0.666 |
↑ | +0.656 |
pak | +0.624 |
kat | +0.607 |
gross | +0.606 |
Neg logit contributions | |
AST | -0.578 |
elaide | -0.552 |
igree | -0.546 |
outh | -0.543 |
ovember | -0.542 |
Token | Survivor |
Token ID | 23740 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
wash | +0.133 |
↑ | +0.131 |
pak | +0.125 |
kat | +0.121 |
gross | +0.121 |
Neg logit contributions | |
AST | -0.118 |
elaide | -0.113 |
igree | -0.111 |
outh | -0.111 |
ovember | -0.111 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
wash | +0.363 |
↑ | +0.358 |
pak | +0.340 |
kat | +0.331 |
gross | +0.331 |
Neg logit contributions | |
AST | -0.307 |
elaide | -0.293 |
igree | -0.289 |
outh | -0.288 |
ovember | -0.287 |
Token | abilia |
Token ID | 48249 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
wash | +2.587 |
↑ | +2.559 |
pak | +2.459 |
kat | +2.412 |
gross | +2.399 |
Neg logit contributions | |
AST | -1.191 |
elaide | -1.123 |
outh | -1.091 |
igree | -1.089 |
ovember | -1.084 |
Token | throughout |
Token ID | 3690 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
AST | +0.308 |
elaide | +0.292 |
igree | +0.288 |
outh | +0.288 |
ovember | +0.286 |
Neg logit contributions | |
wash | -0.404 |
↑ | -0.398 |
pak | -0.380 |
gross | -0.371 |
kat | -0.370 |
Token | the |
Token ID | 262 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
AST | +0.081 |
elaide | +0.077 |
igree | +0.075 |
outh | +0.075 |
ovember | +0.075 |
Neg logit contributions | |
wash | -0.119 |
↑ | -0.117 |
pak | -0.112 |
kat | -0.110 |
gross | -0.109 |
Token | queue |
Token ID | 16834 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
wash | +0.177 |
↑ | +0.175 |
pak | +0.167 |
kat | +0.163 |
gross | +0.163 |
Neg logit contributions | |
AST | -0.122 |
elaide | -0.115 |
igree | -0.113 |
outh | -0.113 |
ovember | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
AST | +0.296 |
elaide | +0.282 |
igree | +0.277 |
outh | +0.277 |
ovember | +0.274 |
Neg logit contributions | |
wash | -0.406 |
↑ | -0.401 |
pak | -0.384 |
gross | -0.374 |
kat | -0.374 |
Token | the |
Token ID | 262 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
wash | +0.088 |
↑ | +0.087 |
pak | +0.083 |
kat | +0.081 |
gross | +0.080 |
Neg logit contributions | |
AST | -0.070 |
elaide | -0.067 |
igree | -0.066 |
outh | -0.066 |
ovember | -0.066 |
Token | name |
Token ID | 1438 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
wash | +0.184 |
↑ | +0.181 |
pak | +0.172 |
kat | +0.168 |
gross | +0.167 |
Neg logit contributions | |
AST | -0.155 |
elaide | -0.147 |
igree | -0.145 |
outh | -0.145 |
ovember | -0.144 |
Token | a |
Token ID | 257 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
wash | +0.265 |
↑ | +0.262 |
pak | +0.250 |
kat | +0.243 |
gross | +0.242 |
Neg logit contributions | |
AST | -0.220 |
elaide | -0.209 |
igree | -0.207 |
outh | -0.206 |
ovember | -0.205 |
Token | teenage |
Token ID | 16330 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
wash | +0.078 |
↑ | +0.077 |
pak | +0.073 |
kat | +0.071 |
gross | +0.071 |
Neg logit contributions | |
AST | -0.062 |
elaide | -0.059 |
igree | -0.058 |
outh | -0.058 |
ovember | -0.058 |
Token | boy |
Token ID | 2933 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
wash | +0.157 |
↑ | +0.155 |
pak | +0.149 |
kat | +0.145 |
gross | +0.145 |
Neg logit contributions | |
AST | -0.089 |
elaide | -0.085 |
igree | -0.083 |
ovember | -0.082 |
outh | -0.082 |
Token | memor |
Token ID | 16181 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
AST | +0.860 |
elaide | +0.818 |
outh | +0.814 |
igree | +0.809 |
ovember | +0.805 |
Neg logit contributions | |
wash | -0.913 |
↑ | -0.904 |
pak | -0.857 |
gross | -0.832 |
kat | -0.827 |
Token | ably |
Token ID | 1346 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
wash | +1.470 |
↑ | +1.439 |
pak | +1.343 |
kat | +1.300 |
gross | +1.291 |
Neg logit contributions | |
AST | -2.261 |
elaide | -2.186 |
outh | -2.162 |
igree | -2.161 |
ovember | -2.152 |
Token | gives |
Token ID | 3607 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
wash | +0.436 |
↑ | +0.430 |
pak | +0.407 |
kat | +0.396 |
gross | +0.395 |
Neg logit contributions | |
AST | -0.426 |
elaide | -0.407 |
outh | -0.402 |
igree | -0.402 |
ovember | -0.400 |
Token | his |
Token ID | 465 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
wash | +0.009 |
↑ | +0.009 |
pak | +0.008 |
kat | +0.008 |
gross | +0.008 |
Neg logit contributions | |
AST | -0.009 |
elaide | -0.009 |
outh | -0.009 |
igree | -0.009 |
Monarch | -0.009 |
Token | penis |
Token ID | 16360 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
wash | +0.172 |
↑ | +0.169 |
pak | +0.161 |
kat | +0.157 |
gross | +0.157 |
Neg logit contributions | |
AST | -0.139 |
elaide | -0.132 |
igree | -0.131 |
outh | -0.130 |
ovember | -0.130 |
Token | in |
Token ID | 287 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
AST | +0.134 |
elaide | +0.128 |
igree | +0.127 |
outh | +0.126 |
ovember | +0.126 |
Neg logit contributions | |
wash | -0.140 |
↑ | -0.138 |
pak | -0.131 |
kat | -0.127 |
gross | -0.127 |
Token | / |
Token ID | 14 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
wash | +0.206 |
↑ | +0.203 |
pak | +0.193 |
kat | +0.188 |
gross | +0.188 |
Neg logit contributions | |
AST | -0.186 |
elaide | -0.176 |
outh | -0.174 |
igree | -0.174 |
ovember | -0.172 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
wash | +0.181 |
↑ | +0.177 |
pak | +0.166 |
kat | +0.160 |
gross | +0.159 |
Neg logit contributions | |
AST | -0.275 |
elaide | -0.264 |
outh | -0.262 |
igree | -0.262 |
ovember | -0.260 |
Token | " |
Token ID | 1 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
AST | +0.229 |
elaide | +0.218 |
igree | +0.217 |
outh | +0.216 |
ovember | +0.214 |
Neg logit contributions | |
wash | -0.209 |
↑ | -0.205 |
pak | -0.195 |
kat | -0.189 |
gross | -0.188 |
Token |
|
Token ID | 198 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
wash | +0.177 |
↑ | +0.174 |
pak | +0.165 |
kat | +0.161 |
gross | +0.160 |
Neg logit contributions | |
AST | -0.173 |
elaide | -0.166 |
igree | -0.164 |
outh | -0.163 |
ovember | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
AST | +0.006 |
outh | +0.005 |
Monarch | +0.005 |
ADHD | +0.005 |
Lyme | +0.005 |
Neg logit contributions | |
wash | -0.007 |
↑ | -0.007 |
pak | -0.006 |
gross | -0.006 |
kat | -0.006 |
Token | http |
Token ID | 4023 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
AST | +0.049 |
elaide | +0.047 |
outh | +0.047 |
igree | +0.047 |
ovember | +0.046 |
Neg logit contributions | |
wash | -0.035 |
↑ | -0.035 |
pak | -0.033 |
kat | -0.031 |
gross | -0.031 |
Token | :// |
Token ID | 1378 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
wash | +1.681 |
↑ | +1.660 |
pak | +1.562 |
kat | +1.515 |
gross | +1.502 |
Neg logit contributions | |
AST | -2.036 |
elaide | -1.976 |
igree | -1.954 |
ovember | -1.935 |
outh | -1.934 |
Token | the |
Token ID | 1169 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
wash | +1.216 |
↑ | +1.189 |
pak | +1.114 |
kat | +1.075 |
gross | +1.068 |
Neg logit contributions | |
AST | -1.897 |
elaide | -1.832 |
igree | -1.811 |
outh | -1.807 |
ovember | -1.807 |
Token | hook |
Token ID | 25480 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
AST | +0.067 |
elaide | +0.064 |
igree | +0.063 |
outh | +0.063 |
ovember | +0.063 |
Neg logit contributions | |
wash | -0.055 |
↑ | -0.054 |
pak | -0.051 |
kat | -0.049 |
gross | -0.049 |
Token | journal |
Token ID | 24891 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
AST | +0.927 |
elaide | +0.895 |
igree | +0.889 |
outh | +0.889 |
ovember | +0.880 |
Neg logit contributions | |
wash | -0.871 |
↑ | -0.868 |
pak | -0.809 |
gross | -0.787 |
kat | -0.786 |
Token | . |
Token ID | 13 |
Feature activation | -5.95e-03 |
Pos logit contributions | |
AST | +1.219 |
elaide | +1.177 |
outh | +1.168 |
igree | +1.158 |
ovember | +1.148 |
Neg logit contributions | |
↑ | -1.453 |
wash | -1.453 |
pak | -1.359 |
gross | -1.328 |
kat | -1.319 |
Token | { |
Token ID | 1391 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
AST | +0.360 |
elaide | +0.343 |
outh | +0.339 |
igree | +0.338 |
ovember | +0.335 |
Neg logit contributions | |
wash | -0.387 |
↑ | -0.378 |
pak | -0.362 |
kat | -0.351 |
gross | -0.351 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
wash | +0.287 |
↑ | +0.281 |
pak | +0.264 |
kat | +0.254 |
gross | +0.254 |
Neg logit contributions | |
AST | -0.411 |
elaide | -0.396 |
igree | -0.392 |
outh | -0.392 |
ovember | -0.390 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
wash | +0.191 |
↑ | +0.188 |
pak | +0.180 |
gross | +0.176 |
kat | +0.176 |
Neg logit contributions | |
AST | -0.133 |
outh | -0.124 |
elaide | -0.123 |
igree | -0.122 |
ovember | -0.121 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
AST | +0.215 |
elaide | +0.206 |
igree | +0.203 |
outh | +0.203 |
ovember | +0.202 |
Neg logit contributions | |
wash | -0.212 |
↑ | -0.208 |
pak | -0.198 |
kat | -0.192 |
gross | -0.192 |
Token | } |
Token ID | 92 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
wash | +0.290 |
↑ | +0.286 |
pak | +0.271 |
kat | +0.263 |
gross | +0.262 |
Neg logit contributions | |
AST | -0.294 |
elaide | -0.282 |
igree | -0.279 |
outh | -0.278 |
ovember | -0.277 |
Token | < |
Token ID | 1279 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
AST | +0.899 |
elaide | +0.850 |
outh | +0.840 |
igree | +0.839 |
ovember | +0.832 |
Neg logit contributions | |
wash | -1.090 |
↑ | -1.066 |
pak | -1.022 |
kat | -0.996 |
gross | -0.995 |
Token | -> |
Token ID | 3784 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
wash | +1.412 |
↑ | +1.405 |
pak | +1.298 |
kat | +1.251 |
gross | +1.222 |
Neg logit contributions | |
AST | -2.298 |
elaide | -2.227 |
igree | -2.202 |
outh | -2.195 |
ovember | -2.190 |
Token | { |
Token ID | 1391 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
wash | +0.586 |
↑ | +0.581 |
pak | +0.555 |
kat | +0.543 |
gross | +0.541 |
Neg logit contributions | |
AST | -0.350 |
elaide | -0.332 |
igree | -0.327 |
outh | -0.326 |
ovember | -0.325 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
wash | +0.205 |
↑ | +0.201 |
pak | +0.189 |
kat | +0.182 |
gross | +0.181 |
Neg logit contributions | |
AST | -0.296 |
elaide | -0.285 |
igree | -0.282 |
outh | -0.282 |
ovember | -0.281 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
wash | +0.242 |
↑ | +0.237 |
pak | +0.228 |
gross | +0.223 |
kat | +0.222 |
Neg logit contributions | |
AST | -0.164 |
outh | -0.153 |
elaide | -0.151 |
Monarch | -0.150 |
igree | -0.149 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
AST | +0.290 |
elaide | +0.276 |
outh | +0.273 |
igree | +0.272 |
ovember | +0.271 |
Neg logit contributions | |
wash | -0.282 |
↑ | -0.277 |
pak | -0.263 |
kat | -0.255 |
gross | -0.255 |
Token | distinct |
Token ID | 7310 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
wash | +0.113 |
↑ | +0.112 |
pak | +0.106 |
kat | +0.103 |
gross | +0.103 |
Neg logit contributions | |
AST | -0.103 |
elaide | -0.099 |
igree | -0.098 |
outh | -0.098 |
ovember | -0.097 |
Token | flavor |
Token ID | 9565 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
AST | +0.715 |
elaide | +0.674 |
igree | +0.667 |
outh | +0.666 |
ovember | +0.657 |
Neg logit contributions | |
wash | -0.990 |
↑ | -0.979 |
pak | -0.934 |
gross | -0.910 |
kat | -0.909 |
Token | and |
Token ID | 290 |
Feature activation | -6.75e-03 |
Pos logit contributions | |
wash | +0.870 |
↑ | +0.858 |
pak | +0.815 |
kat | +0.793 |
gross | +0.791 |
Neg logit contributions | |
AST | -0.795 |
elaide | -0.761 |
igree | -0.751 |
outh | -0.750 |
ovember | -0.747 |
Token | slightly |
Token ID | 4622 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
AST | +0.012 |
elaide | +0.011 |
outh | +0.011 |
igree | +0.011 |
ovember | +0.011 |
Neg logit contributions | |
wash | -0.012 |
↑ | -0.012 |
pak | -0.012 |
kat | -0.011 |
gross | -0.011 |
Token | green |
Token ID | 4077 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
wash | +0.998 |
↑ | +0.984 |
pak | +0.933 |
kat | +0.909 |
gross | +0.906 |
Neg logit contributions | |
AST | -0.901 |
elaide | -0.867 |
igree | -0.856 |
ovember | -0.852 |
outh | -0.850 |
Token | color |
Token ID | 3124 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
wash | +0.928 |
↑ | +0.918 |
pak | +0.876 |
kat | +0.853 |
gross | +0.851 |
Neg logit contributions | |
AST | -0.770 |
elaide | -0.732 |
igree | -0.725 |
outh | -0.725 |
ovember | -0.715 |
Token | and |
Token ID | 290 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
wash | +1.919 |
↑ | +1.888 |
pak | +1.787 |
kat | +1.739 |
gross | +1.737 |
Neg logit contributions | |
AST | -1.761 |
elaide | -1.696 |
igree | -1.665 |
ovember | -1.664 |
outh | -1.660 |
Token | is |
Token ID | 318 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
wash | +0.161 |
↑ | +0.159 |
pak | +0.151 |
kat | +0.147 |
gross | +0.146 |
Neg logit contributions | |
AST | -0.148 |
elaide | -0.140 |
igree | -0.139 |
outh | -0.139 |
ovember | -0.138 |
Token | easier |
Token ID | 4577 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
wash | +0.268 |
↑ | +0.264 |
pak | +0.251 |
kat | +0.244 |
gross | +0.243 |
Neg logit contributions | |
AST | -0.247 |
elaide | -0.237 |
igree | -0.233 |
outh | -0.233 |
ovember | -0.232 |
Token | to |
Token ID | 284 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
AST | +0.114 |
elaide | +0.110 |
outh | +0.109 |
igree | +0.108 |
ovember | +0.108 |
Neg logit contributions | |
wash | -0.099 |
↑ | -0.098 |
pak | -0.092 |
kat | -0.089 |
gross | -0.089 |
Token | make |
Token ID | 787 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
wash | +0.141 |
↑ | +0.139 |
pak | +0.133 |
kat | +0.130 |
gross | +0.129 |
Neg logit contributions | |
AST | -0.098 |
elaide | -0.093 |
igree | -0.092 |
outh | -0.091 |
ovember | -0.091 |
Token | joke |
Token ID | 9707 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
AST | +0.162 |
elaide | +0.157 |
igree | +0.156 |
ovember | +0.154 |
outh | +0.154 |
Neg logit contributions | |
wash | -0.221 |
↑ | -0.217 |
pak | -0.206 |
kat | -0.204 |
gross | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
wash | +0.452 |
↑ | +0.446 |
pak | +0.424 |
kat | +0.413 |
gross | +0.412 |
Neg logit contributions | |
AST | -0.395 |
elaide | -0.378 |
igree | -0.373 |
outh | -0.372 |
ovember | -0.370 |
Token | and |
Token ID | 290 |
Feature activation | -4.37e-04 |
Pos logit contributions | |
AST | +0.041 |
elaide | +0.039 |
igree | +0.039 |
outh | +0.039 |
ovember | +0.038 |
Neg logit contributions | |
wash | -0.046 |
↑ | -0.045 |
pak | -0.043 |
kat | -0.042 |
gross | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
AST | +0.001 |
elaide | +0.001 |
igree | +0.001 |
outh | +0.001 |
ovember | +0.001 |
Neg logit contributions | |
wash | -0.001 |
↑ | -0.001 |
pak | -0.001 |
kat | -0.001 |
gross | -0.001 |
Token | steep |
Token ID | 14559 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
wash | +0.158 |
↑ | +0.156 |
pak | +0.149 |
kat | +0.145 |
gross | +0.145 |
Neg logit contributions | |
AST | -0.125 |
elaide | -0.118 |
igree | -0.117 |
outh | -0.117 |
ovember | -0.116 |
Token | incl |
Token ID | 13358 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
AST | +0.319 |
elaide | +0.304 |
igree | +0.301 |
outh | +0.300 |
ovember | +0.297 |
Neg logit contributions | |
wash | -0.359 |
↑ | -0.354 |
pak | -0.337 |
kat | -0.328 |
gross | -0.328 |
Token | ines |
Token ID | 1127 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
AST | +1.625 |
outh | +1.521 |
igree | +1.500 |
elaide | +1.489 |
Monarch | +1.410 |
Neg logit contributions | |
wash | -3.147 |
↑ | -3.071 |
pak | -3.031 |
kat | -2.950 |
200000 | -2.927 |
Token | can |
Token ID | 460 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
AST | +0.917 |
elaide | +0.874 |
outh | +0.866 |
igree | +0.866 |
ovember | +0.859 |
Neg logit contributions | |
wash | -0.926 |
↑ | -0.915 |
pak | -0.867 |
kat | -0.844 |
gross | -0.841 |
Token | be |
Token ID | 307 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
AST | +0.083 |
elaide | +0.079 |
igree | +0.078 |
outh | +0.078 |
ovember | +0.078 |
Neg logit contributions | |
wash | -0.092 |
↑ | -0.090 |
pak | -0.086 |
kat | -0.083 |
gross | -0.083 |
Token | treacherous |
Token ID | 45365 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
wash | +0.076 |
↑ | +0.074 |
pak | +0.071 |
gross | +0.069 |
kat | +0.069 |
Neg logit contributions | |
AST | -0.066 |
elaide | -0.063 |
igree | -0.062 |
ovember | -0.062 |
outh | -0.062 |
Token | with |
Token ID | 351 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
AST | +0.212 |
elaide | +0.202 |
igree | +0.200 |
outh | +0.199 |
ovember | +0.198 |
Neg logit contributions | |
wash | -0.238 |
↑ | -0.235 |
pak | -0.224 |
kat | -0.218 |
gross | -0.217 |
Token | a |
Token ID | 257 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
wash | +0.046 |
↑ | +0.046 |
pak | +0.044 |
kat | +0.043 |
gross | +0.042 |
Neg logit contributions | |
AST | -0.037 |
elaide | -0.035 |
igree | -0.035 |
outh | -0.034 |
ovember | -0.034 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
wash | +0.010 |
↑ | +0.009 |
pak | +0.009 |
kat | +0.009 |
gross | +0.009 |
Neg logit contributions | |
AST | -0.009 |
elaide | -0.008 |
igree | -0.008 |
outh | -0.008 |
ovember | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
wash | +0.202 |
↑ | +0.199 |
pak | +0.189 |
kat | +0.184 |
gross | +0.183 |
Neg logit contributions | |
AST | -0.186 |
elaide | -0.179 |
igree | -0.176 |
outh | -0.176 |
ovember | -0.175 |
Token | 000 |
Token ID | 830 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
AST | +0.130 |
elaide | +0.126 |
igree | +0.125 |
outh | +0.125 |
ovember | +0.124 |
Neg logit contributions | |
wash | -0.068 |
↑ | -0.067 |
pak | -0.061 |
kat | -0.059 |
gross | -0.058 |
Token | ft |
Token ID | 10117 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
AST | +0.257 |
elaide | +0.237 |
igree | +0.234 |
outh | +0.233 |
ovember | +0.231 |
Neg logit contributions | |
wash | -0.558 |
↑ | -0.552 |
pak | -0.532 |
kat | -0.520 |
gross | -0.519 |
Token | incl |
Token ID | 13358 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
wash | +0.554 |
↑ | +0.547 |
pak | +0.520 |
kat | +0.507 |
gross | +0.505 |
Neg logit contributions | |
AST | -0.463 |
elaide | -0.443 |
igree | -0.437 |
outh | -0.436 |
ovember | -0.435 |
Token | ine |
Token ID | 500 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
AST | +1.822 |
outh | +1.714 |
igree | +1.712 |
elaide | +1.707 |
ovember | +1.641 |
Neg logit contributions | |
wash | -2.930 |
↑ | -2.877 |
pak | -2.805 |
kat | -2.722 |
gross | -2.698 |
Token | over |
Token ID | 625 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
AST | +0.642 |
elaide | +0.607 |
igree | +0.602 |
outh | +0.600 |
ovember | +0.595 |
Neg logit contributions | |
wash | -0.799 |
↑ | -0.791 |
pak | -0.756 |
kat | -0.734 |
gross | -0.733 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
wash | +0.205 |
↑ | +0.203 |
pak | +0.194 |
kat | +0.189 |
gross | +0.189 |
Neg logit contributions | |
AST | -0.149 |
elaide | -0.141 |
igree | -0.140 |
outh | -0.139 |
ovember | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
wash | +0.236 |
↑ | +0.233 |
pak | +0.222 |
kat | +0.216 |
gross | +0.216 |
Neg logit contributions | |
AST | -0.182 |
elaide | -0.175 |
igree | -0.172 |
outh | -0.171 |
ovember | -0.171 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
AST | +0.178 |
elaide | +0.169 |
outh | +0.169 |
igree | +0.168 |
ovember | +0.168 |
Neg logit contributions | |
wash | -0.149 |
↑ | -0.146 |
pak | -0.138 |
gross | -0.134 |
kat | -0.133 |
Token | equivalent |
Token ID | 7548 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
AST | +0.385 |
outh | +0.361 |
elaide | +0.361 |
igree | +0.359 |
Monarch | +0.358 |
Neg logit contributions | |
wash | -0.385 |
↑ | -0.379 |
pak | -0.360 |
kat | -0.348 |
gross | -0.348 |
Token | of |
Token ID | 286 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
AST | +0.515 |
elaide | +0.482 |
outh | +0.478 |
igree | +0.476 |
ovember | +0.472 |
Neg logit contributions | |
wash | -0.711 |
↑ | -0.703 |
pak | -0.670 |
kat | -0.656 |
gross | -0.653 |
Token | an |
Token ID | 281 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
AST | +0.251 |
elaide | +0.236 |
outh | +0.235 |
igree | +0.233 |
ovember | +0.232 |
Neg logit contributions | |
wash | -0.296 |
↑ | -0.292 |
pak | -0.278 |
kat | -0.271 |
gross | -0.269 |
Token | Olympic |
Token ID | 11514 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
AST | +0.284 |
elaide | +0.270 |
igree | +0.267 |
outh | +0.267 |
ovember | +0.265 |
Neg logit contributions | |
wash | -0.337 |
↑ | -0.333 |
pak | -0.317 |
kat | -0.309 |
gross | -0.308 |
Token | gymn |
Token ID | 38581 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
AST | +0.376 |
elaide | +0.354 |
outh | +0.350 |
igree | +0.350 |
ovember | +0.347 |
Neg logit contributions | |
wash | -0.542 |
↑ | -0.537 |
pak | -0.512 |
gross | -0.500 |
kat | -0.499 |
Token | astics |
Token ID | 24232 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
AST | +0.365 |
outh | +0.344 |
elaide | +0.343 |
igree | +0.341 |
ovember | +0.339 |
Neg logit contributions | |
wash | -0.470 |
↑ | -0.469 |
pak | -0.444 |
gross | -0.434 |
kat | -0.430 |
Token | routine |
Token ID | 8027 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
AST | +1.954 |
outh | +1.775 |
igree | +1.752 |
Monarch | +1.750 |
ADHD | +1.748 |
Neg logit contributions | |
wash | -2.792 |
↑ | -2.766 |
pak | -2.637 |
gross | -2.597 |
kat | -2.565 |
Token | for |
Token ID | 329 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
AST | +1.388 |
elaide | +1.301 |
outh | +1.291 |
igree | +1.290 |
ovember | +1.277 |
Neg logit contributions | |
wash | -1.678 |
↑ | -1.661 |
pak | -1.588 |
kat | -1.546 |
gross | -1.543 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
AST | +0.278 |
elaide | +0.261 |
outh | +0.259 |
igree | +0.258 |
ovember | +0.257 |
Neg logit contributions | |
wash | -0.353 |
↑ | -0.350 |
pak | -0.333 |
kat | -0.325 |
gross | -0.324 |
Token | speaker |
Token ID | 10834 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
AST | +0.265 |
elaide | +0.250 |
outh | +0.248 |
igree | +0.247 |
ovember | +0.246 |
Neg logit contributions | |
wash | -0.325 |
↑ | -0.321 |
pak | -0.306 |
kat | -0.298 |
gross | -0.298 |
Token | � |
Token ID | 447 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
wash | +0.516 |
↑ | +0.509 |
pak | +0.484 |
kat | +0.471 |
gross | +0.470 |
Neg logit contributions | |
AST | -0.451 |
elaide | -0.431 |
igree | -0.426 |
outh | -0.425 |
ovember | -0.423 |
Token | quickly |
Token ID | 2952 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
wash | +0.026 |
↑ | +0.026 |
pak | +0.025 |
kat | +0.024 |
gross | +0.024 |
Neg logit contributions | |
AST | -0.027 |
elaide | -0.025 |
igree | -0.025 |
outh | -0.025 |
ovember | -0.025 |
Token | came |
Token ID | 1625 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
wash | +0.016 |
↑ | +0.016 |
pak | +0.015 |
kat | +0.015 |
gross | +0.015 |
Neg logit contributions | |
AST | -0.017 |
elaide | -0.016 |
igree | -0.016 |
outh | -0.016 |
ovember | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
AST | +0.122 |
elaide | +0.117 |
igree | +0.115 |
outh | +0.115 |
ovember | +0.115 |
Neg logit contributions | |
wash | -0.130 |
↑ | -0.128 |
pak | -0.122 |
kat | -0.118 |
gross | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
AST | +0.063 |
elaide | +0.060 |
igree | +0.059 |
outh | +0.059 |
ovember | +0.058 |
Neg logit contributions | |
wash | -0.092 |
↑ | -0.091 |
pak | -0.087 |
kat | -0.085 |
gross | -0.084 |
Token | steep |
Token ID | 14559 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
AST | +0.028 |
elaide | +0.027 |
igree | +0.026 |
outh | +0.026 |
ovember | +0.026 |
Neg logit contributions | |
wash | -0.034 |
↑ | -0.034 |
pak | -0.032 |
kat | -0.031 |
gross | -0.031 |
Token | incl |
Token ID | 13358 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
AST | +0.329 |
elaide | +0.315 |
igree | +0.310 |
outh | +0.310 |
ovember | +0.308 |
Neg logit contributions | |
wash | -0.392 |
↑ | -0.387 |
pak | -0.368 |
kat | -0.358 |
gross | -0.357 |
Token | ine |
Token ID | 500 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
AST | +1.795 |
outh | +1.695 |
igree | +1.689 |
elaide | +1.686 |
ovember | +1.628 |
Neg logit contributions | |
wash | -2.829 |
↑ | -2.781 |
pak | -2.715 |
kat | -2.643 |
gross | -2.627 |
Token | at |
Token ID | 379 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
AST | +0.820 |
elaide | +0.777 |
igree | +0.769 |
outh | +0.769 |
ovember | +0.762 |
Neg logit contributions | |
wash | -1.003 |
↑ | -0.995 |
pak | -0.949 |
kat | -0.924 |
gross | -0.922 |
Token | mile |
Token ID | 10591 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
AST | +0.196 |
elaide | +0.187 |
igree | +0.184 |
outh | +0.183 |
ovember | +0.183 |
Neg logit contributions | |
wash | -0.272 |
↑ | -0.269 |
pak | -0.256 |
kat | -0.250 |
gross | -0.250 |
Token | 16 |
Token ID | 1467 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
AST | +0.119 |
elaide | +0.113 |
outh | +0.111 |
igree | +0.111 |
ovember | +0.110 |
Neg logit contributions | |
wash | -0.142 |
↑ | -0.140 |
pak | -0.134 |
gross | -0.130 |
kat | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
AST | +0.340 |
elaide | +0.324 |
igree | +0.320 |
outh | +0.320 |
ovember | +0.317 |
Neg logit contributions | |
wash | -0.409 |
↑ | -0.404 |
pak | -0.385 |
kat | -0.375 |
gross | -0.374 |
Token | year |
Token ID | 614 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
AST | +0.169 |
elaide | +0.161 |
igree | +0.158 |
outh | +0.157 |
ovember | +0.156 |
Neg logit contributions | |
wash | -0.307 |
↑ | -0.303 |
pak | -0.290 |
kat | -0.285 |
gross | -0.283 |
Token | was |
Token ID | 373 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
AST | +0.110 |
elaide | +0.105 |
igree | +0.104 |
outh | +0.103 |
ovember | +0.103 |
Neg logit contributions | |
wash | -0.136 |
↑ | -0.134 |
pak | -0.128 |
kat | -0.125 |
gross | -0.125 |
Token | last |
Token ID | 938 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
AST | +0.055 |
elaide | +0.052 |
igree | +0.052 |
outh | +0.052 |
ovember | +0.051 |
Neg logit contributions | |
wash | -0.060 |
↑ | -0.059 |
pak | -0.056 |
kat | -0.054 |
gross | -0.054 |
Token | year |
Token ID | 614 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
AST | +0.328 |
elaide | +0.312 |
igree | +0.307 |
outh | +0.304 |
ovember | +0.303 |
Neg logit contributions | |
wash | -0.571 |
↑ | -0.563 |
pak | -0.540 |
kat | -0.529 |
gross | -0.527 |
Token | ," |
Token ID | 553 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
AST | +0.126 |
elaide | +0.121 |
igree | +0.119 |
outh | +0.119 |
ovember | +0.118 |
Neg logit contributions | |
wash | -0.146 |
↑ | -0.143 |
pak | -0.136 |
kat | -0.133 |
gross | -0.133 |
Token | Stevens |
Token ID | 20019 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
AST | +0.168 |
elaide | +0.160 |
igree | +0.158 |
outh | +0.157 |
ovember | +0.157 |
Neg logit contributions | |
wash | -0.207 |
↑ | -0.205 |
pak | -0.195 |
kat | -0.190 |
gross | -0.190 |
Token | said |
Token ID | 531 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
AST | +1.941 |
elaide | +1.849 |
outh | +1.829 |
igree | +1.827 |
ovember | +1.817 |
Neg logit contributions | |
wash | -2.340 |
↑ | -2.309 |
pak | -2.195 |
kat | -2.141 |
gross | -2.138 |
Token | . |
Token ID | 13 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
AST | +0.307 |
elaide | +0.293 |
igree | +0.289 |
outh | +0.289 |
ovember | +0.287 |
Neg logit contributions | |
wash | -0.360 |
↑ | -0.356 |
pak | -0.338 |
kat | -0.329 |
gross | -0.328 |
Token | " |
Token ID | 366 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
AST | +0.077 |
elaide | +0.074 |
igree | +0.073 |
outh | +0.073 |
ovember | +0.073 |
Neg logit contributions | |
wash | -0.082 |
↑ | -0.081 |
pak | -0.076 |
kat | -0.074 |
gross | -0.074 |
Token | I |
Token ID | 40 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
AST | +0.418 |
elaide | +0.403 |
igree | +0.399 |
outh | +0.397 |
ovember | +0.396 |
Neg logit contributions | |
wash | -0.351 |
↑ | -0.346 |
pak | -0.326 |
kat | -0.316 |
gross | -0.314 |
Token | don |
Token ID | 836 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
AST | +0.074 |
elaide | +0.071 |
igree | +0.070 |
outh | +0.070 |
ovember | +0.069 |
Neg logit contributions | |
wash | -0.074 |
↑ | -0.073 |
pak | -0.069 |
kat | -0.067 |
gross | -0.067 |
Token | resemble |
Token ID | 22464 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
wash | +0.800 |
↑ | +0.787 |
pak | +0.750 |
kat | +0.730 |
gross | +0.727 |
Neg logit contributions | |
AST | -0.642 |
elaide | -0.614 |
outh | -0.604 |
igree | -0.603 |
ovember | -0.601 |
Token | symptoms |
Token ID | 7460 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
wash | +0.067 |
↑ | +0.066 |
pak | +0.063 |
kat | +0.061 |
gross | +0.061 |
Neg logit contributions | |
AST | -0.058 |
elaide | -0.055 |
igree | -0.054 |
outh | -0.054 |
ovember | -0.054 |
Token | of |
Token ID | 286 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
AST | +0.464 |
elaide | +0.439 |
igree | +0.434 |
outh | +0.434 |
ovember | +0.430 |
Neg logit contributions | |
wash | -0.617 |
↑ | -0.610 |
pak | -0.581 |
kat | -0.568 |
gross | -0.566 |
Token | schizophrenia |
Token ID | 22794 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
AST | +0.078 |
elaide | +0.074 |
igree | +0.072 |
outh | +0.072 |
ovember | +0.072 |
Neg logit contributions | |
wash | -0.125 |
↑ | -0.123 |
pak | -0.118 |
kat | -0.115 |
gross | -0.115 |
Token | called |
Token ID | 1444 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
AST | +0.547 |
elaide | +0.519 |
igree | +0.512 |
outh | +0.512 |
ovember | +0.507 |
Neg logit contributions | |
wash | -0.694 |
↑ | -0.686 |
pak | -0.654 |
kat | -0.638 |
gross | -0.637 |
Token | derail |
Token ID | 33749 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
AST | +0.579 |
elaide | +0.546 |
outh | +0.540 |
igree | +0.538 |
ovember | +0.534 |
Neg logit contributions | |
wash | -0.775 |
↑ | -0.767 |
pak | -0.731 |
kat | -0.714 |
gross | -0.712 |
Token | ment |
Token ID | 434 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
AST | +2.355 |
elaide | +2.245 |
igree | +2.229 |
outh | +2.219 |
ovember | +2.214 |
Neg logit contributions | |
wash | -1.888 |
↑ | -1.860 |
pak | -1.775 |
kat | -1.704 |
gross | -1.696 |
Token | and |
Token ID | 290 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
AST | +0.442 |
elaide | +0.416 |
igree | +0.409 |
outh | +0.409 |
ovember | +0.406 |
Neg logit contributions | |
wash | -0.723 |
↑ | -0.715 |
pak | -0.685 |
kat | -0.670 |
gross | -0.668 |
Token | delusion |
Token ID | 40969 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
AST | +0.059 |
elaide | +0.056 |
igree | +0.056 |
outh | +0.055 |
ovember | +0.055 |
Neg logit contributions | |
wash | -0.079 |
↑ | -0.079 |
pak | -0.075 |
kat | -0.073 |
gross | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
AST | +0.269 |
elaide | +0.255 |
outh | +0.252 |
igree | +0.252 |
Monarch | +0.249 |
Neg logit contributions | |
wash | -0.347 |
↑ | -0.343 |
pak | -0.327 |
kat | -0.320 |
gross | -0.318 |
Token | In |
Token ID | 554 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
wash | +0.246 |
↑ | +0.243 |
pak | +0.231 |
kat | +0.224 |
gross | +0.222 |
Neg logit contributions | |
AST | -0.224 |
elaide | -0.219 |
igree | -0.216 |
ovember | -0.215 |
outh | -0.214 |
Token | C |
Token ID | 34 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
AST | +0.134 |
elaide | +0.129 |
outh | +0.127 |
igree | +0.127 |
ovember | +0.127 |
Neg logit contributions | |
wash | -0.134 |
↑ | -0.132 |
pak | -0.125 |
kat | -0.121 |
gross | -0.121 |
Token | elt |
Token ID | 2120 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
wash | +0.082 |
↑ | +0.081 |
pak | +0.074 |
kat | +0.070 |
gross | +0.068 |
Neg logit contributions | |
AST | -0.211 |
outh | -0.206 |
elaide | -0.205 |
igree | -0.204 |
ovember | -0.204 |
Token | ics |
Token ID | 873 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
wash | +0.546 |
↑ | +0.538 |
pak | +0.512 |
gross | +0.499 |
kat | +0.499 |
Neg logit contributions | |
AST | -0.434 |
elaide | -0.408 |
outh | -0.408 |
igree | -0.407 |
ovember | -0.404 |
Token | coach |
Token ID | 3985 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
AST | +0.419 |
elaide | +0.378 |
outh | +0.377 |
igree | +0.374 |
ovember | +0.372 |
Neg logit contributions | |
wash | -1.025 |
↑ | -1.017 |
pak | -0.979 |
kat | -0.962 |
gross | -0.959 |
Token | Brad |
Token ID | 8114 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
AST | +0.494 |
elaide | +0.473 |
igree | +0.466 |
outh | +0.466 |
ovember | +0.464 |
Neg logit contributions | |
wash | -0.560 |
↑ | -0.552 |
pak | -0.525 |
kat | -0.511 |
gross | -0.510 |
Token | Stevens |
Token ID | 20019 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
AST | +0.417 |
igree | +0.393 |
elaide | +0.393 |
outh | +0.390 |
ovember | +0.388 |
Neg logit contributions | |
wash | -0.557 |
↑ | -0.549 |
pak | -0.522 |
kat | -0.510 |
gross | -0.508 |
Token | isn |
Token ID | 2125 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
AST | +1.928 |
outh | +1.805 |
elaide | +1.805 |
ovember | +1.798 |
igree | +1.795 |
Neg logit contributions | |
wash | -2.301 |
↑ | -2.279 |
pak | -2.161 |
kat | -2.111 |
gross | -2.103 |
Token | 't |
Token ID | 470 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
AST | +0.122 |
outh | +0.116 |
elaide | +0.114 |
ADHD | +0.114 |
ovember | +0.114 |
Neg logit contributions | |
wash | -0.097 |
↑ | -0.095 |
pak | -0.090 |
gross | -0.087 |
kat | -0.087 |
Token | sure |
Token ID | 1654 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
AST | +0.222 |
elaide | +0.213 |
igree | +0.211 |
outh | +0.210 |
ovember | +0.209 |
Neg logit contributions | |
wash | -0.227 |
↑ | -0.224 |
pak | -0.212 |
kat | -0.206 |
gross | -0.206 |
Token | if |
Token ID | 611 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
AST | +0.104 |
elaide | +0.100 |
igree | +0.098 |
outh | +0.097 |
ovember | +0.097 |
Neg logit contributions | |
wash | -0.134 |
↑ | -0.132 |
pak | -0.125 |
kat | -0.122 |
gross | -0.122 |
Token | any |
Token ID | 597 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
AST | +0.071 |
elaide | +0.068 |
igree | +0.067 |
outh | +0.067 |
ovember | +0.066 |
Neg logit contributions | |
wash | -0.119 |
↑ | -0.118 |
pak | -0.112 |
gross | -0.110 |
kat | -0.110 |
Token | Pennsylvania |
Token ID | 9589 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
wash | +0.387 |
↑ | +0.382 |
pak | +0.365 |
kat | +0.356 |
gross | +0.355 |
Neg logit contributions | |
AST | -0.285 |
elaide | -0.271 |
igree | -0.267 |
outh | -0.267 |
ovember | -0.265 |
Token | 's |
Token ID | 338 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
AST | +0.284 |
elaide | +0.270 |
igree | +0.267 |
outh | +0.267 |
ovember | +0.265 |
Neg logit contributions | |
wash | -0.308 |
↑ | -0.304 |
pak | -0.289 |
kat | -0.281 |
gross | -0.280 |
Token | Th |
Token ID | 536 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
wash | +0.003 |
↑ | +0.003 |
pak | +0.003 |
kat | +0.003 |
gross | +0.003 |
Neg logit contributions | |
AST | -0.003 |
elaide | -0.002 |
igree | -0.002 |
outh | -0.002 |
ovember | -0.002 |
Token | add |
Token ID | 2860 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
AST | +0.401 |
elaide | +0.384 |
outh | +0.380 |
igree | +0.379 |
ovember | +0.377 |
Neg logit contributions | |
wash | -0.431 |
↑ | -0.426 |
pak | -0.404 |
kat | -0.392 |
gross | -0.392 |
Token | eus |
Token ID | 27650 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
AST | +0.429 |
elaide | +0.405 |
ovember | +0.401 |
igree | +0.400 |
outh | +0.396 |
Neg logit contributions | |
wash | -0.603 |
↑ | -0.593 |
pak | -0.566 |
kat | -0.554 |
gross | -0.554 |
Token | Stevens |
Token ID | 20019 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
AST | +0.095 |
elaide | +0.090 |
igree | +0.089 |
outh | +0.089 |
ovember | +0.088 |
Neg logit contributions | |
wash | -0.126 |
↑ | -0.125 |
pak | -0.119 |
kat | -0.116 |
gross | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
AST | +1.723 |
outh | +1.608 |
elaide | +1.607 |
igree | +1.605 |
Monarch | +1.594 |
Neg logit contributions | |
wash | -2.480 |
↑ | -2.443 |
pak | -2.336 |
gross | -2.281 |
kat | -2.272 |
Token | who |
Token ID | 508 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
wash | +0.027 |
↑ | +0.027 |
pak | +0.025 |
kat | +0.025 |
gross | +0.025 |
Neg logit contributions | |
AST | -0.021 |
elaide | -0.020 |
igree | -0.020 |
outh | -0.020 |
ovember | -0.020 |
Token | represented |
Token ID | 7997 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
wash | +0.100 |
↑ | +0.098 |
pak | +0.093 |
kat | +0.091 |
gross | +0.091 |
Neg logit contributions | |
AST | -0.089 |
elaide | -0.085 |
igree | -0.084 |
outh | -0.084 |
ovember | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
AST | +0.033 |
elaide | +0.031 |
igree | +0.031 |
outh | +0.031 |
ovember | +0.031 |
Neg logit contributions | |
wash | -0.052 |
↑ | -0.051 |
pak | -0.049 |
kat | -0.048 |
gross | -0.048 |
Token | mining |
Token ID | 9691 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
wash | +0.102 |
↑ | +0.101 |
pak | +0.096 |
kat | +0.094 |
gross | +0.093 |
Neg logit contributions | |
AST | -0.083 |
elaide | -0.079 |
igree | -0.078 |
outh | -0.078 |
ovember | -0.077 |
Token | www |
Token ID | 2503 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
↑ | +0.813 |
wash | +0.803 |
pak | +0.717 |
kat | +0.682 |
Net | +0.679 |
Neg logit contributions | |
AST | -1.764 |
outh | -1.736 |
elaide | -1.724 |
igree | -1.708 |
ovember | -1.678 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
wash | +0.091 |
↑ | +0.090 |
pak | +0.086 |
gross | +0.085 |
kat | +0.084 |
Neg logit contributions | |
AST | -0.069 |
outh | -0.065 |
ADHD | -0.064 |
Monarch | -0.063 |
elaide | -0.063 |
Token | bel |
Token ID | 6667 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
↑ | +0.016 |
wash | +0.015 |
pak | +0.014 |
kat | +0.013 |
200000 | +0.013 |
Neg logit contributions | |
AST | -0.026 |
outh | -0.026 |
elaide | -0.026 |
igree | -0.026 |
Lyme | -0.025 |
Token | fast |
Token ID | 7217 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
AST | +0.247 |
elaide | +0.236 |
igree | +0.233 |
outh | +0.233 |
ovember | +0.232 |
Neg logit contributions | |
wash | -0.274 |
↑ | -0.271 |
pak | -0.257 |
kat | -0.250 |
gross | -0.249 |
Token | te |
Token ID | 660 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
wash | +0.007 |
↑ | +0.007 |
pak | +0.007 |
kat | +0.007 |
gross | +0.007 |
Neg logit contributions | |
AST | -0.008 |
elaide | -0.007 |
igree | -0.007 |
outh | -0.007 |
ovember | -0.007 |
Token | legraph |
Token ID | 16606 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
AST | +0.007 |
elaide | +0.006 |
outh | +0.006 |
igree | +0.006 |
roit | +0.006 |
Neg logit contributions | |
wash | -0.013 |
↑ | -0.013 |
pak | -0.012 |
200000 | -0.012 |
gross | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-03 |
Pos logit contributions | |
AST | +1.745 |
outh | +1.660 |
elaide | +1.620 |
ADHD | +1.600 |
Monarch | +1.587 |
Neg logit contributions | |
wash | -2.388 |
↑ | -2.355 |
pak | -2.253 |
gross | -2.220 |
kat | -2.168 |
Token | co |
Token ID | 1073 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
wash | +0.014 |
↑ | +0.014 |
pak | +0.013 |
kat | +0.013 |
gross | +0.013 |
Neg logit contributions | |
AST | -0.010 |
elaide | -0.009 |
outh | -0.009 |
igree | -0.009 |
ovember | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
AST | +0.107 |
elaide | +0.101 |
outh | +0.101 |
igree | +0.100 |
ovember | +0.099 |
Neg logit contributions | |
wash | -0.126 |
↑ | -0.124 |
pak | -0.118 |
gross | -0.115 |
kat | -0.115 |
Token | uk |
Token ID | 2724 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
AST | +0.026 |
elaide | +0.024 |
outh | +0.024 |
igree | +0.024 |
ovember | +0.024 |
Neg logit contributions | |
wash | -0.027 |
↑ | -0.027 |
pak | -0.025 |
gross | -0.025 |
kat | -0.025 |
Token | / |
Token ID | 14 |
Feature activation | +1.06e-04 |
Pos logit contributions | |
AST | +0.054 |
elaide | +0.052 |
outh | +0.051 |
igree | +0.051 |
ovember | +0.051 |
Neg logit contributions | |
wash | -0.059 |
↑ | -0.058 |
pak | -0.055 |
kat | -0.054 |
gross | -0.054 |
Token | House |
Token ID | 2097 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
AST | +0.026 |
elaide | +0.025 |
igree | +0.025 |
outh | +0.025 |
ovember | +0.024 |
Neg logit contributions | |
wash | -0.032 |
↑ | -0.032 |
pak | -0.030 |
kat | -0.030 |
gross | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
AST | +0.287 |
elaide | +0.273 |
igree | +0.269 |
outh | +0.269 |
ovember | +0.267 |
Neg logit contributions | |
wash | -0.362 |
↑ | -0.358 |
pak | -0.341 |
kat | -0.332 |
gross | -0.331 |
Token | Representatives |
Token ID | 17132 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
wash | +0.027 |
↑ | +0.027 |
pak | +0.025 |
kat | +0.025 |
gross | +0.025 |
Neg logit contributions | |
AST | -0.033 |
elaide | -0.031 |
igree | -0.031 |
outh | -0.031 |
ovember | -0.031 |
Token | ( |
Token ID | 357 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
wash | +0.169 |
↑ | +0.167 |
pak | +0.158 |
kat | +0.154 |
gross | +0.153 |
Neg logit contributions | |
AST | -0.163 |
elaide | -0.156 |
igree | -0.154 |
outh | -0.154 |
ovember | -0.153 |
Token | the |
Token ID | 1169 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
wash | +0.015 |
↑ | +0.015 |
pak | +0.014 |
kat | +0.014 |
gross | +0.014 |
Neg logit contributions | |
AST | -0.019 |
elaide | -0.019 |
outh | -0.018 |
igree | -0.018 |
ovember | -0.018 |
Token | lower |
Token ID | 2793 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
wash | +0.204 |
↑ | +0.202 |
pak | +0.193 |
kat | +0.188 |
gross | +0.188 |
Neg logit contributions | |
AST | -0.138 |
elaide | -0.131 |
igree | -0.129 |
outh | -0.128 |
ovember | -0.128 |
Token | house |
Token ID | 2156 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
AST | +1.904 |
elaide | +1.792 |
igree | +1.780 |
Monarch | +1.774 |
outh | +1.773 |
Neg logit contributions | |
wash | -2.270 |
↑ | -2.260 |
pak | -2.142 |
kat | -2.090 |
gross | -2.074 |
Token | ) |
Token ID | 8 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
wash | +0.248 |
↑ | +0.244 |
pak | +0.232 |
kat | +0.225 |
gross | +0.224 |
Neg logit contributions | |
AST | -0.243 |
elaide | -0.232 |
igree | -0.229 |
outh | -0.229 |
ovember | -0.228 |
Token | has |
Token ID | 468 |
Feature activation | +8.99e-03 |
Pos logit contributions | |
wash | +0.132 |
↑ | +0.130 |
pak | +0.123 |
kat | +0.120 |
gross | +0.119 |
Neg logit contributions | |
AST | -0.133 |
elaide | -0.127 |
outh | -0.125 |
igree | -0.125 |
ovember | -0.125 |
Token | 150 |
Token ID | 6640 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
wash | +0.018 |
↑ | +0.018 |
pak | +0.017 |
kat | +0.016 |
gross | +0.016 |
Neg logit contributions | |
AST | -0.015 |
elaide | -0.014 |
outh | -0.014 |
igree | -0.014 |
ovember | -0.014 |
Token | members |
Token ID | 1866 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
wash | +0.116 |
↑ | +0.113 |
pak | +0.106 |
kat | +0.103 |
gross | +0.102 |
Neg logit contributions | |
AST | -0.157 |
elaide | -0.151 |
outh | -0.149 |
igree | -0.149 |
ovember | -0.148 |
Token | basketball |
Token ID | 9669 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
wash | +0.178 |
↑ | +0.176 |
pak | +0.168 |
kat | +0.163 |
gross | +0.163 |
Neg logit contributions | |
AST | -0.142 |
elaide | -0.136 |
igree | -0.135 |
outh | -0.134 |
ovember | -0.133 |
Token | won |
Token ID | 1839 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
AST | +0.186 |
elaide | +0.178 |
igree | +0.176 |
outh | +0.175 |
ovember | +0.175 |
Neg logit contributions | |
wash | -0.202 |
↑ | -0.200 |
pak | -0.189 |
kat | -0.184 |
gross | -0.184 |
Token | out |
Token ID | 503 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
AST | +0.030 |
elaide | +0.029 |
igree | +0.028 |
outh | +0.028 |
ovember | +0.028 |
Neg logit contributions | |
wash | -0.029 |
↑ | -0.028 |
pak | -0.027 |
kat | -0.026 |
gross | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
AST | +0.183 |
elaide | +0.175 |
igree | +0.172 |
outh | +0.172 |
ovember | +0.171 |
Neg logit contributions | |
wash | -0.215 |
↑ | -0.213 |
pak | -0.202 |
kat | -0.197 |
gross | -0.196 |
Token | A |
Token ID | 317 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
wash | +0.120 |
↑ | +0.119 |
pak | +0.113 |
kat | +0.110 |
gross | +0.110 |
Neg logit contributions | |
AST | -0.107 |
elaide | -0.104 |
igree | -0.103 |
outh | -0.102 |
ovember | -0.102 |
Token | court |
Token ID | 2184 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
wash | +0.137 |
↑ | +0.135 |
pak | +0.129 |
kat | +0.125 |
gross | +0.125 |
Neg logit contributions | |
AST | -0.108 |
elaide | -0.103 |
igree | -0.101 |
outh | -0.101 |
ovember | -0.100 |
Token | was |
Token ID | 373 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
AST | +1.866 |
elaide | +1.772 |
igree | +1.754 |
outh | +1.752 |
ovember | +1.743 |
Neg logit contributions | |
wash | -2.276 |
↑ | -2.263 |
pak | -2.155 |
kat | -2.095 |
gross | -2.090 |
Token | set |
Token ID | 900 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
AST | +0.075 |
elaide | +0.072 |
igree | +0.071 |
outh | +0.071 |
ovember | +0.070 |
Neg logit contributions | |
wash | -0.077 |
↑ | -0.076 |
pak | -0.072 |
kat | -0.070 |
gross | -0.070 |
Token | up |
Token ID | 510 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
AST | +0.552 |
elaide | +0.524 |
igree | +0.517 |
outh | +0.513 |
ovember | +0.513 |
Neg logit contributions | |
wash | -0.882 |
↑ | -0.869 |
pak | -0.832 |
kat | -0.815 |
gross | -0.811 |
Token | , |
Token ID | 11 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
wash | +0.031 |
↑ | +0.031 |
pak | +0.029 |
kat | +0.029 |
gross | +0.029 |
Neg logit contributions | |
AST | -0.027 |
elaide | -0.026 |
igree | -0.026 |
outh | -0.026 |
ovember | -0.025 |
Token | concrete |
Token ID | 10017 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
AST | +0.080 |
elaide | +0.077 |
igree | +0.075 |
outh | +0.075 |
ovember | +0.075 |
Neg logit contributions | |
wash | -0.102 |
↑ | -0.101 |
pak | -0.096 |
kat | -0.094 |
gross | -0.094 |
Token | goals |
Token ID | 4661 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
AST | +0.182 |
elaide | +0.174 |
ovember | +0.172 |
igree | +0.172 |
outh | +0.171 |
Neg logit contributions | |
wash | -0.237 |
↑ | -0.234 |
pak | -0.223 |
kat | -0.217 |
gross | -0.217 |
Token | or |
Token ID | 393 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
AST | +0.346 |
elaide | +0.331 |
igree | +0.326 |
outh | +0.326 |
ovember | +0.324 |
Neg logit contributions | |
wash | -0.410 |
↑ | -0.404 |
pak | -0.384 |
kat | -0.375 |
gross | -0.373 |
Token | hitting |
Token ID | 9008 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
AST | +0.163 |
elaide | +0.156 |
igree | +0.154 |
outh | +0.154 |
ovember | +0.153 |
Neg logit contributions | |
wash | -0.208 |
↑ | -0.205 |
pak | -0.196 |
kat | -0.191 |
gross | -0.191 |
Token | cross |
Token ID | 3272 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
AST | +0.734 |
elaide | +0.697 |
igree | +0.688 |
outh | +0.686 |
ovember | +0.681 |
Neg logit contributions | |
wash | -0.953 |
↑ | -0.941 |
pak | -0.898 |
kat | -0.876 |
gross | -0.873 |
Token | - |
Token ID | 12 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
AST | +0.906 |
elaide | +0.858 |
igree | +0.851 |
outh | +0.841 |
ovember | +0.836 |
Neg logit contributions | |
wash | -1.092 |
↑ | -1.082 |
pak | -1.026 |
gross | -0.998 |
kat | -0.996 |
Token | court |
Token ID | 22230 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
AST | +0.367 |
elaide | +0.350 |
igree | +0.345 |
outh | +0.341 |
ovember | +0.336 |
Neg logit contributions | |
wash | -0.504 |
↑ | -0.501 |
pak | -0.475 |
gross | -0.464 |
kat | -0.464 |
Token | winners |
Token ID | 14591 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
AST | +1.824 |
elaide | +1.728 |
igree | +1.704 |
outh | +1.699 |
Monarch | +1.675 |
Neg logit contributions | |
wash | -2.343 |
↑ | -2.313 |
pak | -2.208 |
gross | -2.153 |
kat | -2.145 |
Token | when |
Token ID | 618 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
AST | +0.339 |
elaide | +0.324 |
igree | +0.320 |
outh | +0.319 |
ovember | +0.317 |
Neg logit contributions | |
wash | -0.395 |
↑ | -0.390 |
pak | -0.371 |
kat | -0.361 |
gross | -0.360 |
Token | a |
Token ID | 257 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
AST | +0.188 |
elaide | +0.179 |
igree | +0.176 |
outh | +0.175 |
ovember | +0.175 |
Neg logit contributions | |
wash | -0.284 |
↑ | -0.280 |
pak | -0.268 |
kat | -0.262 |
gross | -0.261 |
Token | child |
Token ID | 1200 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
AST | +0.101 |
elaide | +0.096 |
igree | +0.095 |
ovember | +0.094 |
outh | +0.094 |
Neg logit contributions | |
wash | -0.141 |
↑ | -0.140 |
pak | -0.133 |
kat | -0.130 |
gross | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
AST | +1.149 |
elaide | +1.100 |
igree | +1.086 |
outh | +1.084 |
ovember | +1.079 |
Neg logit contributions | |
wash | -1.250 |
↑ | -1.233 |
pak | -1.171 |
kat | -1.139 |
gross | -1.136 |
Token | : |
Token ID | 25 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
wash | +0.104 |
↑ | +0.103 |
pak | +0.098 |
kat | +0.096 |
gross | +0.095 |
Neg logit contributions | |
AST | -0.084 |
elaide | -0.080 |
igree | -0.079 |
outh | -0.079 |
ovember | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
AST | +0.011 |
elaide | +0.011 |
igree | +0.011 |
outh | +0.010 |
ovember | +0.010 |
Neg logit contributions | |
wash | -0.011 |
↑ | -0.010 |
pak | -0.010 |
kat | -0.010 |
gross | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
AST | +0.283 |
outh | +0.264 |
ADHD | +0.259 |
Monarch | +0.259 |
Lyme | +0.259 |
Neg logit contributions | |
wash | -0.348 |
↑ | -0.340 |
pak | -0.327 |
gross | -0.319 |
kat | -0.317 |
Token | 13 |
Token ID | 1485 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
AST | +0.258 |
elaide | +0.248 |
outh | +0.246 |
ovember | +0.245 |
igree | +0.245 |
Neg logit contributions | |
wash | -0.228 |
↑ | -0.222 |
pak | -0.212 |
kat | -0.205 |
gross | -0.204 |
Token | PH |
Token ID | 9370 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
AST | +0.066 |
elaide | +0.063 |
igree | +0.063 |
outh | +0.062 |
ovember | +0.062 |
Neg logit contributions | |
wash | -0.070 |
↑ | -0.069 |
pak | -0.065 |
kat | -0.063 |
gross | -0.063 |
Token | OTOS |
Token ID | 33291 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
AST | +0.151 |
elaide | +0.139 |
igree | +0.136 |
outh | +0.135 |
ovember | +0.134 |
Neg logit contributions | |
wash | -0.389 |
↑ | -0.385 |
pak | -0.372 |
kat | -0.365 |
gross | -0.363 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
AST | +1.780 |
outh | +1.655 |
Monarch | +1.641 |
elaide | +1.627 |
ovember | +1.626 |
Neg logit contributions | |
wash | -2.383 |
↑ | -2.338 |
pak | -2.227 |
kat | -2.189 |
gross | -2.182 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
AST | +0.513 |
outh | +0.476 |
elaide | +0.475 |
ovember | +0.474 |
igree | +0.471 |
Neg logit contributions | |
wash | -0.748 |
↑ | -0.739 |
pak | -0.704 |
gross | -0.691 |
kat | -0.690 |
Token | 's |
Token ID | 338 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
AST | +0.100 |
elaide | +0.095 |
igree | +0.094 |
outh | +0.094 |
ovember | +0.094 |
Neg logit contributions | |
wash | -0.106 |
↑ | -0.104 |
pak | -0.099 |
kat | -0.097 |
gross | -0.096 |
Token | potential |
Token ID | 2785 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
wash | +0.159 |
↑ | +0.157 |
pak | +0.149 |
kat | +0.145 |
gross | +0.145 |
Neg logit contributions | |
AST | -0.143 |
elaide | -0.137 |
igree | -0.135 |
outh | -0.134 |
ovember | -0.134 |
Token | running |
Token ID | 2491 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
wash | +0.062 |
↑ | +0.061 |
pak | +0.059 |
kat | +0.057 |
gross | +0.057 |
Neg logit contributions | |
AST | -0.034 |
elaide | -0.032 |
outh | -0.032 |
igree | -0.032 |
ovember | -0.031 |
Token | www |
Token ID | 2503 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
↑ | +0.840 |
wash | +0.831 |
pak | +0.731 |
kat | +0.697 |
gross | +0.696 |
Neg logit contributions | |
AST | -1.969 |
outh | -1.928 |
elaide | -1.921 |
igree | -1.904 |
ovember | -1.885 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
wash | +0.300 |
↑ | +0.296 |
pak | +0.283 |
gross | +0.277 |
kat | +0.274 |
Neg logit contributions | |
AST | -0.241 |
outh | -0.228 |
elaide | -0.223 |
Monarch | -0.222 |
ADHD | -0.222 |
Token | bel |
Token ID | 6667 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
outh | +0.099 |
AST | +0.098 |
elaide | +0.098 |
igree | +0.097 |
ovember | +0.094 |
Neg logit contributions | |
↑ | -0.059 |
wash | -0.056 |
pak | -0.051 |
200000 | -0.050 |
kat | -0.049 |
Token | fast |
Token ID | 7217 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
AST | +0.026 |
elaide | +0.025 |
outh | +0.025 |
igree | +0.025 |
ovember | +0.025 |
Neg logit contributions | |
wash | -0.031 |
↑ | -0.031 |
pak | -0.029 |
kat | -0.029 |
gross | -0.028 |
Token | te |
Token ID | 660 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
AST | +0.056 |
elaide | +0.054 |
outh | +0.053 |
igree | +0.053 |
ovember | +0.052 |
Neg logit contributions | |
wash | -0.056 |
↑ | -0.055 |
pak | -0.052 |
gross | -0.050 |
kat | -0.050 |
Token | legraph |
Token ID | 16606 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
wash | +0.091 |
↑ | +0.090 |
pak | +0.086 |
gross | +0.084 |
kat | +0.084 |
Neg logit contributions | |
AST | -0.056 |
elaide | -0.053 |
outh | -0.052 |
igree | -0.052 |
ovember | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
AST | +1.737 |
outh | +1.640 |
elaide | +1.595 |
ADHD | +1.590 |
Monarch | +1.581 |
Neg logit contributions | |
wash | -2.338 |
↑ | -2.298 |
pak | -2.206 |
gross | -2.176 |
kat | -2.133 |
Token | co |
Token ID | 1073 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
AST | +0.098 |
outh | +0.093 |
elaide | +0.092 |
igree | +0.091 |
Monarch | +0.090 |
Neg logit contributions | |
wash | -0.139 |
↑ | -0.138 |
pak | -0.130 |
kat | -0.128 |
gross | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
wash | +0.030 |
↑ | +0.030 |
pak | +0.029 |
gross | +0.028 |
kat | +0.028 |
Neg logit contributions | |
AST | -0.025 |
outh | -0.024 |
elaide | -0.024 |
ovember | -0.023 |
igree | -0.023 |
Token | uk |
Token ID | 2724 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
AST | +0.158 |
outh | +0.150 |
elaide | +0.150 |
igree | +0.147 |
ovember | +0.147 |
Neg logit contributions | |
wash | -0.166 |
↑ | -0.164 |
pak | -0.155 |
gross | -0.152 |
kat | -0.151 |
Token | / |
Token ID | 14 |
Feature activation | +9.82e-03 |
Pos logit contributions | |
wash | +0.091 |
↑ | +0.090 |
pak | +0.085 |
gross | +0.083 |
kat | +0.083 |
Neg logit contributions | |
AST | -0.083 |
elaide | -0.078 |
outh | -0.078 |
ovember | -0.077 |
igree | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
AST | +0.448 |
elaide | +0.426 |
igree | +0.420 |
outh | +0.419 |
ovember | +0.417 |
Neg logit contributions | |
wash | -0.565 |
↑ | -0.558 |
pak | -0.532 |
kat | -0.519 |
gross | -0.517 |
Token | ore |
Token ID | 23751 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
wash | +0.046 |
↑ | +0.046 |
pak | +0.043 |
kat | +0.042 |
gross | +0.042 |
Neg logit contributions | |
AST | -0.042 |
elaide | -0.040 |
igree | -0.040 |
outh | -0.040 |
ovember | -0.040 |
Token | refinement |
Token ID | 47517 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
AST | +0.131 |
elaide | +0.125 |
igree | +0.124 |
outh | +0.123 |
ovember | +0.123 |
Neg logit contributions | |
wash | -0.160 |
↑ | -0.158 |
pak | -0.150 |
kat | -0.146 |
gross | -0.146 |
Token | machinery |
Token ID | 20230 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
wash | +0.363 |
↑ | +0.359 |
pak | +0.340 |
kat | +0.331 |
gross | +0.330 |
Neg logit contributions | |
AST | -0.322 |
elaide | -0.308 |
igree | -0.304 |
outh | -0.304 |
ovember | -0.302 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
wash | +0.333 |
↑ | +0.329 |
pak | +0.313 |
kat | +0.305 |
gross | +0.304 |
Neg logit contributions | |
AST | -0.280 |
elaide | -0.267 |
igree | -0.264 |
outh | -0.263 |
ovember | -0.262 |
Token | Stevens |
Token ID | 20019 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
AST | +0.038 |
elaide | +0.036 |
igree | +0.035 |
outh | +0.035 |
ovember | +0.035 |
Neg logit contributions | |
wash | -0.045 |
↑ | -0.044 |
pak | -0.042 |
kat | -0.041 |
gross | -0.041 |
Token | related |
Token ID | 3519 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
AST | +1.890 |
elaide | +1.780 |
outh | +1.770 |
igree | +1.768 |
ovember | +1.764 |
Neg logit contributions | |
wash | -2.162 |
↑ | -2.132 |
pak | -2.025 |
kat | -1.969 |
gross | -1.965 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
wash | +0.378 |
↑ | +0.373 |
pak | +0.355 |
kat | +0.346 |
gross | +0.345 |
Neg logit contributions | |
AST | -0.313 |
elaide | -0.299 |
igree | -0.295 |
outh | -0.294 |
ovember | -0.293 |
Token | and |
Token ID | 290 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
AST | +0.049 |
elaide | +0.046 |
igree | +0.046 |
outh | +0.046 |
ovember | +0.045 |
Neg logit contributions | |
wash | -0.058 |
↑ | -0.058 |
pak | -0.055 |
kat | -0.053 |
gross | -0.053 |
Token | it |
Token ID | 340 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
wash | +0.016 |
↑ | +0.015 |
pak | +0.015 |
kat | +0.014 |
gross | +0.014 |
Neg logit contributions | |
AST | -0.012 |
elaide | -0.012 |
igree | -0.011 |
outh | -0.011 |
ovember | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
AST | +0.089 |
elaide | +0.085 |
igree | +0.084 |
outh | +0.084 |
ovember | +0.083 |
Neg logit contributions | |
wash | -0.095 |
↑ | -0.094 |
pak | -0.089 |
kat | -0.087 |
gross | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
AST | +0.221 |
elaide | +0.211 |
igree | +0.209 |
outh | +0.208 |
ovember | +0.207 |
Neg logit contributions | |
wash | -0.261 |
↑ | -0.258 |
pak | -0.245 |
kat | -0.239 |
gross | -0.238 |
Token | prime |
Token ID | 6994 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
AST | +0.181 |
elaide | +0.173 |
outh | +0.172 |
igree | +0.171 |
ovember | +0.170 |
Neg logit contributions | |
wash | -0.174 |
↑ | -0.171 |
pak | -0.162 |
kat | -0.157 |
gross | -0.157 |
Token | challenge |
Token ID | 4427 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
AST | +0.073 |
elaide | +0.070 |
igree | +0.069 |
outh | +0.068 |
ovember | +0.068 |
Neg logit contributions | |
wash | -0.093 |
↑ | -0.091 |
pak | -0.087 |
kat | -0.085 |
gross | -0.085 |
Token | Belfast |
Token ID | 29713 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
AST | +0.272 |
elaide | +0.259 |
igree | +0.256 |
outh | +0.256 |
ovember | +0.254 |
Neg logit contributions | |
wash | -0.309 |
↑ | -0.304 |
pak | -0.289 |
kat | -0.282 |
gross | -0.281 |
Token | Te |
Token ID | 6767 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
AST | +0.141 |
elaide | +0.134 |
outh | +0.133 |
igree | +0.132 |
ovember | +0.131 |
Neg logit contributions | |
wash | -0.164 |
↑ | -0.162 |
pak | -0.154 |
kat | -0.150 |
gross | -0.150 |
Token | legraph |
Token ID | 16606 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
AST | +0.202 |
elaide | +0.191 |
igree | +0.185 |
outh | +0.185 |
ovember | +0.184 |
Neg logit contributions | |
wash | -0.365 |
↑ | -0.360 |
pak | -0.346 |
gross | -0.338 |
kat | -0.335 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
AST | +1.781 |
elaide | +1.637 |
outh | +1.609 |
igree | +1.607 |
Lyme | +1.604 |
Neg logit contributions | |
wash | -2.298 |
↑ | -2.250 |
pak | -2.168 |
gross | -2.134 |
kat | -2.079 |
Token | co |
Token ID | 1073 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
wash | +0.043 |
↑ | +0.043 |
pak | +0.041 |
gross | +0.040 |
kat | +0.040 |
Neg logit contributions | |
AST | -0.029 |
elaide | -0.027 |
outh | -0.027 |
Monarch | -0.026 |
igree | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
AST | +0.082 |
elaide | +0.078 |
outh | +0.078 |
igree | +0.076 |
ovember | +0.076 |
Neg logit contributions | |
wash | -0.099 |
↑ | -0.097 |
pak | -0.092 |
gross | -0.090 |
kat | -0.089 |
Token | uk |
Token ID | 2724 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
AST | +0.030 |
elaide | +0.029 |
outh | +0.029 |
igree | +0.028 |
ovember | +0.028 |
Neg logit contributions | |
wash | -0.031 |
↑ | -0.031 |
pak | -0.029 |
gross | -0.029 |
kat | -0.029 |
Token | Dis |
Token ID | 3167 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
AST | +0.046 |
elaide | +0.044 |
igree | +0.044 |
outh | +0.044 |
ovember | +0.043 |
Neg logit contributions | |
wash | -0.054 |
↑ | -0.054 |
pak | -0.051 |
kat | -0.050 |
gross | -0.050 |
Token | like |
Token ID | 588 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
wash | +0.033 |
↑ | +0.033 |
pak | +0.031 |
kat | +0.030 |
gross | +0.030 |
Neg logit contributions | |
AST | -0.027 |
elaide | -0.026 |
igree | -0.026 |
outh | -0.026 |
ovember | -0.026 |
Token | public |
Token ID | 1171 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
AST | +0.095 |
elaide | +0.090 |
igree | +0.089 |
outh | +0.089 |
ovember | +0.089 |
Neg logit contributions | |
wash | -0.109 |
↑ | -0.107 |
pak | -0.102 |
kat | -0.099 |
gross | -0.099 |
Token | izing |
Token ID | 2890 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
wash | +0.257 |
↑ | +0.253 |
pak | +0.241 |
kat | +0.235 |
gross | +0.234 |
Neg logit contributions | |
AST | -0.205 |
elaide | -0.196 |
igree | -0.194 |
outh | -0.192 |
ovember | -0.192 |
Token | mar |
Token ID | 1667 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
wash | +0.098 |
↑ | +0.097 |
pak | +0.092 |
kat | +0.090 |
gross | +0.090 |
Neg logit contributions | |
AST | -0.071 |
elaide | -0.068 |
igree | -0.067 |
outh | -0.067 |
ovember | -0.066 |
Token | ath |
Token ID | 776 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
wash | +0.477 |
↑ | +0.469 |
pak | +0.447 |
kat | +0.435 |
gross | +0.432 |
Neg logit contributions | |
AST | -0.494 |
elaide | -0.474 |
igree | -0.468 |
outh | -0.466 |
ovember | -0.466 |
Token | ons |
Token ID | 684 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
wash | +0.186 |
↑ | +0.184 |
pak | +0.176 |
kat | +0.172 |
gross | +0.172 |
Neg logit contributions | |
AST | -0.109 |
elaide | -0.103 |
igree | -0.101 |
outh | -0.101 |
ovember | -0.100 |
Token | to |
Token ID | 284 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
AST | +1.768 |
elaide | +1.676 |
outh | +1.673 |
ovember | +1.650 |
igree | +1.648 |
Neg logit contributions | |
wash | -2.225 |
↑ | -2.189 |
pak | -2.103 |
gross | -2.038 |
kat | -2.037 |
Token | promote |
Token ID | 7719 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
AST | +0.128 |
elaide | +0.122 |
igree | +0.121 |
outh | +0.120 |
ovember | +0.120 |
Neg logit contributions | |
wash | -0.166 |
↑ | -0.164 |
pak | -0.156 |
kat | -0.152 |
gross | -0.152 |
Token | j |
Token ID | 474 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
wash | +0.635 |
↑ | +0.626 |
pak | +0.596 |
kat | +0.583 |
gross | +0.581 |
Neg logit contributions | |
AST | -0.474 |
elaide | -0.458 |
igree | -0.453 |
outh | -0.446 |
ovember | -0.445 |
Token | ogging |
Token ID | 30853 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
AST | +0.260 |
elaide | +0.247 |
outh | +0.243 |
igree | +0.243 |
ovember | +0.242 |
Neg logit contributions | |
wash | -0.364 |
↑ | -0.360 |
pak | -0.344 |
kat | -0.335 |
gross | -0.334 |
Token | — |
Token ID | 960 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
wash | +0.718 |
↑ | +0.712 |
pak | +0.671 |
kat | +0.658 |
gross | +0.653 |
Neg logit contributions | |
AST | -0.608 |
elaide | -0.582 |
igree | -0.577 |
ovember | -0.570 |
outh | -0.569 |
Token | well |
Token ID | 880 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
wash | +1.123 |
↑ | +1.095 |
pak | +1.041 |
gross | +1.010 |
kat | +1.006 |
Neg logit contributions | |
AST | -1.177 |
elaide | -1.153 |
ovember | -1.136 |
igree | -1.135 |
outh | -1.124 |
Token | . |
Token ID | 13 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
wash | +0.827 |
↑ | +0.814 |
pak | +0.775 |
kat | +0.753 |
gross | +0.752 |
Neg logit contributions | |
AST | -0.735 |
elaide | -0.709 |
igree | -0.699 |
ovember | -0.695 |
outh | -0.695 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
AST | +0.169 |
elaide | +0.166 |
igree | +0.163 |
ovember | +0.163 |
outh | +0.162 |
Neg logit contributions | |
wash | -0.165 |
↑ | -0.163 |
pak | -0.154 |
kat | -0.150 |
gross | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
AST | +0.219 |
outh | +0.205 |
ADHD | +0.201 |
Monarch | +0.201 |
Lyme | +0.201 |
Neg logit contributions | |
wash | -0.265 |
↑ | -0.260 |
pak | -0.249 |
gross | -0.244 |
kat | -0.242 |
Token | Con |
Token ID | 3103 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
AST | +0.230 |
elaide | +0.221 |
igree | +0.219 |
outh | +0.218 |
ovember | +0.217 |
Neg logit contributions | |
wash | -0.198 |
↑ | -0.194 |
pak | -0.184 |
kat | -0.178 |
gross | -0.177 |
Token | clusions |
Token ID | 11539 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
AST | +0.295 |
elaide | +0.275 |
igree | +0.270 |
outh | +0.269 |
ovember | +0.266 |
Neg logit contributions | |
wash | -0.654 |
↑ | -0.647 |
pak | -0.622 |
kat | -0.610 |
gross | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
AST | +1.875 |
elaide | +1.760 |
igree | +1.754 |
outh | +1.748 |
ovember | +1.740 |
Neg logit contributions | |
wash | -2.152 |
↑ | -2.070 |
pak | -2.009 |
kat | -1.955 |
gross | -1.949 |
Token |
|
Token ID | 198 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
AST | +0.373 |
outh | +0.348 |
ADHD | +0.342 |
Monarch | +0.342 |
Lyme | +0.341 |
Neg logit contributions | |
wash | -0.455 |
↑ | -0.444 |
pak | -0.426 |
gross | -0.417 |
kat | -0.415 |
Token | Arthur |
Token ID | 29874 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
AST | +0.405 |
elaide | +0.389 |
igree | +0.385 |
outh | +0.384 |
ovember | +0.383 |
Neg logit contributions | |
wash | -0.357 |
↑ | -0.351 |
pak | -0.332 |
kat | -0.321 |
gross | -0.321 |
Token | Sch |
Token ID | 3059 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
wash | +0.442 |
↑ | +0.437 |
pak | +0.417 |
kat | +0.406 |
gross | +0.405 |
Neg logit contributions | |
AST | -0.337 |
elaide | -0.321 |
igree | -0.316 |
outh | -0.315 |
ovember | -0.314 |
Token | open |
Token ID | 9654 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
AST | +0.099 |
elaide | +0.095 |
igree | +0.093 |
outh | +0.093 |
ovember | +0.093 |
Neg logit contributions | |
wash | -0.101 |
↑ | -0.100 |
pak | -0.094 |
kat | -0.092 |
gross | -0.091 |
Token | ends |
Token ID | 5645 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
wash | +0.203 |
↑ | +0.200 |
pak | +0.190 |
kat | +0.185 |
gross | +0.184 |
Neg logit contributions | |
AST | -0.197 |
elaide | -0.189 |
igree | -0.187 |
outh | -0.186 |
ovember | -0.186 |
Token | stand |
Token ID | 1302 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
AST | +0.279 |
elaide | +0.266 |
igree | +0.263 |
outh | +0.262 |
ovember | +0.260 |
Neg logit contributions | |
wash | -0.349 |
↑ | -0.346 |
pak | -0.329 |
kat | -0.320 |
gross | -0.319 |
Token | over |
Token ID | 625 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
AST | +0.129 |
elaide | +0.123 |
igree | +0.122 |
outh | +0.121 |
ovember | +0.121 |
Neg logit contributions | |
wash | -0.148 |
↑ | -0.145 |
pak | -0.139 |
kat | -0.135 |
gross | -0.135 |
Token | an |
Token ID | 281 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
wash | +0.110 |
↑ | +0.108 |
pak | +0.103 |
kat | +0.101 |
gross | +0.101 |
Neg logit contributions | |
AST | -0.077 |
elaide | -0.073 |
igree | -0.072 |
outh | -0.072 |
ovember | -0.071 |
Token | empty |
Token ID | 6565 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
AST | +0.035 |
elaide | +0.034 |
igree | +0.033 |
outh | +0.033 |
ovember | +0.033 |
Neg logit contributions | |
wash | -0.040 |
↑ | -0.039 |
pak | -0.038 |
kat | -0.037 |
gross | -0.036 |
Token | court |
Token ID | 2184 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
wash | +0.947 |
↑ | +0.932 |
pak | +0.892 |
kat | +0.870 |
gross | +0.866 |
Neg logit contributions | |
AST | -0.650 |
elaide | -0.624 |
igree | -0.613 |
outh | -0.610 |
ovember | -0.608 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
AST | +1.791 |
elaide | +1.702 |
igree | +1.683 |
outh | +1.678 |
ovember | +1.668 |
Neg logit contributions | |
wash | -2.161 |
↑ | -2.159 |
pak | -2.046 |
kat | -1.989 |
gross | -1.986 |
Token |
|
Token ID | 198 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
AST | +0.036 |
elaide | +0.034 |
igree | +0.034 |
outh | +0.034 |
ovember | +0.034 |
Neg logit contributions | |
wash | -0.040 |
↑ | -0.039 |
pak | -0.037 |
kat | -0.036 |
gross | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
wash | +0.133 |
↑ | +0.131 |
pak | +0.125 |
gross | +0.123 |
kat | +0.122 |
Neg logit contributions | |
AST | -0.110 |
outh | -0.103 |
Monarch | -0.101 |
ADHD | -0.101 |
Lyme | -0.101 |
Token | The |
Token ID | 464 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
wash | +0.099 |
↑ | +0.097 |
pak | +0.092 |
kat | +0.089 |
gross | +0.089 |
Neg logit contributions | |
AST | -0.117 |
elaide | -0.112 |
outh | -0.112 |
igree | -0.111 |
ovember | -0.111 |
Token | goals |
Token ID | 4661 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
wash | +0.158 |
↑ | +0.156 |
pak | +0.149 |
kat | +0.145 |
gross | +0.145 |
Neg logit contributions | |
AST | -0.129 |
elaide | -0.124 |
igree | -0.122 |
outh | -0.122 |
ovember | -0.121 |
Token | played |
Token ID | 2826 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
AST | +0.104 |
elaide | +0.099 |
igree | +0.098 |
outh | +0.098 |
ovember | +0.097 |
Neg logit contributions | |
wash | -0.104 |
↑ | -0.103 |
pak | -0.097 |
kat | -0.095 |
gross | -0.094 |
Token | on |
Token ID | 319 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
AST | +0.457 |
elaide | +0.433 |
igree | +0.427 |
ovember | +0.427 |
outh | +0.427 |
Neg logit contributions | |
wash | -0.561 |
↑ | -0.555 |
pak | -0.529 |
kat | -0.515 |
gross | -0.513 |
Token | a |
Token ID | 257 |
Feature activation | -8.44e-04 |
Pos logit contributions | |
AST | +0.025 |
elaide | +0.023 |
igree | +0.023 |
outh | +0.023 |
ovember | +0.023 |
Neg logit contributions | |
wash | -0.034 |
↑ | -0.034 |
pak | -0.032 |
kat | -0.031 |
gross | -0.031 |
Token | half |
Token ID | 2063 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
AST | +0.001 |
elaide | +0.001 |
igree | +0.001 |
outh | +0.001 |
ovember | +0.001 |
Neg logit contributions | |
wash | -0.002 |
↑ | -0.002 |
pak | -0.002 |
kat | -0.002 |
gross | -0.002 |
Token | - |
Token ID | 12 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
AST | +0.467 |
elaide | +0.440 |
igree | +0.433 |
outh | +0.432 |
ovember | +0.429 |
Neg logit contributions | |
wash | -0.809 |
↑ | -0.801 |
pak | -0.767 |
kat | -0.750 |
gross | -0.749 |
Token | court |
Token ID | 22230 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
wash | +0.048 |
↑ | +0.048 |
pak | +0.045 |
kat | +0.044 |
gross | +0.044 |
Neg logit contributions | |
AST | -0.034 |
elaide | -0.032 |
igree | -0.031 |
outh | -0.031 |
ovember | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
AST | +1.598 |
elaide | +1.486 |
outh | +1.477 |
igree | +1.477 |
Monarch | +1.461 |
Neg logit contributions | |
wash | -2.371 |
↑ | -2.357 |
pak | -2.259 |
kat | -2.187 |
gross | -2.185 |
Token | the |
Token ID | 262 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
AST | +0.026 |
elaide | +0.024 |
igree | +0.024 |
outh | +0.024 |
ovember | +0.024 |
Neg logit contributions | |
wash | -0.037 |
↑ | -0.036 |
pak | -0.035 |
kat | -0.034 |
gross | -0.034 |
Token | yard |
Token ID | 12699 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
AST | +0.067 |
elaide | +0.063 |
igree | +0.062 |
outh | +0.062 |
ovember | +0.062 |
Neg logit contributions | |
wash | -0.094 |
↑ | -0.093 |
pak | -0.089 |
kat | -0.087 |
gross | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
AST | +0.117 |
elaide | +0.112 |
igree | +0.110 |
outh | +0.110 |
ovember | +0.109 |
Neg logit contributions | |
wash | -0.147 |
↑ | -0.145 |
pak | -0.138 |
kat | -0.135 |
gross | -0.134 |
Token | with |
Token ID | 351 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
wash | +0.200 |
↑ | +0.198 |
pak | +0.188 |
kat | +0.183 |
gross | +0.183 |
Neg logit contributions | |
AST | -0.167 |
elaide | -0.160 |
igree | -0.158 |
outh | -0.158 |
ovember | -0.157 |
Token | Pre |
Token ID | 3771 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
wash | +0.106 |
↑ | +0.105 |
pak | +0.100 |
gross | +0.098 |
kat | +0.098 |
Neg logit contributions | |
AST | -0.089 |
Monarch | -0.083 |
outh | -0.082 |
Lyme | -0.082 |
igree | -0.082 |
Token | y |
Token ID | 88 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
AST | +0.251 |
outh | +0.244 |
igree | +0.238 |
elaide | +0.236 |
ADHD | +0.236 |
Neg logit contributions | |
wash | -0.228 |
↑ | -0.225 |
pak | -0.214 |
gross | -0.209 |
kat | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-04 |
Pos logit contributions | |
wash | +0.081 |
↑ | +0.080 |
pak | +0.076 |
kat | +0.074 |
gross | +0.074 |
Neg logit contributions | |
AST | -0.075 |
elaide | -0.071 |
igree | -0.070 |
outh | -0.070 |
ovember | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
AST | +0.000 |
outh | +0.000 |
Monarch | +0.000 |
ADHD | +0.000 |
Lyme | +0.000 |
Neg logit contributions | |
wash | -0.000 |
↑ | -0.000 |
pak | -0.000 |
gross | -0.000 |
kat | -0.000 |
Token | https |
Token ID | 5450 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
AST | +0.014 |
elaide | +0.014 |
outh | +0.014 |
igree | +0.014 |
ovember | +0.014 |
Neg logit contributions | |
wash | -0.011 |
↑ | -0.011 |
pak | -0.010 |
kat | -0.010 |
gross | -0.010 |
Token | :// |
Token ID | 1378 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
wash | +1.523 |
↑ | +1.499 |
pak | +1.414 |
kat | +1.370 |
gross | +1.366 |
Neg logit contributions | |
AST | -1.773 |
elaide | -1.702 |
igree | -1.683 |
outh | -1.683 |
ovember | -1.674 |
Token | kill |
Token ID | 12728 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
wash | +1.593 |
↑ | +1.565 |
pak | +1.481 |
kat | +1.439 |
gross | +1.433 |
Neg logit contributions | |
AST | -1.792 |
elaide | -1.718 |
igree | -1.695 |
ovember | -1.693 |
outh | -1.693 |
Token | ert |
Token ID | 861 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
wash | +0.524 |
↑ | +0.515 |
pak | +0.486 |
kat | +0.471 |
gross | +0.470 |
Neg logit contributions | |
AST | -0.603 |
elaide | -0.579 |
igree | -0.573 |
outh | -0.572 |
ovember | -0.569 |
Token | of |
Token ID | 1659 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
wash | +1.289 |
↑ | +1.258 |
pak | +1.205 |
kat | +1.172 |
gross | +1.168 |
Neg logit contributions | |
AST | -1.216 |
elaide | -1.155 |
igree | -1.138 |
ovember | -1.133 |
outh | -1.131 |
Token | ure |
Token ID | 495 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
AST | +0.052 |
elaide | +0.050 |
igree | +0.050 |
outh | +0.050 |
ovember | +0.049 |
Neg logit contributions | |
↑ | -0.048 |
wash | -0.048 |
pak | -0.044 |
kat | -0.043 |
gross | -0.043 |
Token | c |
Token ID | 66 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
AST | +0.587 |
elaide | +0.565 |
outh | +0.565 |
igree | +0.562 |
ovember | +0.556 |
Neg logit contributions | |
wash | -0.451 |
↑ | -0.447 |
pak | -0.416 |
gross | -0.402 |
kat | -0.401 |
Token |
|
Token ID | 198 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
AST | +0.094 |
outh | +0.088 |
Monarch | +0.086 |
ADHD | +0.086 |
elaide | +0.086 |
Neg logit contributions | |
wash | -0.114 |
↑ | -0.111 |
pak | -0.107 |
gross | -0.105 |
kat | -0.104 |
Token | You |
Token ID | 1639 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
AST | +0.147 |
elaide | +0.141 |
igree | +0.140 |
outh | +0.139 |
ovember | +0.139 |
Neg logit contributions | |
wash | -0.127 |
↑ | -0.125 |
pak | -0.118 |
kat | -0.115 |
gross | -0.114 |
Token | can |
Token ID | 460 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
AST | +0.387 |
elaide | +0.370 |
igree | +0.366 |
outh | +0.366 |
ovember | +0.364 |
Neg logit contributions | |
wash | -0.390 |
↑ | -0.384 |
pak | -0.365 |
kat | -0.355 |
gross | -0.354 |
Token | pick |
Token ID | 2298 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
AST | +0.131 |
elaide | +0.125 |
igree | +0.124 |
outh | +0.123 |
ovember | +0.123 |
Neg logit contributions | |
wash | -0.138 |
↑ | -0.136 |
pak | -0.129 |
kat | -0.125 |
gross | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
AST | +0.117 |
elaide | +0.111 |
igree | +0.109 |
outh | +0.109 |
ovember | +0.109 |
Neg logit contributions | |
wash | -0.154 |
↑ | -0.152 |
pak | -0.145 |
kat | -0.142 |
gross | -0.141 |
Token | maths |
Token ID | 47761 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
wash | +0.088 |
↑ | +0.087 |
pak | +0.083 |
kat | +0.080 |
gross | +0.080 |
Neg logit contributions | |
AST | -0.069 |
elaide | -0.066 |
igree | -0.065 |
outh | -0.065 |
ovember | -0.065 |
Token | teacher |
Token ID | 4701 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
wash | +1.405 |
↑ | +1.390 |
pak | +1.327 |
kat | +1.293 |
gross | +1.288 |
Neg logit contributions | |
AST | -1.017 |
elaide | -0.978 |
igree | -0.967 |
ovember | -0.961 |
outh | -0.956 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
wash | +0.437 |
↑ | +0.431 |
pak | +0.410 |
kat | +0.400 |
gross | +0.398 |
Neg logit contributions | |
AST | -0.367 |
elaide | -0.351 |
igree | -0.346 |
outh | -0.345 |
ovember | -0.344 |
Token | a |
Token ID | 257 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
AST | +0.190 |
elaide | +0.181 |
igree | +0.178 |
outh | +0.178 |
ovember | +0.177 |
Neg logit contributions | |
wash | -0.251 |
↑ | -0.248 |
pak | -0.237 |
kat | -0.231 |
gross | -0.230 |
Token | mental |
Token ID | 5110 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
AST | +0.007 |
elaide | +0.006 |
igree | +0.006 |
outh | +0.006 |
ovember | +0.006 |
Neg logit contributions | |
wash | -0.009 |
↑ | -0.009 |
pak | -0.008 |
kat | -0.008 |
gross | -0.008 |
Token | capacity |
Token ID | 5339 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
AST | +0.072 |
elaide | +0.068 |
outh | +0.067 |
igree | +0.067 |
ovember | +0.067 |
Neg logit contributions | |
wash | -0.091 |
↑ | -0.090 |
pak | -0.085 |
kat | -0.083 |
gross | -0.083 |
Token | DPR |
Token ID | 41176 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
AST | +0.159 |
elaide | +0.150 |
igree | +0.148 |
outh | +0.148 |
ovember | +0.147 |
Neg logit contributions | |
wash | -0.228 |
↑ | -0.226 |
pak | -0.215 |
kat | -0.210 |
gross | -0.210 |
Token | Korea |
Token ID | 4969 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
AST | +0.025 |
elaide | +0.024 |
igree | +0.024 |
outh | +0.024 |
ovember | +0.024 |
Neg logit contributions | |
wash | -0.026 |
↑ | -0.026 |
pak | -0.024 |
kat | -0.024 |
gross | -0.024 |
Token | lose |
Token ID | 4425 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
AST | +0.307 |
elaide | +0.293 |
outh | +0.289 |
igree | +0.289 |
ovember | +0.287 |
Neg logit contributions | |
wash | -0.329 |
↑ | -0.325 |
pak | -0.308 |
kat | -0.300 |
gross | -0.300 |
Token | their |
Token ID | 511 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
AST | +0.092 |
elaide | +0.088 |
igree | +0.086 |
outh | +0.086 |
ovember | +0.086 |
Neg logit contributions | |
wash | -0.118 |
↑ | -0.116 |
pak | -0.111 |
kat | -0.108 |
gross | -0.108 |
Token | last |
Token ID | 938 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
wash | +0.038 |
↑ | +0.038 |
pak | +0.036 |
kat | +0.035 |
gross | +0.035 |
Neg logit contributions | |
AST | -0.037 |
elaide | -0.036 |
outh | -0.035 |
igree | -0.035 |
ovember | -0.035 |
Token | match |
Token ID | 2872 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
AST | +0.260 |
elaide | +0.246 |
igree | +0.242 |
outh | +0.241 |
ovember | +0.240 |
Neg logit contributions | |
wash | -0.428 |
↑ | -0.423 |
pak | -0.405 |
kat | -0.397 |
gross | -0.396 |
Token | against |
Token ID | 1028 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
wash | +1.281 |
↑ | +1.264 |
pak | +1.202 |
kat | +1.171 |
gross | +1.164 |
Neg logit contributions | |
AST | -1.128 |
elaide | -1.081 |
igree | -1.069 |
outh | -1.064 |
ovember | -1.062 |
Token | the |
Token ID | 262 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
wash | +0.259 |
↑ | +0.256 |
pak | +0.244 |
kat | +0.238 |
gross | +0.238 |
Neg logit contributions | |
AST | -0.185 |
elaide | -0.176 |
igree | -0.174 |
outh | -0.173 |
ovember | -0.172 |
Token | Philippines |
Token ID | 13316 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
AST | +0.082 |
elaide | +0.077 |
outh | +0.076 |
igree | +0.076 |
ovember | +0.076 |
Neg logit contributions | |
wash | -0.100 |
↑ | -0.099 |
pak | -0.094 |
kat | -0.092 |
gross | -0.092 |
Token | in |
Token ID | 287 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
AST | +0.211 |
elaide | +0.200 |
outh | +0.198 |
igree | +0.197 |
ovember | +0.196 |
Neg logit contributions | |
wash | -0.270 |
↑ | -0.266 |
pak | -0.254 |
kat | -0.248 |
gross | -0.247 |
Token | Manila |
Token ID | 31721 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
AST | +0.081 |
elaide | +0.077 |
outh | +0.076 |
igree | +0.076 |
ovember | +0.075 |
Neg logit contributions | |
wash | -0.089 |
↑ | -0.088 |
pak | -0.083 |
gross | -0.081 |
kat | -0.081 |
Token | address |
Token ID | 21975 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
AST | +0.334 |
elaide | +0.320 |
outh | +0.316 |
igree | +0.315 |
ovember | +0.312 |
Neg logit contributions | |
wash | -0.347 |
↑ | -0.342 |
pak | -0.325 |
kat | -0.316 |
gross | -0.315 |
Token | of |
Token ID | 286 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
wash | +0.661 |
↑ | +0.653 |
pak | +0.623 |
kat | +0.607 |
gross | +0.605 |
Neg logit contributions | |
AST | -0.500 |
elaide | -0.478 |
igree | -0.472 |
outh | -0.468 |
ovember | -0.468 |
Token | system |
Token ID | 1080 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
AST | +0.049 |
elaide | +0.047 |
igree | +0.046 |
outh | +0.046 |
ovember | +0.046 |
Neg logit contributions | |
wash | -0.057 |
↑ | -0.056 |
pak | -0.053 |
kat | -0.052 |
gross | -0.052 |
Token | ] |
Token ID | 60 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
wash | +0.200 |
↑ | +0.198 |
pak | +0.191 |
kat | +0.187 |
gross | +0.186 |
Neg logit contributions | |
AST | -0.092 |
elaide | -0.086 |
igree | -0.084 |
outh | -0.084 |
ovember | -0.084 |
Token | | |
Token ID | 930 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
AST | +0.306 |
outh | +0.280 |
Monarch | +0.278 |
elaide | +0.277 |
ADHD | +0.276 |
Neg logit contributions | |
wash | -0.448 |
↑ | -0.435 |
pak | -0.419 |
gross | -0.412 |
kat | -0.410 |
Token | < |
Token ID | 1279 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
AST | +0.398 |
elaide | +0.380 |
igree | +0.375 |
outh | +0.375 |
ovember | +0.373 |
Neg logit contributions | |
wash | -0.357 |
↑ | -0.350 |
pak | -0.332 |
kat | -0.322 |
gross | -0.321 |
Token | -- |
Token ID | 438 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
wash | +1.680 |
↑ | +1.663 |
pak | +1.589 |
kat | +1.548 |
gross | +1.543 |
Neg logit contributions | |
AST | -1.122 |
elaide | -1.074 |
igree | -1.055 |
outh | -1.045 |
ovember | -1.045 |
Token | stack |
Token ID | 8931 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
AST | +0.391 |
elaide | +0.369 |
igree | +0.364 |
outh | +0.363 |
ovember | +0.360 |
Neg logit contributions | |
wash | -0.615 |
↑ | -0.608 |
pak | -0.581 |
kat | -0.569 |
gross | -0.567 |
Token | pointer |
Token ID | 17562 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
wash | +0.459 |
↑ | +0.455 |
pak | +0.437 |
kat | +0.429 |
gross | +0.428 |
Neg logit contributions | |
AST | -0.197 |
elaide | -0.183 |
igree | -0.179 |
outh | -0.179 |
ovember | -0.177 |
Token | + |
Token ID | 1343 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
wash | +0.364 |
↑ | +0.358 |
pak | +0.339 |
kat | +0.328 |
gross | +0.327 |
Neg logit contributions | |
AST | -0.413 |
elaide | -0.396 |
igree | -0.392 |
outh | -0.391 |
ovember | -0.389 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
AST | +0.031 |
outh | +0.029 |
elaide | +0.029 |
igree | +0.029 |
ovember | +0.029 |
Neg logit contributions | |
wash | -0.031 |
↑ | -0.030 |
pak | -0.029 |
kat | -0.028 |
gross | -0.028 |
Token | technology |
Token ID | 3037 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
AST | +0.131 |
elaide | +0.125 |
igree | +0.124 |
outh | +0.123 |
ovember | +0.122 |
Neg logit contributions | |
wash | -0.152 |
↑ | -0.150 |
pak | -0.142 |
kat | -0.139 |
gross | -0.138 |
Token | : |
Token ID | 25 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
wash | +0.415 |
↑ | +0.410 |
pak | +0.388 |
kat | +0.379 |
gross | +0.377 |
Neg logit contributions | |
AST | -0.372 |
elaide | -0.356 |
igree | -0.352 |
outh | -0.350 |
ovember | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
AST | +0.006 |
elaide | +0.006 |
outh | +0.006 |
igree | +0.006 |
ovember | +0.006 |
Neg logit contributions | |
wash | -0.007 |
↑ | -0.006 |
pak | -0.006 |
gross | -0.006 |
kat | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
AST | +0.224 |
outh | +0.210 |
ADHD | +0.206 |
Monarch | +0.205 |
Lyme | +0.205 |
Neg logit contributions | |
wash | -0.278 |
↑ | -0.271 |
pak | -0.261 |
gross | -0.256 |
kat | -0.253 |
Token | https |
Token ID | 5450 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
AST | +0.203 |
elaide | +0.196 |
outh | +0.195 |
ovember | +0.194 |
igree | +0.194 |
Neg logit contributions | |
wash | -0.097 |
↑ | -0.094 |
pak | -0.087 |
gross | -0.083 |
kat | -0.082 |
Token | :// |
Token ID | 1378 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
wash | +1.384 |
↑ | +1.362 |
pak | +1.285 |
kat | +1.245 |
gross | +1.242 |
Neg logit contributions | |
AST | -1.603 |
elaide | -1.537 |
outh | -1.522 |
igree | -1.520 |
ovember | -1.513 |
Token | www |
Token ID | 2503 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
wash | +1.020 |
↑ | +0.992 |
pak | +0.915 |
kat | +0.877 |
gross | +0.870 |
Neg logit contributions | |
AST | -2.082 |
elaide | -2.017 |
igree | -1.998 |
outh | -1.991 |
ovember | -1.988 |
Token | . |
Token ID | 13 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
wash | +0.449 |
↑ | +0.442 |
pak | +0.423 |
gross | +0.412 |
kat | +0.410 |
Neg logit contributions | |
AST | -0.371 |
outh | -0.350 |
elaide | -0.346 |
igree | -0.342 |
Monarch | -0.342 |
Token | eff |
Token ID | 14822 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
wash | +0.109 |
↑ | +0.108 |
pak | +0.104 |
kat | +0.102 |
gross | +0.102 |
Neg logit contributions | |
AST | -0.035 |
elaide | -0.032 |
outh | -0.031 |
igree | -0.031 |
ovember | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
AST | +0.131 |
elaide | +0.125 |
outh | +0.124 |
igree | +0.124 |
ovember | +0.123 |
Neg logit contributions | |
wash | -0.153 |
↑ | -0.151 |
pak | -0.143 |
gross | -0.140 |
kat | -0.140 |
Token | org |
Token ID | 2398 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
wash | +0.039 |
↑ | +0.039 |
pak | +0.036 |
kat | +0.035 |
gross | +0.035 |
Neg logit contributions | |
AST | -0.040 |
elaide | -0.038 |
outh | -0.038 |
igree | -0.038 |
ovember | -0.038 |
Token | he |
Token ID | 339 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
wash | +0.209 |
↑ | +0.206 |
pak | +0.197 |
kat | +0.192 |
gross | +0.192 |
Neg logit contributions | |
AST | -0.150 |
elaide | -0.143 |
igree | -0.141 |
outh | -0.140 |
ovember | -0.140 |
Token | 's |
Token ID | 338 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
AST | +0.074 |
elaide | +0.071 |
igree | +0.070 |
outh | +0.070 |
ovember | +0.069 |
Neg logit contributions | |
wash | -0.079 |
↑ | -0.078 |
pak | -0.074 |
kat | -0.072 |
gross | -0.072 |
Token | notorious |
Token ID | 18192 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
wash | +0.212 |
↑ | +0.209 |
pak | +0.198 |
kat | +0.193 |
gross | +0.192 |
Neg logit contributions | |
AST | -0.202 |
elaide | -0.193 |
igree | -0.191 |
outh | -0.190 |
ovember | -0.189 |
Token | about |
Token ID | 546 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
wash | +0.640 |
↑ | +0.631 |
pak | +0.600 |
kat | +0.584 |
gross | +0.582 |
Neg logit contributions | |
AST | -0.554 |
elaide | -0.531 |
igree | -0.523 |
outh | -0.522 |
ovember | -0.521 |
Token | stealing |
Token ID | 16568 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
AST | +0.249 |
elaide | +0.237 |
igree | +0.234 |
outh | +0.234 |
ovember | +0.232 |
Neg logit contributions | |
wash | -0.310 |
↑ | -0.306 |
pak | -0.292 |
kat | -0.284 |
gross | -0.284 |
Token | players |
Token ID | 1938 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
AST | +1.151 |
elaide | +1.088 |
outh | +1.082 |
igree | +1.080 |
Monarch | +1.075 |
Neg logit contributions | |
wash | -1.288 |
↑ | -1.268 |
pak | -1.211 |
kat | -1.180 |
gross | -1.180 |
Token | from |
Token ID | 422 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
wash | +0.251 |
↑ | +0.248 |
pak | +0.236 |
kat | +0.229 |
gross | +0.229 |
Neg logit contributions | |
AST | -0.222 |
elaide | -0.213 |
igree | -0.210 |
outh | -0.209 |
ovember | -0.209 |
Token | other |
Token ID | 584 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
AST | +0.159 |
elaide | +0.152 |
igree | +0.150 |
outh | +0.149 |
ovember | +0.149 |
Neg logit contributions | |
wash | -0.201 |
↑ | -0.199 |
pak | -0.189 |
kat | -0.184 |
gross | -0.184 |
Token | team |
Token ID | 1074 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
AST | +0.124 |
elaide | +0.118 |
igree | +0.117 |
outh | +0.117 |
ovember | +0.116 |
Neg logit contributions | |
wash | -0.138 |
↑ | -0.136 |
pak | -0.130 |
kat | -0.126 |
gross | -0.126 |
Token | such |
Token ID | 884 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
wash | +0.058 |
↑ | +0.057 |
pak | +0.054 |
kat | +0.053 |
gross | +0.053 |
Neg logit contributions | |
AST | -0.053 |
elaide | -0.050 |
igree | -0.050 |
outh | -0.050 |
ovember | -0.049 |
Token | as |
Token ID | 355 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
AST | +0.621 |
elaide | +0.594 |
igree | +0.587 |
outh | +0.586 |
ovember | +0.582 |
Neg logit contributions | |
wash | -0.610 |
↑ | -0.603 |
pak | -0.567 |
gross | -0.552 |
kat | -0.551 |
Token | : |
Token ID | 25 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
AST | +1.282 |
outh | +1.201 |
ADHD | +1.190 |
Lyme | +1.174 |
Monarch | +1.170 |
Neg logit contributions | |
wash | -1.463 |
↑ | -1.419 |
pak | -1.361 |
gross | -1.346 |
kat | -1.327 |
Token | Carly |
Token ID | 35982 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
wash | +0.040 |
↑ | +0.038 |
pak | +0.036 |
gross | +0.036 |
kat | +0.035 |
Neg logit contributions | |
AST | -0.057 |
Lyme | -0.053 |
outh | -0.053 |
Monarch | -0.053 |
ADHD | -0.053 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
wash | +0.036 |
↑ | +0.034 |
pak | +0.032 |
kat | +0.031 |
gross | +0.031 |
Neg logit contributions | |
AST | -0.079 |
outh | -0.076 |
Lyme | -0.075 |
igree | -0.075 |
ADHD | -0.075 |
Token | 's |
Token ID | 338 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
AST | +0.058 |
outh | +0.054 |
elaide | +0.054 |
Monarch | +0.054 |
igree | +0.053 |
Neg logit contributions | |
wash | -0.079 |
↑ | -0.078 |
pak | -0.074 |
gross | -0.073 |
kat | -0.073 |
Token | political |
Token ID | 1964 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
wash | +0.026 |
↑ | +0.026 |
pak | +0.024 |
kat | +0.024 |
gross | +0.023 |
Neg logit contributions | |
AST | -0.025 |
outh | -0.024 |
elaide | -0.024 |
igree | -0.023 |
Monarch | -0.023 |
Token | career |
Token ID | 3451 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
wash | +0.591 |
↑ | +0.584 |
pak | +0.557 |
kat | +0.543 |
gross | +0.542 |
Neg logit contributions | |
AST | -0.429 |
elaide | -0.410 |
igree | -0.403 |
outh | -0.402 |
ovember | -0.400 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
wash | +0.574 |
↑ | +0.561 |
pak | +0.513 |
kat | +0.488 |
gross | +0.488 |
Neg logit contributions | |
AST | -1.282 |
elaide | -1.237 |
outh | -1.230 |
igree | -1.229 |
ovember | -1.222 |
Token | speaks |
Token ID | 9209 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
AST | +0.092 |
elaide | +0.087 |
outh | +0.086 |
igree | +0.086 |
ovember | +0.086 |
Neg logit contributions | |
wash | -0.098 |
↑ | -0.097 |
pak | -0.092 |
kat | -0.089 |
gross | -0.089 |
Token | during |
Token ID | 1141 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
AST | +0.628 |
elaide | +0.588 |
outh | +0.588 |
ovember | +0.586 |
igree | +0.584 |
Neg logit contributions | |
wash | -0.736 |
↑ | -0.734 |
pak | -0.694 |
kat | -0.678 |
gross | -0.677 |
Token | a |
Token ID | 257 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
AST | +0.058 |
elaide | +0.054 |
outh | +0.054 |
igree | +0.053 |
Monarch | +0.053 |
Neg logit contributions | |
wash | -0.091 |
↑ | -0.090 |
pak | -0.085 |
kat | -0.084 |
gross | -0.084 |
Token | forum |
Token ID | 10041 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
wash | +0.059 |
↑ | +0.059 |
pak | +0.056 |
kat | +0.055 |
gross | +0.054 |
Neg logit contributions | |
AST | -0.046 |
outh | -0.044 |
elaide | -0.043 |
Monarch | -0.043 |
ovember | -0.043 |
Token | � |
Token ID | 247 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
wash | +0.384 |
↑ | +0.377 |
pak | +0.362 |
kat | +0.355 |
gross | +0.351 |
Neg logit contributions | |
AST | -0.239 |
elaide | -0.226 |
igree | -0.225 |
outh | -0.223 |
ovember | -0.221 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
wash | +0.058 |
↑ | +0.057 |
pak | +0.055 |
kat | +0.053 |
gross | +0.053 |
Neg logit contributions | |
AST | -0.051 |
elaide | -0.049 |
igree | -0.048 |
outh | -0.048 |
ovember | -0.048 |
Token | � |
Token ID | 564 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
AST | +0.051 |
elaide | +0.048 |
igree | +0.047 |
outh | +0.047 |
ovember | +0.047 |
Neg logit contributions | |
wash | -0.061 |
↑ | -0.060 |
pak | -0.057 |
kat | -0.055 |
gross | -0.055 |
Token | � |
Token ID | 246 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
AST | +0.011 |
elaide | +0.011 |
igree | +0.011 |
outh | +0.011 |
ovember | +0.010 |
Neg logit contributions | |
wash | -0.014 |
↑ | -0.014 |
pak | -0.013 |
kat | -0.013 |
gross | -0.013 |
Token | Every |
Token ID | 6109 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
wash | +0.017 |
↑ | +0.016 |
pak | +0.016 |
kat | +0.015 |
gross | +0.015 |
Neg logit contributions | |
AST | -0.019 |
elaide | -0.018 |
outh | -0.018 |
igree | -0.018 |
ovember | -0.018 |
Token | Time |
Token ID | 3862 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
AST | +0.038 |
elaide | +0.037 |
igree | +0.036 |
outh | +0.036 |
ovember | +0.036 |
Neg logit contributions | |
wash | -0.046 |
↑ | -0.046 |
pak | -0.044 |
kat | -0.043 |
gross | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
wash | +0.276 |
↑ | +0.273 |
pak | +0.260 |
kat | +0.253 |
gross | +0.252 |
Neg logit contributions | |
AST | -0.222 |
elaide | -0.212 |
igree | -0.209 |
outh | -0.208 |
ovember | -0.208 |
Token | Sun |
Token ID | 3825 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
wash | +0.263 |
↑ | +0.260 |
pak | +0.247 |
kat | +0.240 |
gross | +0.239 |
Neg logit contributions | |
AST | -0.229 |
elaide | -0.220 |
igree | -0.216 |
outh | -0.216 |
ovember | -0.216 |
Token | Comes |
Token ID | 34606 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
AST | +0.363 |
elaide | +0.342 |
outh | +0.339 |
igree | +0.338 |
Monarch | +0.337 |
Neg logit contributions | |
wash | -0.352 |
↑ | -0.347 |
pak | -0.328 |
kat | -0.320 |
gross | -0.319 |
Token | Up |
Token ID | 3205 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
wash | +0.285 |
↑ | +0.282 |
pak | +0.270 |
kat | +0.263 |
gross | +0.263 |
Neg logit contributions | |
AST | -0.189 |
elaide | -0.179 |
igree | -0.176 |
outh | -0.176 |
ovember | -0.175 |
Token | � |
Token ID | 447 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
wash | +0.105 |
↑ | +0.104 |
pak | +0.098 |
kat | +0.095 |
gross | +0.095 |
Neg logit contributions | |
AST | -0.115 |
elaide | -0.110 |
igree | -0.109 |
outh | -0.109 |
ovember | -0.108 |
Token | video |
Token ID | 2008 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
AST | +0.030 |
elaide | +0.028 |
igree | +0.028 |
outh | +0.028 |
ovember | +0.028 |
Neg logit contributions | |
wash | -0.035 |
↑ | -0.034 |
pak | -0.033 |
kat | -0.032 |
gross | -0.032 |
Token | that |
Token ID | 326 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
AST | +0.360 |
elaide | +0.345 |
igree | +0.341 |
outh | +0.340 |
ovember | +0.339 |
Neg logit contributions | |
wash | -0.389 |
↑ | -0.384 |
pak | -0.365 |
kat | -0.355 |
gross | -0.354 |
Token | I |
Token ID | 314 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
AST | +0.099 |
elaide | +0.094 |
igree | +0.093 |
outh | +0.093 |
ovember | +0.092 |
Neg logit contributions | |
wash | -0.109 |
↑ | -0.107 |
pak | -0.102 |
kat | -0.099 |
gross | -0.099 |
Token | have |
Token ID | 423 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
wash | +0.032 |
↑ | +0.032 |
pak | +0.030 |
kat | +0.029 |
gross | +0.029 |
Neg logit contributions | |
AST | -0.031 |
elaide | -0.030 |
igree | -0.029 |
outh | -0.029 |
ovember | -0.029 |
Token | never |
Token ID | 1239 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
AST | +0.018 |
elaide | +0.017 |
outh | +0.017 |
igree | +0.017 |
ovember | +0.017 |
Neg logit contributions | |
wash | -0.021 |
↑ | -0.020 |
pak | -0.019 |
kat | -0.019 |
gross | -0.019 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
AST | +0.221 |
elaide | +0.208 |
outh | +0.207 |
igree | +0.205 |
ovember | +0.205 |
Neg logit contributions | |
wash | -0.312 |
↑ | -0.308 |
pak | -0.293 |
kat | -0.287 |
gross | -0.286 |
Token | or |
Token ID | 393 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
wash | +0.035 |
↑ | +0.035 |
pak | +0.033 |
kat | +0.032 |
gross | +0.032 |
Neg logit contributions | |
AST | -0.031 |
elaide | -0.029 |
outh | -0.029 |
igree | -0.029 |
ovember | -0.029 |
Token | does |
Token ID | 857 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
AST | +0.126 |
elaide | +0.120 |
outh | +0.118 |
igree | +0.118 |
ovember | +0.118 |
Neg logit contributions | |
wash | -0.164 |
↑ | -0.162 |
pak | -0.155 |
kat | -0.151 |
gross | -0.151 |
Token | not |
Token ID | 407 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
wash | +0.227 |
↑ | +0.221 |
pak | +0.209 |
kat | +0.202 |
gross | +0.201 |
Neg logit contributions | |
AST | -0.303 |
elaide | -0.291 |
outh | -0.289 |
igree | -0.288 |
ovember | -0.287 |
Token | exist |
Token ID | 2152 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
AST | +0.053 |
elaide | +0.051 |
outh | +0.050 |
igree | +0.050 |
ovember | +0.050 |
Neg logit contributions | |
wash | -0.057 |
↑ | -0.056 |
pak | -0.053 |
kat | -0.051 |
gross | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
AST | +0.454 |
elaide | +0.434 |
outh | +0.430 |
igree | +0.428 |
ovember | +0.426 |
Neg logit contributions | |
wash | -0.537 |
↑ | -0.526 |
pak | -0.501 |
gross | -0.487 |
kat | -0.486 |
Token | and |
Token ID | 290 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
wash | +0.506 |
↑ | +0.500 |
pak | +0.475 |
gross | +0.462 |
kat | +0.461 |
Neg logit contributions | |
AST | -0.472 |
elaide | -0.449 |
outh | -0.444 |
igree | -0.444 |
ovember | -0.441 |
Token | white |
Token ID | 2330 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
wash | +0.121 |
↑ | +0.119 |
pak | +0.114 |
kat | +0.111 |
gross | +0.111 |
Neg logit contributions | |
AST | -0.079 |
elaide | -0.075 |
igree | -0.074 |
outh | -0.074 |
ovember | -0.074 |
Token | ? |
Token ID | 30 |
Feature activation | +5.50e-03 |
Pos logit contributions | |
AST | +0.495 |
elaide | +0.464 |
outh | +0.464 |
Monarch | +0.463 |
igree | +0.462 |
Neg logit contributions | |
wash | -0.481 |
↑ | -0.471 |
pak | -0.449 |
gross | -0.438 |
kat | -0.433 |
Token | Although |
Token ID | 4900 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
wash | +0.010 |
↑ | +0.010 |
pak | +0.009 |
kat | +0.009 |
gross | +0.009 |
Neg logit contributions | |
AST | -0.010 |
elaide | -0.009 |
igree | -0.009 |
outh | -0.009 |
ovember | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
AST | +0.054 |
elaide | +0.051 |
igree | +0.050 |
outh | +0.050 |
ovember | +0.050 |
Neg logit contributions | |
wash | -0.073 |
↑ | -0.073 |
pak | -0.069 |
kat | -0.068 |
gross | -0.067 |
Token | color |
Token ID | 3124 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
wash | +0.130 |
↑ | +0.127 |
pak | +0.121 |
kat | +0.118 |
gross | +0.118 |
Neg logit contributions | |
AST | -0.120 |
elaide | -0.113 |
igree | -0.112 |
outh | -0.112 |
ovember | -0.112 |
Token | of |
Token ID | 286 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
wash | +0.418 |
↑ | +0.412 |
pak | +0.391 |
kat | +0.381 |
gross | +0.380 |
Neg logit contributions | |
AST | -0.361 |
elaide | -0.346 |
igree | -0.341 |
outh | -0.340 |
ovember | -0.338 |
Token | the |
Token ID | 262 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
wash | +0.047 |
↑ | +0.047 |
pak | +0.045 |
kat | +0.044 |
gross | +0.044 |
Neg logit contributions | |
AST | -0.032 |
elaide | -0.030 |
outh | -0.030 |
igree | -0.029 |
ovember | -0.029 |
Token | device |
Token ID | 3335 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
wash | +0.120 |
↑ | +0.118 |
pak | +0.112 |
gross | +0.110 |
kat | +0.109 |
Neg logit contributions | |
AST | -0.112 |
elaide | -0.105 |
outh | -0.105 |
igree | -0.105 |
ovember | -0.104 |
Token | has |
Token ID | 468 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
AST | +0.029 |
elaide | +0.028 |
igree | +0.027 |
outh | +0.027 |
ovember | +0.027 |
Neg logit contributions | |
wash | -0.029 |
↑ | -0.029 |
pak | -0.027 |
kat | -0.026 |
gross | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
AST | +0.022 |
elaide | +0.021 |
outh | +0.021 |
igree | +0.021 |
ovember | +0.021 |
Neg logit contributions | |
wash | -0.022 |
↑ | -0.022 |
pak | -0.020 |
kat | -0.020 |
gross | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
AST | +0.083 |
elaide | +0.079 |
igree | +0.078 |
outh | +0.078 |
ovember | +0.078 |
Neg logit contributions | |
wash | -0.098 |
↑ | -0.097 |
pak | -0.092 |
kat | -0.090 |
gross | -0.089 |
Token | two |
Token ID | 734 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
AST | +0.125 |
elaide | +0.119 |
igree | +0.118 |
outh | +0.118 |
ovember | +0.117 |
Neg logit contributions | |
wash | -0.164 |
↑ | -0.161 |
pak | -0.154 |
kat | -0.150 |
gross | -0.150 |
Token | touchdowns |
Token ID | 17692 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
AST | +0.186 |
elaide | +0.177 |
igree | +0.175 |
outh | +0.174 |
ovember | +0.173 |
Neg logit contributions | |
wash | -0.206 |
↑ | -0.204 |
pak | -0.194 |
kat | -0.189 |
gross | -0.189 |
Token | through |
Token ID | 832 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
wash | +0.764 |
↑ | +0.753 |
pak | +0.716 |
kat | +0.697 |
gross | +0.695 |
Neg logit contributions | |
AST | -0.656 |
elaide | -0.628 |
igree | -0.621 |
outh | -0.618 |
ovember | -0.616 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
AST | +0.672 |
elaide | +0.634 |
igree | +0.622 |
outh | +0.621 |
ovember | +0.618 |
Neg logit contributions | |
wash | -1.051 |
↑ | -1.044 |
pak | -0.997 |
kat | -0.976 |
gross | -0.973 |
Token | air |
Token ID | 1633 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
wash | +0.047 |
↑ | +0.046 |
pak | +0.044 |
kat | +0.043 |
gross | +0.043 |
Neg logit contributions | |
AST | -0.044 |
elaide | -0.041 |
igree | -0.041 |
outh | -0.041 |
ovember | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
AST | +0.222 |
elaide | +0.212 |
igree | +0.209 |
outh | +0.209 |
ovember | +0.208 |
Neg logit contributions | |
wash | -0.271 |
↑ | -0.268 |
pak | -0.255 |
kat | -0.249 |
gross | -0.248 |
Token | Per |
Token ID | 2448 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
AST | +0.067 |
elaide | +0.064 |
igree | +0.063 |
outh | +0.063 |
ovember | +0.063 |
Neg logit contributions | |
wash | -0.071 |
↑ | -0.070 |
pak | -0.066 |
kat | -0.064 |
gross | -0.064 |
Token | Football |
Token ID | 9957 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
AST | +0.376 |
elaide | +0.355 |
igree | +0.350 |
outh | +0.349 |
ovember | +0.346 |
Neg logit contributions | |
wash | -0.573 |
↑ | -0.567 |
pak | -0.542 |
kat | -0.530 |
gross | -0.528 |
Token | Outs |
Token ID | 46580 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
AST | +0.185 |
elaide | +0.171 |
igree | +0.170 |
outh | +0.168 |
ovember | +0.167 |
Neg logit contributions | |
wash | -0.355 |
↑ | -0.352 |
pak | -0.337 |
kat | -0.332 |
gross | -0.331 |
Token | iders |
Token ID | 4157 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
AST | +0.452 |
elaide | +0.426 |
outh | +0.424 |
igree | +0.423 |
ovember | +0.416 |
Neg logit contributions | |
wash | -0.657 |
↑ | -0.646 |
pak | -0.617 |
gross | -0.604 |
kat | -0.601 |
Token | ured |
Token ID | 1522 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
wash | +0.138 |
↑ | +0.137 |
pak | +0.127 |
kat | +0.123 |
gross | +0.122 |
Neg logit contributions | |
AST | -0.206 |
elaide | -0.198 |
outh | -0.197 |
igree | -0.196 |
ovember | -0.195 |
Token | loans |
Token ID | 10021 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
AST | +0.368 |
elaide | +0.351 |
igree | +0.348 |
outh | +0.348 |
ovember | +0.346 |
Neg logit contributions | |
wash | -0.325 |
↑ | -0.320 |
pak | -0.301 |
kat | -0.292 |
gross | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
wash | +0.927 |
↑ | +0.914 |
pak | +0.871 |
kat | +0.848 |
gross | +0.846 |
Neg logit contributions | |
AST | -0.812 |
elaide | -0.782 |
igree | -0.771 |
outh | -0.768 |
ovember | -0.764 |
Token | The |
Token ID | 383 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
wash | +0.135 |
↑ | +0.133 |
pak | +0.126 |
kat | +0.123 |
gross | +0.123 |
Neg logit contributions | |
AST | -0.118 |
elaide | -0.113 |
igree | -0.111 |
outh | -0.111 |
ovember | -0.110 |
Token | three |
Token ID | 1115 |
Feature activation | -7.25e-04 |
Pos logit contributions | |
AST | +0.073 |
elaide | +0.070 |
igree | +0.069 |
outh | +0.069 |
ovember | +0.069 |
Neg logit contributions | |
wash | -0.079 |
↑ | -0.078 |
pak | -0.074 |
kat | -0.072 |
gross | -0.072 |
Token | men |
Token ID | 1450 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
AST | +0.001 |
elaide | +0.001 |
igree | +0.001 |
outh | +0.001 |
ovember | +0.001 |
Neg logit contributions | |
wash | -0.001 |
↑ | -0.001 |
pak | -0.001 |
kat | -0.001 |
gross | -0.001 |
Token | own |
Token ID | 898 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
AST | +0.088 |
elaide | +0.083 |
igree | +0.083 |
outh | +0.083 |
ovember | +0.083 |
Neg logit contributions | |
wash | -0.088 |
↑ | -0.087 |
pak | -0.083 |
kat | -0.080 |
gross | -0.080 |
Token | five |
Token ID | 1936 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
wash | +0.371 |
↑ | +0.366 |
pak | +0.350 |
kat | +0.341 |
gross | +0.340 |
Neg logit contributions | |
AST | -0.296 |
elaide | -0.283 |
igree | -0.279 |
outh | -0.278 |
ovember | -0.277 |
Token | additional |
Token ID | 3224 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
AST | +0.085 |
elaide | +0.081 |
igree | +0.080 |
outh | +0.080 |
ovember | +0.079 |
Neg logit contributions | |
wash | -0.090 |
↑ | -0.089 |
pak | -0.084 |
kat | -0.082 |
gross | -0.082 |
Token | Kh |
Token ID | 5311 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
AST | +0.613 |
elaide | +0.584 |
igree | +0.579 |
outh | +0.578 |
Monarch | +0.576 |
Neg logit contributions | |
wash | -0.567 |
↑ | -0.559 |
pak | -0.525 |
kat | -0.513 |
gross | -0.510 |
Token | ark |
Token ID | 668 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
AST | +0.012 |
elaide | +0.011 |
outh | +0.011 |
igree | +0.011 |
ovember | +0.011 |
Neg logit contributions | |
wash | -0.012 |
↑ | -0.011 |
pak | -0.011 |
gross | -0.010 |
kat | -0.010 |
Token | who |
Token ID | 508 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
AST | +0.188 |
elaide | +0.180 |
igree | +0.178 |
outh | +0.177 |
ovember | +0.176 |
Neg logit contributions | |
wash | -0.205 |
↑ | -0.203 |
pak | -0.192 |
kat | -0.187 |
gross | -0.187 |
Token | was |
Token ID | 373 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
AST | +0.037 |
elaide | +0.036 |
igree | +0.035 |
outh | +0.035 |
ovember | +0.035 |
Neg logit contributions | |
wash | -0.039 |
↑ | -0.039 |
pak | -0.037 |
kat | -0.036 |
gross | -0.036 |
Token | following |
Token ID | 1708 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
AST | +0.019 |
elaide | +0.018 |
igree | +0.018 |
outh | +0.018 |
ovember | +0.018 |
Neg logit contributions | |
wash | -0.020 |
↑ | -0.019 |
pak | -0.018 |
kat | -0.018 |
gross | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
AST | +0.717 |
elaide | +0.677 |
igree | +0.675 |
outh | +0.670 |
Monarch | +0.666 |
Neg logit contributions | |
wash | -0.806 |
↑ | -0.796 |
pak | -0.757 |
gross | -0.737 |
kat | -0.736 |
Token | upstairs |
Token ID | 26148 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
wash | +0.030 |
↑ | +0.030 |
pak | +0.028 |
kat | +0.027 |
gross | +0.027 |
Neg logit contributions | |
AST | -0.024 |
elaide | -0.023 |
igree | -0.023 |
outh | -0.023 |
ovember | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
AST | +0.149 |
elaide | +0.142 |
outh | +0.140 |
igree | +0.140 |
ovember | +0.139 |
Neg logit contributions | |
wash | -0.190 |
↑ | -0.189 |
pak | -0.180 |
kat | -0.175 |
gross | -0.174 |
Token | got |
Token ID | 1392 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
AST | +0.032 |
elaide | +0.031 |
igree | +0.030 |
outh | +0.030 |
ovember | +0.030 |
Neg logit contributions | |
wash | -0.033 |
↑ | -0.033 |
pak | -0.031 |
kat | -0.030 |
gross | -0.030 |
Token | crushed |
Token ID | 18577 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
wash | +0.311 |
↑ | +0.307 |
pak | +0.293 |
kat | +0.285 |
gross | +0.285 |
Neg logit contributions | |
AST | -0.241 |
elaide | -0.230 |
igree | -0.226 |
outh | -0.226 |
ovember | -0.225 |
Token | under |
Token ID | 739 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
wash | +0.459 |
↑ | +0.453 |
pak | +0.429 |
kat | +0.417 |
gross | +0.416 |
Neg logit contributions | |
AST | -0.445 |
elaide | -0.426 |
igree | -0.421 |
outh | -0.420 |
ovember | -0.419 |
Token | her |
Token ID | 607 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
wash | +0.153 |
↑ | +0.151 |
pak | +0.144 |
kat | +0.141 |
gross | +0.141 |
Neg logit contributions | |
AST | -0.102 |
elaide | -0.096 |
igree | -0.095 |
outh | -0.095 |
ovember | -0.094 |
Token | weight |
Token ID | 3463 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
wash | +0.093 |
↑ | +0.092 |
pak | +0.087 |
kat | +0.085 |
gross | +0.085 |
Neg logit contributions | |
AST | -0.068 |
elaide | -0.065 |
igree | -0.064 |
outh | -0.064 |
ovember | -0.064 |
Token | — |
Token ID | 960 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
AST | +0.022 |
elaide | +0.021 |
outh | +0.021 |
igree | +0.021 |
ovember | +0.021 |
Neg logit contributions | |
wash | -0.028 |
↑ | -0.028 |
pak | -0.026 |
kat | -0.026 |
gross | -0.026 |
Token | sp |
Token ID | 2777 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
AST | +0.520 |
elaide | +0.501 |
outh | +0.498 |
igree | +0.497 |
ovember | +0.492 |
Neg logit contributions | |
wash | -0.348 |
↑ | -0.345 |
pak | -0.319 |
kat | -0.308 |
gross | -0.304 |
Token | ark |
Token ID | 668 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
wash | +0.247 |
↑ | +0.244 |
pak | +0.230 |
kat | +0.224 |
gross | +0.223 |
Neg logit contributions | |
AST | -0.248 |
elaide | -0.238 |
igree | -0.235 |
outh | -0.235 |
ovember | -0.234 |
Token | ed |
Token ID | 276 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
AST | +0.612 |
elaide | +0.587 |
outh | +0.581 |
igree | +0.578 |
ovember | +0.575 |
Neg logit contributions | |
wash | -0.541 |
↑ | -0.535 |
pak | -0.505 |
kat | -0.489 |
gross | -0.487 |
Token | even |
Token ID | 772 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
AST | +0.281 |
elaide | +0.268 |
igree | +0.264 |
outh | +0.263 |
ovember | +0.262 |
Neg logit contributions | |
wash | -0.380 |
↑ | -0.375 |
pak | -0.358 |
kat | -0.349 |
gross | -0.348 |
Token | more |
Token ID | 517 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
wash | +0.236 |
↑ | +0.232 |
pak | +0.219 |
kat | +0.213 |
gross | +0.212 |
Neg logit contributions | |
AST | -0.257 |
elaide | -0.249 |
igree | -0.246 |
outh | -0.244 |
ovember | -0.244 |
Token | anger |
Token ID | 8993 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
AST | +0.247 |
elaide | +0.236 |
igree | +0.233 |
outh | +0.231 |
ovember | +0.230 |
Neg logit contributions | |
wash | -0.336 |
↑ | -0.331 |
pak | -0.316 |
kat | -0.308 |
gross | -0.308 |
Token | . |
Token ID | 13 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
wash | +0.549 |
↑ | +0.541 |
pak | +0.514 |
kat | +0.501 |
gross | +0.500 |
Neg logit contributions | |
AST | -0.464 |
elaide | -0.443 |
igree | -0.438 |
outh | -0.436 |
ovember | -0.435 |
Token |
|
Token ID | 198 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
AST | +0.167 |
elaide | +0.159 |
outh | +0.157 |
igree | +0.157 |
ovember | +0.156 |
Neg logit contributions | |
wash | -0.183 |
↑ | -0.180 |
pak | -0.171 |
gross | -0.166 |
kat | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
AST | +0.155 |
outh | +0.146 |
ADHD | +0.143 |
Monarch | +0.143 |
Lyme | +0.142 |
Neg logit contributions | |
wash | -0.191 |
↑ | -0.187 |
pak | -0.179 |
gross | -0.176 |
kat | -0.174 |
Token | Two |
Token ID | 7571 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
AST | +0.175 |
elaide | +0.167 |
outh | +0.166 |
igree | +0.165 |
ovember | +0.165 |
Neg logit contributions | |
wash | -0.151 |
↑ | -0.148 |
pak | -0.140 |
gross | -0.136 |
kat | -0.135 |
Token | knew |
Token ID | 2993 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
AST | +0.339 |
elaide | +0.324 |
igree | +0.320 |
outh | +0.320 |
ovember | +0.318 |
Neg logit contributions | |
wash | -0.361 |
↑ | -0.357 |
pak | -0.339 |
kat | -0.330 |
gross | -0.329 |
Token | from |
Token ID | 422 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
AST | +0.589 |
elaide | +0.558 |
igree | +0.552 |
outh | +0.551 |
ovember | +0.546 |
Neg logit contributions | |
wash | -0.767 |
↑ | -0.757 |
pak | -0.723 |
kat | -0.704 |
gross | -0.703 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
AST | +0.218 |
elaide | +0.207 |
outh | +0.204 |
igree | +0.204 |
ovember | +0.202 |
Neg logit contributions | |
wash | -0.311 |
↑ | -0.307 |
pak | -0.294 |
kat | -0.287 |
gross | -0.286 |
Token | start |
Token ID | 923 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
AST | +0.242 |
elaide | +0.231 |
outh | +0.230 |
igree | +0.229 |
Monarch | +0.227 |
Neg logit contributions | |
wash | -0.204 |
↑ | -0.200 |
pak | -0.190 |
kat | -0.184 |
gross | -0.184 |
Token | I |
Token ID | 314 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
AST | +0.130 |
elaide | +0.124 |
igree | +0.122 |
outh | +0.122 |
ovember | +0.121 |
Neg logit contributions | |
wash | -0.161 |
↑ | -0.159 |
pak | -0.151 |
kat | -0.148 |
gross | -0.147 |
Token | could |
Token ID | 714 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
AST | +0.158 |
elaide | +0.151 |
igree | +0.150 |
outh | +0.149 |
ovember | +0.149 |
Neg logit contributions | |
wash | -0.168 |
↑ | -0.166 |
pak | -0.157 |
kat | -0.153 |
gross | -0.153 |
Token | never |
Token ID | 1239 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
AST | +0.246 |
elaide | +0.234 |
igree | +0.232 |
outh | +0.231 |
ovember | +0.230 |
Neg logit contributions | |
wash | -0.259 |
↑ | -0.256 |
pak | -0.243 |
kat | -0.237 |
gross | -0.236 |
Token | become |
Token ID | 1716 |
Feature activation | -4.58e-03 |
Pos logit contributions | |
AST | +0.417 |
elaide | +0.394 |
outh | +0.390 |
igree | +0.390 |
ovember | +0.387 |
Neg logit contributions | |
wash | -0.479 |
↑ | -0.473 |
pak | -0.450 |
kat | -0.440 |
gross | -0.439 |
Token | Na |
Token ID | 11013 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
AST | +0.007 |
elaide | +0.007 |
igree | +0.007 |
outh | +0.007 |
ovember | +0.007 |
Neg logit contributions | |
wash | -0.009 |
↑ | -0.009 |
pak | -0.009 |
kat | -0.009 |
gross | -0.009 |
Token | of |
Token ID | 1659 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
AST | +0.243 |
elaide | +0.233 |
outh | +0.232 |
igree | +0.231 |
ovember | +0.230 |
Neg logit contributions | |
wash | -0.228 |
↑ | -0.226 |
pak | -0.213 |
kat | -0.207 |
gross | -0.207 |
Token | umi |
Token ID | 12994 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
AST | +0.318 |
outh | +0.308 |
igree | +0.306 |
elaide | +0.306 |
ovember | +0.303 |
Neg logit contributions | |
wash | -0.266 |
↑ | -0.262 |
pak | -0.247 |
gross | -0.240 |
kat | -0.237 |
Token | s |
Token ID | 82 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
wash | +0.295 |
↑ | +0.289 |
pak | +0.272 |
gross | +0.266 |
kat | +0.264 |
Neg logit contributions | |
AST | -0.329 |
elaide | -0.312 |
outh | -0.311 |
igree | -0.310 |
Monarch | -0.308 |
Token | � |
Token ID | 564 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
AST | +0.445 |
elaide | +0.418 |
outh | +0.416 |
igree | +0.415 |
Monarch | +0.415 |
Neg logit contributions | |
wash | -0.494 |
↑ | -0.483 |
pak | -0.462 |
gross | -0.452 |
kat | -0.448 |
Token | � |
Token ID | 250 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
AST | +0.053 |
elaide | +0.051 |
igree | +0.051 |
outh | +0.051 |
ovember | +0.051 |
Neg logit contributions | |
wash | -0.032 |
↑ | -0.032 |
pak | -0.029 |
kat | -0.028 |
gross | -0.028 |
Token | Event |
Token ID | 9237 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
AST | +0.213 |
elaide | +0.204 |
igree | +0.201 |
outh | +0.201 |
ovember | +0.201 |
Neg logit contributions | |
wash | -0.197 |
↑ | -0.194 |
pak | -0.183 |
gross | -0.178 |
kat | -0.178 |
Token | Qu |
Token ID | 2264 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
wash | +0.317 |
↑ | +0.314 |
pak | +0.297 |
kat | +0.288 |
gross | +0.287 |
Neg logit contributions | |
AST | -0.314 |
elaide | -0.301 |
igree | -0.297 |
outh | -0.297 |
ovember | -0.295 |
Token | ests |
Token ID | 3558 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
wash | +0.456 |
↑ | +0.451 |
pak | +0.432 |
kat | +0.422 |
gross | +0.422 |
Neg logit contributions | |
AST | -0.252 |
elaide | -0.236 |
igree | -0.234 |
outh | -0.233 |
ovember | -0.231 |
Token | � |
Token ID | 447 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
AST | +1.225 |
elaide | +1.151 |
outh | +1.147 |
igree | +1.141 |
Monarch | +1.138 |
Neg logit contributions | |
wash | -1.431 |
↑ | -1.399 |
pak | -1.343 |
gross | -1.314 |
kat | -1.308 |
Token | � |
Token ID | 251 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
wash | +0.062 |
↑ | +0.061 |
pak | +0.056 |
kat | +0.054 |
gross | +0.054 |
Neg logit contributions | |
AST | -0.101 |
elaide | -0.097 |
outh | -0.097 |
igree | -0.097 |
ovember | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
AST | +0.167 |
elaide | +0.160 |
outh | +0.158 |
igree | +0.158 |
ovember | +0.157 |
Neg logit contributions | |
wash | -0.165 |
↑ | -0.162 |
pak | -0.153 |
kat | -0.149 |
gross | -0.149 |
Token | � |
Token ID | 564 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
AST | +0.258 |
elaide | +0.246 |
igree | +0.243 |
outh | +0.242 |
ovember | +0.241 |
Neg logit contributions | |
wash | -0.306 |
↑ | -0.302 |
pak | -0.287 |
kat | -0.280 |
gross | -0.279 |
Token | � |
Token ID | 250 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
AST | +0.171 |
elaide | +0.165 |
igree | +0.164 |
outh | +0.164 |
ovember | +0.164 |
Neg logit contributions | |
wash | -0.095 |
↑ | -0.092 |
pak | -0.086 |
kat | -0.082 |
gross | -0.082 |
Token | � |
Token ID | 564 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
wash | +0.127 |
↑ | +0.125 |
pak | +0.118 |
kat | +0.115 |
gross | +0.115 |
Neg logit contributions | |
AST | -0.118 |
elaide | -0.113 |
igree | -0.111 |
outh | -0.111 |
ovember | -0.111 |
Token | � |
Token ID | 250 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
wash | +0.228 |
↑ | +0.223 |
pak | +0.209 |
kat | +0.200 |
gross | +0.199 |
Neg logit contributions | |
AST | -0.385 |
elaide | -0.373 |
igree | -0.371 |
outh | -0.371 |
ovember | -0.371 |
Token | C |
Token ID | 34 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
AST | +0.120 |
elaide | +0.115 |
outh | +0.114 |
igree | +0.114 |
ovember | +0.114 |
Neg logit contributions | |
wash | -0.098 |
↑ | -0.097 |
pak | -0.091 |
kat | -0.088 |
gross | -0.088 |
Token | ute |
Token ID | 1133 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
wash | +0.307 |
↑ | +0.304 |
pak | +0.287 |
kat | +0.279 |
gross | +0.279 |
Neg logit contributions | |
AST | -0.314 |
elaide | -0.301 |
outh | -0.300 |
igree | -0.297 |
ovember | -0.297 |
Token | video |
Token ID | 2008 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
AST | +0.606 |
outh | +0.573 |
elaide | +0.571 |
igree | +0.569 |
ovember | +0.568 |
Neg logit contributions | |
wash | -0.681 |
↑ | -0.669 |
pak | -0.640 |
gross | -0.624 |
kat | -0.620 |
Token | Aj |
Token ID | 22028 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
AST | +0.275 |
elaide | +0.261 |
igree | +0.258 |
outh | +0.258 |
ovember | +0.257 |
Neg logit contributions | |
wash | -0.329 |
↑ | -0.325 |
pak | -0.310 |
gross | -0.301 |
kat | -0.301 |
Token | it |
Token ID | 270 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
AST | +1.389 |
elaide | +1.335 |
igree | +1.332 |
outh | +1.329 |
ovember | +1.323 |
Neg logit contributions | |
wash | -1.128 |
↑ | -1.113 |
pak | -1.038 |
gross | -1.008 |
kat | -1.003 |
Token | � |
Token ID | 564 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
AST | +0.332 |
elaide | +0.318 |
outh | +0.316 |
ovember | +0.316 |
igree | +0.316 |
Neg logit contributions | |
wash | -0.268 |
↑ | -0.262 |
pak | -0.248 |
gross | -0.240 |
kat | -0.239 |
Token | � |
Token ID | 246 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
wash | +0.092 |
↑ | +0.089 |
pak | +0.084 |
kat | +0.081 |
gross | +0.080 |
Neg logit contributions | |
AST | -0.147 |
elaide | -0.142 |
igree | -0.141 |
ovember | -0.141 |
outh | -0.141 |
Token | Aren |
Token ID | 43199 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
wash | +0.019 |
↑ | +0.019 |
pak | +0.018 |
kat | +0.017 |
gross | +0.017 |
Neg logit contributions | |
AST | -0.020 |
elaide | -0.020 |
outh | -0.019 |
igree | -0.019 |
ovember | -0.019 |
Token | � |
Token ID | 447 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
wash | +0.652 |
↑ | +0.642 |
pak | +0.604 |
kat | +0.585 |
gross | +0.583 |
Neg logit contributions | |
AST | -0.791 |
elaide | -0.761 |
igree | -0.752 |
outh | -0.752 |
ovember | -0.748 |
Token | for |
Token ID | 329 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
AST | +0.268 |
elaide | +0.254 |
outh | +0.253 |
igree | +0.251 |
Monarch | +0.249 |
Neg logit contributions | |
wash | -0.335 |
↑ | -0.330 |
pak | -0.316 |
kat | -0.307 |
gross | -0.304 |
Token | tuition |
Token ID | 18385 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
wash | +0.101 |
↑ | +0.099 |
pak | +0.095 |
kat | +0.093 |
gross | +0.092 |
Neg logit contributions | |
AST | -0.073 |
elaide | -0.069 |
igree | -0.068 |
outh | -0.068 |
ovember | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
wash | +0.698 |
↑ | +0.689 |
pak | +0.655 |
kat | +0.640 |
gross | +0.639 |
Neg logit contributions | |
AST | -0.554 |
elaide | -0.529 |
igree | -0.522 |
outh | -0.520 |
ovember | -0.518 |
Token | boasts |
Token ID | 22103 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
wash | +0.146 |
↑ | +0.144 |
pak | +0.137 |
kat | +0.134 |
gross | +0.133 |
Neg logit contributions | |
AST | -0.121 |
elaide | -0.115 |
igree | -0.114 |
outh | -0.114 |
ovember | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
wash | +0.558 |
↑ | +0.551 |
pak | +0.526 |
kat | +0.513 |
gross | +0.512 |
Neg logit contributions | |
AST | -0.415 |
elaide | -0.393 |
igree | -0.388 |
outh | -0.388 |
ovember | -0.385 |
Token | high |
Token ID | 1029 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
wash | +0.142 |
↑ | +0.140 |
pak | +0.133 |
kat | +0.130 |
gross | +0.130 |
Neg logit contributions | |
AST | -0.116 |
elaide | -0.111 |
igree | -0.109 |
outh | -0.109 |
ovember | -0.108 |
Token | success |
Token ID | 1943 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
AST | +1.086 |
elaide | +1.035 |
igree | +1.018 |
outh | +1.015 |
ovember | +1.012 |
Neg logit contributions | |
wash | -1.536 |
↑ | -1.517 |
pak | -1.448 |
kat | -1.414 |
gross | -1.411 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
AST | +0.414 |
elaide | +0.398 |
igree | +0.390 |
ovember | +0.389 |
outh | +0.389 |
Neg logit contributions | |
wash | -0.517 |
↑ | -0.511 |
pak | -0.485 |
kat | -0.474 |
gross | -0.474 |
Token | in |
Token ID | 287 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
AST | +0.027 |
elaide | +0.025 |
igree | +0.025 |
outh | +0.025 |
ovember | +0.025 |
Neg logit contributions | |
wash | -0.032 |
↑ | -0.032 |
pak | -0.030 |
gross | -0.029 |
kat | -0.029 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
wash | +0.138 |
↑ | +0.137 |
pak | +0.130 |
gross | +0.127 |
kat | +0.127 |
Neg logit contributions | |
AST | -0.108 |
elaide | -0.105 |
igree | -0.103 |
ovember | -0.102 |
outh | -0.102 |
Token | its |
Token ID | 663 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
AST | +0.035 |
elaide | +0.034 |
igree | +0.033 |
outh | +0.033 |
ovember | +0.033 |
Neg logit contributions | |
wash | -0.041 |
↑ | -0.040 |
pak | -0.038 |
kat | -0.037 |
gross | -0.037 |
Token | has |
Token ID | 468 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
AST | +0.153 |
elaide | +0.143 |
outh | +0.141 |
igree | +0.140 |
ovember | +0.139 |
Neg logit contributions | |
wash | -0.313 |
↑ | -0.311 |
pak | -0.298 |
kat | -0.292 |
gross | -0.292 |
Token | a |
Token ID | 257 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
wash | +0.003 |
↑ | +0.003 |
pak | +0.003 |
kat | +0.003 |
gross | +0.003 |
Neg logit contributions | |
AST | -0.002 |
elaide | -0.002 |
outh | -0.002 |
igree | -0.002 |
ovember | -0.002 |
Token | fo |
Token ID | 11511 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
AST | +0.013 |
elaide | +0.012 |
igree | +0.012 |
outh | +0.012 |
ovember | +0.012 |
Neg logit contributions | |
wash | -0.016 |
↑ | -0.016 |
pak | -0.015 |
kat | -0.015 |
gross | -0.015 |
Token | os |
Token ID | 418 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
AST | +0.685 |
elaide | +0.653 |
outh | +0.649 |
igree | +0.649 |
ovember | +0.642 |
Neg logit contributions | |
wash | -0.661 |
↑ | -0.652 |
pak | -0.619 |
kat | -0.600 |
gross | -0.599 |
Token | ball |
Token ID | 1894 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
AST | +0.141 |
elaide | +0.133 |
outh | +0.131 |
igree | +0.129 |
Monarch | +0.126 |
Neg logit contributions | |
wash | -0.360 |
↑ | -0.359 |
pak | -0.345 |
kat | -0.337 |
gross | -0.337 |
Token | table |
Token ID | 3084 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
AST | +0.173 |
elaide | +0.163 |
igree | +0.162 |
outh | +0.161 |
ovember | +0.160 |
Neg logit contributions | |
wash | -0.263 |
↑ | -0.260 |
pak | -0.249 |
kat | -0.243 |
gross | -0.243 |
Token | , |
Token ID | 11 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
AST | +1.509 |
elaide | +1.442 |
outh | +1.428 |
igree | +1.420 |
ovember | +1.409 |
Neg logit contributions | |
wash | -1.844 |
↑ | -1.834 |
pak | -1.747 |
kat | -1.696 |
gross | -1.691 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
wash | +0.076 |
↑ | +0.075 |
pak | +0.072 |
kat | +0.070 |
gross | +0.070 |
Neg logit contributions | |
AST | -0.060 |
elaide | -0.057 |
igree | -0.056 |
outh | -0.056 |
ovember | -0.056 |
Token | it |
Token ID | 340 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
wash | +0.093 |
↑ | +0.092 |
pak | +0.088 |
kat | +0.086 |
gross | +0.086 |
Neg logit contributions | |
AST | -0.072 |
elaide | -0.068 |
outh | -0.067 |
igree | -0.067 |
ovember | -0.067 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
wash | +0.105 |
↑ | +0.104 |
pak | +0.098 |
kat | +0.095 |
gross | +0.095 |
Neg logit contributions | |
AST | -0.109 |
elaide | -0.104 |
igree | -0.103 |
outh | -0.103 |
ovember | -0.102 |
Token | action |
Token ID | 2223 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
AST | +0.507 |
elaide | +0.484 |
outh | +0.480 |
igree | +0.476 |
ovember | +0.472 |
Neg logit contributions | |
wash | -0.637 |
↑ | -0.629 |
pak | -0.601 |
kat | -0.585 |
gross | -0.582 |
Token | tools |
Token ID | 4899 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
AST | +0.534 |
elaide | +0.511 |
igree | +0.503 |
outh | +0.503 |
ovember | +0.501 |
Neg logit contributions | |
wash | -0.616 |
↑ | -0.608 |
pak | -0.578 |
kat | -0.560 |
gross | -0.560 |
Token | provided |
Token ID | 2810 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
wash | +0.578 |
↑ | +0.569 |
pak | +0.541 |
kat | +0.526 |
gross | +0.524 |
Neg logit contributions | |
AST | -0.551 |
elaide | -0.529 |
igree | -0.522 |
outh | -0.520 |
ovember | -0.520 |
Token | to |
Token ID | 284 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
AST | +0.608 |
elaide | +0.581 |
igree | +0.575 |
outh | +0.574 |
ovember | +0.569 |
Neg logit contributions | |
wash | -0.578 |
↑ | -0.568 |
pak | -0.539 |
kat | -0.524 |
gross | -0.522 |
Token | gather |
Token ID | 6431 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
AST | +0.070 |
elaide | +0.067 |
igree | +0.066 |
outh | +0.066 |
ovember | +0.066 |
Neg logit contributions | |
wash | -0.080 |
↑ | -0.079 |
pak | -0.075 |
kat | -0.073 |
gross | -0.073 |
Token | inf |
Token ID | 1167 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
AST | +1.030 |
elaide | +0.982 |
igree | +0.969 |
outh | +0.967 |
ovember | +0.962 |
Neg logit contributions | |
wash | -1.263 |
↑ | -1.246 |
pak | -1.187 |
kat | -1.157 |
gross | -1.154 |
Token | erences |
Token ID | 4972 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
AST | +0.842 |
elaide | +0.805 |
igree | +0.797 |
outh | +0.795 |
ovember | +0.790 |
Neg logit contributions | |
wash | -0.901 |
↑ | -0.889 |
pak | -0.844 |
kat | -0.821 |
gross | -0.818 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
AST | +1.135 |
elaide | +1.073 |
outh | +1.066 |
igree | +1.064 |
ovember | +1.053 |
Neg logit contributions | |
wash | -1.414 |
↑ | -1.393 |
pak | -1.330 |
kat | -1.297 |
gross | -1.291 |
Token | observations |
Token ID | 13050 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
AST | +0.229 |
elaide | +0.218 |
igree | +0.215 |
outh | +0.215 |
ovember | +0.214 |
Neg logit contributions | |
wash | -0.275 |
↑ | -0.271 |
pak | -0.258 |
kat | -0.251 |
gross | -0.251 |
Token | on |
Token ID | 319 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
wash | +0.089 |
↑ | +0.088 |
pak | +0.084 |
kat | +0.081 |
gross | +0.081 |
Neg logit contributions | |
AST | -0.077 |
elaide | -0.073 |
igree | -0.072 |
outh | -0.072 |
ovember | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
AST | +0.307 |
elaide | +0.294 |
igree | +0.289 |
outh | +0.287 |
ovember | +0.286 |
Neg logit contributions | |
wash | -0.432 |
↑ | -0.427 |
pak | -0.407 |
kat | -0.397 |
gross | -0.396 |
Token | team |
Token ID | 1074 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
AST | +0.100 |
elaide | +0.095 |
igree | +0.093 |
outh | +0.093 |
ovember | +0.092 |
Neg logit contributions | |
wash | -0.155 |
↑ | -0.153 |
pak | -0.147 |
kat | -0.143 |
gross | -0.143 |