Token | mar |
Token ID | 3876 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
afort | +3.229 |
nels | +2.584 |
arently | +2.503 |
mt | +2.460 |
insula | +2.435 |
Neg logit contributions | |
ees | -3.053 |
REE | -2.684 |
sum | -2.581 |
yip | -2.573 |
hovah | -2.572 |
Token | ia |
Token ID | 544 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ees | +0.274 |
REE | +0.231 |
lust | +0.226 |
sum | +0.225 |
yip | +0.224 |
Neg logit contributions | |
afort | -0.334 |
nels | -0.271 |
arently | -0.265 |
insula | -0.260 |
mt | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
afort | +0.138 |
nels | +0.112 |
arently | +0.109 |
insula | +0.107 |
mt | +0.106 |
Neg logit contributions | |
ees | -0.112 |
REE | -0.095 |
lust | -0.092 |
sum | -0.092 |
yip | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
afort | +0.759 |
nels | +0.626 |
arently | +0.611 |
insula | +0.600 |
mt | +0.598 |
Neg logit contributions | |
ees | -0.533 |
REE | -0.444 |
yip | -0.429 |
lust | -0.429 |
ealous | -0.427 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
afort | +0.747 |
nels | +0.618 |
arently | +0.609 |
insula | +0.600 |
mt | +0.588 |
Neg logit contributions | |
ees | -0.465 |
REE | -0.380 |
lust | -0.370 |
sum | -0.365 |
ealous | -0.364 |
Token | Tai |
Token ID | 47976 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
afort | +0.743 |
nels | +0.594 |
arently | +0.578 |
insula | +0.564 |
mt | +0.559 |
Neg logit contributions | |
ees | -0.700 |
REE | -0.602 |
lust | -0.586 |
yip | -0.581 |
ealous | -0.581 |
Token | Lung |
Token ID | 39337 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
ees | +6.234 |
REE | +4.991 |
sum | +4.922 |
Kai | +4.892 |
yip | +4.879 |
Neg logit contributions | |
afort | -10.720 |
nels | -9.014 |
arently | -8.861 |
insula | -8.635 |
mt | -8.505 |
Token | , |
Token ID | 11 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
ees | +1.645 |
REE | +1.371 |
sum | +1.341 |
yip | +1.340 |
lust | +1.335 |
Neg logit contributions | |
afort | -2.207 |
nels | -1.794 |
arently | -1.765 |
insula | -1.736 |
mt | -1.711 |
Token | the |
Token ID | 262 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ees | +0.036 |
REE | +0.031 |
sum | +0.030 |
lust | +0.030 |
yip | +0.030 |
Neg logit contributions | |
afort | -0.048 |
nels | -0.039 |
arently | -0.038 |
insula | -0.038 |
mt | -0.037 |
Token | main |
Token ID | 1388 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
afort | +0.235 |
nels | +0.193 |
arently | +0.188 |
insula | +0.185 |
mt | +0.184 |
Neg logit contributions | |
ees | -0.171 |
REE | -0.143 |
lust | -0.139 |
yip | -0.138 |
sum | -0.138 |
Token | antagonist |
Token ID | 34667 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
afort | +2.364 |
nels | +1.919 |
arently | +1.872 |
mt | +1.836 |
insula | +1.834 |
Neg logit contributions | |
ees | -1.911 |
REE | -1.630 |
yip | -1.582 |
ealous | -1.572 |
lust | -1.570 |
Token | how |
Token ID | 703 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ees | +1.787 |
REE | +1.487 |
sum | +1.472 |
lust | +1.455 |
diagnosis | +1.445 |
Neg logit contributions | |
afort | -2.397 |
nels | -1.969 |
arently | -1.922 |
insula | -1.890 |
mt | -1.871 |
Token | he |
Token ID | 339 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
afort | +1.146 |
nels | +0.937 |
arently | +0.913 |
insula | +0.896 |
mt | +0.892 |
Neg logit contributions | |
ees | -0.894 |
REE | -0.753 |
lust | -0.730 |
yip | -0.728 |
sum | -0.727 |
Token | handled |
Token ID | 12118 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
afort | +0.177 |
nels | +0.145 |
arently | +0.141 |
insula | +0.138 |
mt | +0.138 |
Neg logit contributions | |
ees | -0.136 |
REE | -0.115 |
yip | -0.111 |
lust | -0.111 |
ealous | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
afort | +4.766 |
nels | +3.855 |
arently | +3.728 |
mt | +3.639 |
insula | +3.622 |
Neg logit contributions | |
ees | -3.914 |
REE | -3.355 |
yip | -3.268 |
hovah | -3.253 |
ealous | -3.230 |
Token | budget |
Token ID | 4466 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ees | +0.585 |
REE | +0.491 |
sum | +0.484 |
lust | +0.480 |
diagnosis | +0.477 |
Neg logit contributions | |
afort | -0.753 |
nels | -0.616 |
arently | -0.603 |
insula | -0.592 |
mt | -0.587 |
Token | sequ |
Token ID | 4726 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
ees | +0.536 |
REE | +0.444 |
lust | +0.429 |
yip | +0.428 |
sum | +0.427 |
Neg logit contributions | |
afort | -0.790 |
nels | -0.653 |
arently | -0.638 |
insula | -0.626 |
mt | -0.624 |
Token | ester |
Token ID | 7834 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ees | +4.322 |
sum | +2.807 |
ealous | +2.798 |
REE | +2.620 |
lust | +2.566 |
Neg logit contributions | |
afort | -12.593 |
nels | -10.636 |
insula | -10.491 |
arently | -10.447 |
Cmd | -10.286 |
Token | that |
Token ID | 326 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ees | +2.317 |
REE | +1.911 |
sum | +1.874 |
lust | +1.860 |
diagnosis | +1.831 |
Neg logit contributions | |
afort | -3.365 |
nels | -2.762 |
arently | -2.692 |
insula | -2.661 |
mt | -2.631 |
Token | Obama |
Token ID | 2486 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
afort | +0.374 |
nels | +0.306 |
arently | +0.298 |
insula | +0.292 |
mt | +0.291 |
Neg logit contributions | |
ees | -0.296 |
REE | -0.250 |
yip | -0.242 |
lust | -0.242 |
ealous | -0.241 |
Token | liked |
Token ID | 8288 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ees | +0.249 |
REE | +0.208 |
sum | +0.202 |
lust | +0.202 |
ealous | +0.201 |
Neg logit contributions | |
afort | -0.334 |
nels | -0.273 |
arently | -0.267 |
insula | -0.262 |
mt | -0.260 |
Token | this |
Token ID | 428 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
afort | +0.562 |
nels | +0.455 |
arently | +0.441 |
insula | +0.431 |
mt | +0.431 |
Neg logit contributions | |
ees | -0.491 |
REE | -0.420 |
yip | -0.407 |
lust | -0.406 |
ealous | -0.405 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
afort | +1.163 |
nels | +0.950 |
arently | +0.927 |
insula | +0.911 |
mt | +0.905 |
Neg logit contributions | |
ees | -0.902 |
REE | -0.757 |
sum | -0.735 |
lust | -0.735 |
ealous | -0.733 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
afort | +0.264 |
nels | +0.217 |
arently | +0.212 |
insula | +0.208 |
mt | +0.207 |
Neg logit contributions | |
ees | -0.186 |
REE | -0.155 |
lust | -0.150 |
yip | -0.149 |
ealous | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
ees | +0.209 |
REE | +0.170 |
lust | +0.166 |
sum | +0.163 |
ealous | +0.162 |
Neg logit contributions | |
afort | -0.352 |
nels | -0.291 |
arently | -0.289 |
insula | -0.285 |
mt | -0.276 |
Token | I |
Token ID | 40 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ees | +0.036 |
REE | +0.031 |
lust | +0.030 |
ealous | +0.030 |
sum | +0.030 |
Neg logit contributions | |
afort | -0.040 |
nels | -0.032 |
arently | -0.032 |
insula | -0.031 |
mt | -0.030 |
Token | van |
Token ID | 10438 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
ees | +1.106 |
REE | +0.923 |
lust | +0.894 |
sum | +0.892 |
ealous | +0.887 |
Neg logit contributions | |
afort | -1.562 |
nels | -1.287 |
arently | -1.258 |
insula | -1.237 |
mt | -1.223 |
Token | Nep |
Token ID | 15310 |
Feature activation | +9.76e+00 |
Pos logit contributions | |
afort | +4.864 |
nels | +3.953 |
arently | +3.876 |
mt | +3.795 |
insula | +3.769 |
Neg logit contributions | |
ees | -3.652 |
REE | -3.176 |
ealous | -3.008 |
hovah | -2.992 |
lust | -2.991 |
Token | om |
Token ID | 296 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
ees | +8.145 |
lust | +6.780 |
ayan | +6.709 |
ealous | +6.636 |
yip | +6.593 |
Neg logit contributions | |
afort | -7.768 |
nels | -6.323 |
insula | -6.158 |
arently | -6.138 |
Cmd | -5.977 |
Token | ny |
Token ID | 3281 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ees | +0.367 |
REE | +0.316 |
lust | +0.306 |
yip | +0.306 |
ealous | +0.305 |
Neg logit contributions | |
afort | -0.405 |
nels | -0.325 |
arently | -0.316 |
mt | -0.308 |
insula | -0.308 |
Token | ash |
Token ID | 1077 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
afort | +2.402 |
nels | +1.948 |
arently | +1.892 |
mt | +1.852 |
insula | +1.835 |
Neg logit contributions | |
ees | -2.069 |
REE | -1.787 |
lust | -1.723 |
yip | -1.716 |
ealous | -1.712 |
Token | ch |
Token ID | 354 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ees | +0.222 |
REE | +0.188 |
lust | +0.182 |
yip | +0.182 |
ealous | +0.181 |
Neg logit contributions | |
afort | -0.275 |
nels | -0.224 |
arently | -0.218 |
insula | -0.214 |
mt | -0.213 |
Token | ikh |
Token ID | 13848 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
afort | +2.174 |
nels | +1.786 |
arently | +1.745 |
mt | +1.705 |
insula | +1.702 |
Neg logit contributions | |
ees | -1.556 |
REE | -1.306 |
yip | -1.262 |
lust | -1.251 |
ealous | -1.244 |
Token | she |
Token ID | 673 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
afort | +1.348 |
nels | +1.101 |
arently | +1.075 |
mt | +1.050 |
insula | +1.044 |
Neg logit contributions | |
ees | -1.070 |
REE | -0.904 |
yip | -0.895 |
lust | -0.879 |
ealous | -0.877 |
Token | reported |
Token ID | 2098 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
afort | +0.908 |
nels | +0.747 |
arently | +0.731 |
mt | +0.713 |
insula | +0.709 |
Neg logit contributions | |
ees | -0.665 |
REE | -0.561 |
yip | -0.548 |
lust | -0.543 |
ealous | -0.540 |
Token | that |
Token ID | 326 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
ees | +0.064 |
REE | +0.054 |
yip | +0.053 |
lust | +0.052 |
ealous | +0.052 |
Neg logit contributions | |
afort | -0.086 |
nels | -0.071 |
arently | -0.069 |
mt | -0.067 |
insula | -0.067 |
Token | she |
Token ID | 673 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
afort | +0.856 |
nels | +0.704 |
arently | +0.687 |
mt | +0.672 |
insula | +0.668 |
Neg logit contributions | |
ees | -0.646 |
REE | -0.543 |
yip | -0.531 |
ealous | -0.526 |
lust | -0.526 |
Token | had |
Token ID | 550 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
afort | +0.911 |
nels | +0.762 |
arently | +0.746 |
mt | +0.732 |
insula | +0.726 |
Neg logit contributions | |
ees | -0.557 |
REE | -0.461 |
yip | -0.446 |
lust | -0.443 |
ealous | -0.441 |
Token | sequ |
Token ID | 4726 |
Feature activation | +9.32e+00 |
Pos logit contributions | |
afort | +0.764 |
nels | +0.641 |
arently | +0.628 |
mt | +0.616 |
insula | +0.614 |
Neg logit contributions | |
ees | -0.441 |
REE | -0.359 |
yip | -0.349 |
ealous | -0.345 |
lust | -0.345 |
Token | enced |
Token ID | 5864 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
ees | +2.865 |
ealous | +1.504 |
REE | +1.443 |
sum | +1.440 |
lust | +1.367 |
Neg logit contributions | |
afort | -12.921 |
nels | -11.354 |
insula | -11.119 |
arently | -11.049 |
mt | -10.941 |
Token | proteins |
Token ID | 15568 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ees | +2.719 |
REE | +2.303 |
sum | +2.251 |
lust | +2.190 |
diagnosis | +2.189 |
Neg logit contributions | |
afort | -3.671 |
nels | -2.989 |
arently | -2.906 |
insula | -2.901 |
mt | -2.824 |
Token | in |
Token ID | 287 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
ees | +3.252 |
REE | +2.689 |
sum | +2.664 |
diagnosis | +2.573 |
lust | +2.560 |
Neg logit contributions | |
afort | -4.964 |
nels | -4.085 |
arently | -3.993 |
insula | -3.973 |
mt | -3.859 |
Token | the |
Token ID | 262 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
afort | +0.002 |
nels | +0.002 |
arently | +0.002 |
mt | +0.002 |
insula | +0.002 |
Neg logit contributions | |
ees | -0.002 |
REE | -0.002 |
yip | -0.001 |
lust | -0.001 |
ealous | -0.001 |
Token | dinosaur |
Token ID | 28257 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ees | +0.115 |
REE | +0.095 |
yip | +0.092 |
lust | +0.092 |
ealous | +0.092 |
Neg logit contributions | |
afort | -0.173 |
nels | -0.144 |
arently | -0.140 |
mt | -0.138 |
insula | -0.137 |
Token | like |
Token ID | 588 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ees | +0.384 |
REE | +0.325 |
lust | +0.316 |
yip | +0.315 |
sum | +0.314 |
Neg logit contributions | |
afort | -0.465 |
nels | -0.378 |
arently | -0.368 |
insula | -0.360 |
mt | -0.359 |
Token | .. |
Token ID | 492 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
ees | +1.415 |
REE | +1.180 |
sum | +1.154 |
lust | +1.141 |
yip | +1.135 |
Neg logit contributions | |
afort | -2.030 |
nels | -1.674 |
arently | -1.634 |
insula | -1.603 |
mt | -1.592 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ees | +0.464 |
REE | +0.386 |
lust | +0.374 |
yip | +0.373 |
sum | +0.372 |
Neg logit contributions | |
afort | -0.659 |
nels | -0.543 |
arently | -0.530 |
insula | -0.520 |
mt | -0.518 |
Token | The |
Token ID | 464 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ees | +1.622 |
REE | +1.408 |
lust | +1.362 |
ealous | +1.333 |
yip | +1.327 |
Neg logit contributions | |
afort | -1.764 |
nels | -1.403 |
arently | -1.378 |
insula | -1.347 |
mt | -1.305 |
Token | imminent |
Token ID | 21161 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ees | +0.984 |
REE | +0.827 |
lust | +0.800 |
sum | +0.798 |
yip | +0.798 |
Neg logit contributions | |
afort | -1.315 |
nels | -1.078 |
arently | -1.051 |
insula | -1.032 |
mt | -1.027 |
Token | merger |
Token ID | 24589 |
Feature activation | +9.15e+00 |
Pos logit contributions | |
ees | +1.985 |
REE | +1.661 |
sum | +1.625 |
lust | +1.615 |
yip | +1.604 |
Neg logit contributions | |
afort | -2.681 |
nels | -2.194 |
arently | -2.142 |
insula | -2.104 |
mt | -2.091 |
Token | between |
Token ID | 1022 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
ees | +6.322 |
sum | +5.085 |
REE | +5.050 |
lust | +4.987 |
diagnosis | +4.956 |
Neg logit contributions | |
afort | -9.127 |
nels | -7.513 |
arently | -7.315 |
insula | -7.234 |
mt | -7.127 |
Token | Time |
Token ID | 3862 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ees | +3.052 |
REE | +2.584 |
sum | +2.528 |
lust | +2.505 |
diagnosis | +2.464 |
Neg logit contributions | |
afort | -3.860 |
nels | -3.192 |
arently | -3.099 |
insula | -3.030 |
mt | -2.987 |
Token | Warner |
Token ID | 14469 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
afort | +0.299 |
nels | +0.235 |
arently | +0.229 |
insula | +0.224 |
mt | +0.221 |
Neg logit contributions | |
ees | -0.320 |
REE | -0.278 |
lust | -0.272 |
sum | -0.271 |
yip | -0.269 |
Token | Cable |
Token ID | 20249 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
afort | +0.410 |
nels | +0.331 |
arently | +0.322 |
insula | +0.314 |
mt | +0.313 |
Neg logit contributions | |
ees | -0.365 |
REE | -0.312 |
lust | -0.303 |
sum | -0.303 |
yip | -0.301 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ees | +0.801 |
REE | +0.663 |
lust | +0.637 |
sum | +0.636 |
yip | +0.633 |
Neg logit contributions | |
afort | -1.230 |
nels | -1.019 |
arently | -0.998 |
insula | -0.980 |
mt | -0.974 |
Token | escape |
Token ID | 6654 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
ees | +1.996 |
REE | +1.598 |
sum | +1.587 |
lust | +1.563 |
yip | +1.540 |
Neg logit contributions | |
afort | -3.336 |
nels | -2.775 |
arently | -2.729 |
insula | -2.707 |
mt | -2.656 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ees | +1.904 |
REE | +1.575 |
lust | +1.532 |
sum | +1.528 |
yip | +1.522 |
Neg logit contributions | |
afort | -2.733 |
nels | -2.246 |
arently | -2.200 |
insula | -2.160 |
mt | -2.145 |
Token | slowdown |
Token ID | 35621 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ees | +1.082 |
REE | +0.892 |
sum | +0.871 |
lust | +0.867 |
ealous | +0.858 |
Neg logit contributions | |
afort | -1.657 |
nels | -1.366 |
arently | -1.340 |
insula | -1.316 |
mt | -1.308 |
Token | in |
Token ID | 287 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ees | +2.892 |
sum | +2.391 |
lust | +2.381 |
REE | +2.359 |
diagnosis | +2.339 |
Neg logit contributions | |
afort | -3.892 |
nels | -3.153 |
arently | -3.112 |
insula | -3.043 |
mt | -3.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ees | +0.973 |
REE | +0.811 |
lust | +0.789 |
sum | +0.789 |
yip | +0.779 |
Neg logit contributions | |
afort | -1.372 |
nels | -1.129 |
arently | -1.105 |
insula | -1.085 |
mt | -1.075 |
Token | eurozone |
Token ID | 37465 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
ees | +0.735 |
REE | +0.613 |
sum | +0.601 |
lust | +0.593 |
diagnosis | +0.588 |
Neg logit contributions | |
afort | -1.080 |
nels | -0.891 |
arently | -0.870 |
insula | -0.856 |
mt | -0.845 |
Token | . |
Token ID | 13 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
ees | +5.998 |
sum | +5.163 |
lust | +4.886 |
diagnosis | +4.867 |
REE | +4.799 |
Neg logit contributions | |
afort | -9.469 |
nels | -7.777 |
arently | -7.689 |
insula | -7.537 |
mt | -7.359 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ees | +0.462 |
REE | +0.387 |
yip | +0.381 |
ealous | +0.373 |
hovah | +0.372 |
Neg logit contributions | |
afort | -0.642 |
nels | -0.529 |
arently | -0.515 |
mt | -0.507 |
insula | -0.506 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ees | +0.199 |
REE | +0.162 |
lust | +0.158 |
sum | +0.155 |
ealous | +0.154 |
Neg logit contributions | |
afort | -0.331 |
nels | -0.274 |
arently | -0.272 |
insula | -0.268 |
mt | -0.260 |
Token | However |
Token ID | 4864 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ees | +0.091 |
REE | +0.077 |
lust | +0.075 |
ealous | +0.074 |
sum | +0.074 |
Neg logit contributions | |
afort | -0.109 |
nels | -0.088 |
arently | -0.086 |
insula | -0.085 |
mt | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ees | +0.390 |
REE | +0.336 |
yip | +0.327 |
ealous | +0.326 |
lust | +0.325 |
Neg logit contributions | |
afort | -0.436 |
nels | -0.353 |
arently | -0.344 |
mt | -0.335 |
insula | -0.333 |
Token | had |
Token ID | 550 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
afort | +0.515 |
nels | +0.420 |
arently | +0.411 |
insula | +0.402 |
mt | +0.401 |
Neg logit contributions | |
ees | -0.395 |
REE | -0.333 |
yip | -0.322 |
lust | -0.321 |
ealous | -0.321 |
Token | been |
Token ID | 587 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
afort | +0.398 |
nels | +0.334 |
arently | +0.331 |
insula | +0.322 |
mt | +0.321 |
Neg logit contributions | |
ees | -0.219 |
REE | -0.178 |
yip | -0.171 |
ealous | -0.170 |
lust | -0.168 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ees | +1.172 |
REE | +0.983 |
sum | +0.965 |
lust | +0.955 |
diagnosis | +0.949 |
Neg logit contributions | |
afort | -1.518 |
nels | -1.238 |
arently | -1.206 |
insula | -1.188 |
mt | -1.177 |
Token | diagnosis |
Token ID | 13669 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
afort | +0.220 |
nels | +0.181 |
arently | +0.176 |
insula | +0.173 |
mt | +0.172 |
Neg logit contributions | |
ees | -0.162 |
REE | -0.136 |
lust | -0.131 |
yip | -0.131 |
sum | -0.131 |
Token | of |
Token ID | 286 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
ees | +4.253 |
diagnosis | +3.507 |
sum | +3.503 |
REE | +3.495 |
lust | +3.374 |
Neg logit contributions | |
afort | -5.916 |
nels | -4.838 |
arently | -4.706 |
insula | -4.674 |
mt | -4.540 |
Token | leukemia |
Token ID | 49030 |
Feature activation | +9.09e+00 |
Pos logit contributions | |
afort | +0.609 |
nels | +0.497 |
arently | +0.484 |
insula | +0.474 |
mt | +0.473 |
Neg logit contributions | |
ees | -0.486 |
REE | -0.411 |
yip | -0.398 |
lust | -0.398 |
ealous | -0.397 |
Token | . |
Token ID | 13 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
ees | +5.841 |
diagnosis | +4.964 |
sum | +4.827 |
REE | +4.824 |
lust | +4.631 |
Neg logit contributions | |
afort | -9.206 |
nels | -7.787 |
insula | -7.567 |
arently | -7.507 |
mt | -7.334 |
Token | Then |
Token ID | 3244 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
ees | +0.051 |
REE | +0.043 |
lust | +0.042 |
sum | +0.042 |
ealous | +0.042 |
Neg logit contributions | |
afort | -0.064 |
nels | -0.052 |
arently | -0.051 |
insula | -0.050 |
mt | -0.049 |
Token | he |
Token ID | 339 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
afort | +0.734 |
nels | +0.603 |
arently | +0.589 |
insula | +0.576 |
mt | +0.576 |
Neg logit contributions | |
ees | -0.547 |
REE | -0.459 |
yip | -0.446 |
ealous | -0.444 |
lust | -0.444 |
Token | � |
Token ID | 447 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
afort | +0.800 |
nels | +0.665 |
arently | +0.651 |
mt | +0.638 |
insula | +0.637 |
Neg logit contributions | |
ees | -0.510 |
REE | -0.422 |
yip | -0.410 |
lust | -0.406 |
ealous | -0.405 |
Token | � |
Token ID | 247 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ees | +0.543 |
REE | +0.447 |
lust | +0.431 |
sum | +0.431 |
ealous | +0.429 |
Neg logit contributions | |
afort | -0.827 |
nels | -0.688 |
arently | -0.668 |
insula | -0.657 |
mt | -0.651 |
Token | also |
Token ID | 635 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ees | +0.837 |
REE | +0.684 |
sum | +0.667 |
lust | +0.665 |
yip | +0.653 |
Neg logit contributions | |
afort | -1.345 |
nels | -1.113 |
arently | -1.091 |
insula | -1.075 |
mt | -1.067 |
Token | in |
Token ID | 287 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
afort | +0.389 |
nels | +0.321 |
arently | +0.314 |
insula | +0.308 |
mt | +0.307 |
Neg logit contributions | |
ees | -0.267 |
REE | -0.222 |
yip | -0.214 |
lust | -0.214 |
ealous | -0.213 |
Token | much |
Token ID | 881 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ees | +0.491 |
REE | +0.418 |
lust | +0.405 |
yip | +0.405 |
ealous | +0.404 |
Neg logit contributions | |
afort | -0.576 |
nels | -0.466 |
arently | -0.453 |
insula | -0.444 |
mt | -0.442 |
Token | of |
Token ID | 286 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
afort | +1.913 |
nels | +1.526 |
arently | +1.486 |
mt | +1.462 |
insula | +1.442 |
Neg logit contributions | |
ees | -1.916 |
REE | -1.661 |
yip | -1.634 |
ealous | -1.625 |
hovah | -1.615 |
Token | the |
Token ID | 262 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
afort | +0.852 |
nels | +0.673 |
arently | +0.652 |
insula | +0.636 |
mt | +0.635 |
Neg logit contributions | |
ees | -0.899 |
REE | -0.778 |
yip | -0.761 |
ealous | -0.759 |
lust | -0.756 |
Token | eurozone |
Token ID | 37465 |
Feature activation | +8.94e+00 |
Pos logit contributions | |
ees | +0.414 |
REE | +0.340 |
sum | +0.331 |
lust | +0.328 |
ealous | +0.324 |
Neg logit contributions | |
afort | -0.686 |
nels | -0.571 |
arently | -0.558 |
insula | -0.550 |
mt | -0.547 |
Token | is |
Token ID | 318 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ees | +5.901 |
sum | +5.087 |
REE | +4.922 |
lust | +4.918 |
diagnosis | +4.825 |
Neg logit contributions | |
afort | -8.932 |
nels | -7.312 |
mt | -7.117 |
arently | -7.075 |
insula | -7.070 |
Token | worse |
Token ID | 4785 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
afort | +1.163 |
nels | +0.947 |
arently | +0.922 |
insula | +0.902 |
mt | +0.901 |
Neg logit contributions | |
ees | -0.948 |
REE | -0.803 |
yip | -0.779 |
ealous | -0.777 |
lust | -0.776 |
Token | than |
Token ID | 621 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
afort | +1.239 |
nels | +1.009 |
arently | +0.983 |
mt | +0.962 |
insula | +0.955 |
Neg logit contributions | |
ees | -1.016 |
REE | -0.862 |
yip | -0.843 |
hovah | -0.832 |
ealous | -0.830 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ees | +1.349 |
REE | +1.121 |
sum | +1.107 |
lust | +1.097 |
yip | +1.083 |
Neg logit contributions | |
afort | -1.917 |
nels | -1.581 |
arently | -1.540 |
insula | -1.517 |
mt | -1.501 |
Token | crime |
Token ID | 4065 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
afort | +0.154 |
nels | +0.127 |
arently | +0.124 |
insula | +0.122 |
mt | +0.122 |
Neg logit contributions | |
ees | -0.110 |
REE | -0.091 |
yip | -0.088 |
ealous | -0.088 |
lust | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ees | +0.005 |
REE | +0.004 |
lust | +0.004 |
sum | +0.004 |
ealous | +0.004 |
Neg logit contributions | |
afort | -0.009 |
nels | -0.007 |
arently | -0.007 |
insula | -0.007 |
mt | -0.007 |
Token | Google |
Token ID | 11708 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
afort | +0.102 |
nels | +0.083 |
arently | +0.083 |
insula | +0.080 |
mt | +0.078 |
Neg logit contributions | |
ees | -0.074 |
REE | -0.064 |
lust | -0.061 |
ealous | -0.060 |
sum | -0.059 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
ees | +0.713 |
REE | +0.537 |
sum | +0.514 |
lust | +0.510 |
ealous | +0.507 |
Neg logit contributions | |
afort | -1.881 |
nels | -1.605 |
arently | -1.592 |
insula | -1.563 |
mt | -1.539 |
Token | S |
Token ID | 311 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ees | +2.782 |
REE | +2.271 |
sum | +2.210 |
lust | +2.172 |
ealous | +2.165 |
Neg logit contributions | |
afort | -4.858 |
nels | -4.038 |
arently | -3.963 |
mt | -3.886 |
insula | -3.883 |
Token | AGE |
Token ID | 11879 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ees | +1.983 |
REE | +1.746 |
sum | +1.692 |
lust | +1.688 |
ealous | +1.684 |
Neg logit contributions | |
afort | -1.603 |
nels | -1.239 |
arently | -1.198 |
insula | -1.168 |
mt | -1.155 |
Token | Journals |
Token ID | 48608 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
ees | +0.126 |
REE | +0.104 |
sum | +0.100 |
lust | +0.100 |
yip | +0.099 |
Neg logit contributions | |
afort | -0.198 |
nels | -0.165 |
arently | -0.162 |
insula | -0.158 |
mt | -0.158 |
Token | | |
Token ID | 930 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ees | +6.217 |
REE | +5.260 |
sum | +5.107 |
lust | +5.060 |
ealous | +5.008 |
Neg logit contributions | |
afort | -8.645 |
nels | -7.145 |
arently | -6.934 |
mt | -6.750 |
insula | -6.694 |
Token | ISI |
Token ID | 22048 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
afort | +0.343 |
nels | +0.285 |
insula | +0.274 |
mt | +0.274 |
arently | +0.271 |
Neg logit contributions | |
ees | -0.214 |
yip | -0.178 |
ealous | -0.171 |
REE | -0.170 |
hovah | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
ees | +0.717 |
REE | +0.597 |
yip | +0.579 |
lust | +0.577 |
ealous | +0.575 |
Neg logit contributions | |
afort | -1.024 |
nels | -0.846 |
arently | -0.826 |
insula | -0.811 |
mt | -0.808 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
afort | +0.423 |
nels | +0.350 |
arently | +0.345 |
insula | +0.339 |
mt | +0.333 |
Neg logit contributions | |
ees | -0.267 |
REE | -0.220 |
lust | -0.213 |
sum | -0.211 |
ealous | -0.210 |
Token | R |
Token ID | 49 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
afort | +0.295 |
nels | +0.232 |
arently | +0.225 |
insula | +0.220 |
mt | +0.218 |
Neg logit contributions | |
ees | -0.313 |
REE | -0.272 |
lust | -0.264 |
yip | -0.263 |
ealous | -0.263 |
Token | ), |
Token ID | 828 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
ees | +0.828 |
REE | +0.717 |
lust | +0.698 |
yip | +0.698 |
ealous | +0.696 |
Neg logit contributions | |
afort | -0.789 |
nels | -0.623 |
arently | -0.604 |
insula | -0.590 |
mt | -0.587 |
Token | which |
Token ID | 543 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
afort | +0.559 |
nels | +0.456 |
arently | +0.446 |
mt | +0.437 |
insula | +0.436 |
Neg logit contributions | |
ees | -0.423 |
REE | -0.357 |
lust | -0.346 |
yip | -0.346 |
ealous | -0.346 |
Token | was |
Token ID | 373 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
afort | +2.364 |
nels | +1.927 |
arently | +1.871 |
mt | +1.829 |
insula | +1.804 |
Neg logit contributions | |
ees | -1.939 |
REE | -1.663 |
ealous | -1.620 |
yip | -1.619 |
lust | -1.610 |
Token | dominated |
Token ID | 13354 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
afort | +2.599 |
nels | +2.137 |
arently | +2.088 |
mt | +2.051 |
insula | +2.035 |
Neg logit contributions | |
ees | -1.838 |
REE | -1.538 |
yip | -1.494 |
ealous | -1.491 |
lust | -1.485 |
Token | by |
Token ID | 416 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
afort | +1.830 |
nels | +1.484 |
arently | +1.447 |
insula | +1.414 |
mt | +1.412 |
Neg logit contributions | |
ees | -1.478 |
REE | -1.258 |
yip | -1.218 |
ealous | -1.216 |
lust | -1.213 |
Token | Kik |
Token ID | 40571 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
ees | +0.137 |
REE | +0.115 |
yip | +0.111 |
lust | +0.111 |
ealous | +0.111 |
Neg logit contributions | |
afort | -0.184 |
nels | -0.151 |
arently | -0.147 |
insula | -0.144 |
mt | -0.144 |
Token | uy |
Token ID | 4669 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ees | +4.608 |
REE | +3.427 |
lust | +3.338 |
sum | +3.319 |
ealous | +3.237 |
Neg logit contributions | |
afort | -10.574 |
nels | -9.081 |
arently | -8.684 |
insula | -8.626 |
mt | -8.464 |
Token | u |
Token ID | 84 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
ees | +1.662 |
REE | +1.418 |
lust | +1.381 |
sum | +1.377 |
yip | +1.374 |
Neg logit contributions | |
afort | -1.769 |
nels | -1.400 |
arently | -1.370 |
insula | -1.340 |
mt | -1.315 |
Token | and |
Token ID | 290 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
ees | +0.647 |
REE | +0.542 |
lust | +0.524 |
yip | +0.523 |
sum | +0.522 |
Neg logit contributions | |
afort | -0.879 |
nels | -0.721 |
arently | -0.703 |
insula | -0.690 |
mt | -0.687 |
Token | Luo |
Token ID | 25956 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
afort | +0.040 |
nels | +0.033 |
arently | +0.032 |
mt | +0.031 |
insula | +0.031 |
Neg logit contributions | |
ees | -0.029 |
REE | -0.025 |
yip | -0.024 |
lust | -0.024 |
ealous | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ees | +1.984 |
REE | +1.651 |
sum | +1.606 |
yip | +1.602 |
lust | +1.597 |
Neg logit contributions | |
afort | -2.684 |
nels | -2.202 |
arently | -2.146 |
insula | -2.119 |
mt | -2.087 |
Token | to |
Token ID | 284 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
afort | +1.693 |
nels | +1.367 |
arently | +1.330 |
mt | +1.294 |
insula | +1.291 |
Neg logit contributions | |
ees | -1.443 |
REE | -1.243 |
yip | -1.204 |
lust | -1.202 |
ealous | -1.196 |
Token | Gat |
Token ID | 29074 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
ees | +0.466 |
REE | +0.390 |
lust | +0.377 |
yip | +0.377 |
sum | +0.376 |
Neg logit contributions | |
afort | -0.639 |
nels | -0.525 |
arently | -0.512 |
insula | -0.503 |
mt | -0.501 |
Token | und |
Token ID | 917 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
afort | +4.967 |
nels | +4.146 |
mt | +4.048 |
arently | +4.008 |
insula | +3.924 |
Neg logit contributions | |
ees | -3.555 |
REE | -3.108 |
hovah | -2.968 |
ealous | -2.953 |
yip | -2.945 |
Token | u |
Token ID | 84 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ees | +0.036 |
REE | +0.031 |
lust | +0.030 |
yip | +0.030 |
ealous | +0.030 |
Neg logit contributions | |
afort | -0.038 |
nels | -0.031 |
arently | -0.030 |
insula | -0.029 |
mt | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ees | +1.184 |
REE | +0.985 |
sum | +0.963 |
lust | +0.958 |
yip | +0.956 |
Neg logit contributions | |
afort | -1.542 |
nels | -1.263 |
arently | -1.233 |
insula | -1.213 |
mt | -1.201 |
Token | Kik |
Token ID | 40571 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
afort | +0.304 |
nels | +0.252 |
arently | +0.246 |
mt | +0.242 |
insula | +0.241 |
Neg logit contributions | |
ees | -0.204 |
REE | -0.169 |
yip | -0.164 |
ealous | -0.163 |
lust | -0.163 |
Token | uy |
Token ID | 4669 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
ees | +4.306 |
lust | +3.025 |
sum | +2.993 |
yip | +2.984 |
ealous | +2.975 |
Neg logit contributions | |
afort | -10.711 |
nels | -9.161 |
arently | -8.936 |
insula | -8.888 |
Anth | -8.630 |
Token | ul |
Token ID | 377 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ees | +2.243 |
REE | +1.840 |
lust | +1.837 |
sum | +1.828 |
ealous | +1.823 |
Neg logit contributions | |
afort | -2.550 |
nels | -2.022 |
arently | -2.008 |
insula | -1.966 |
mt | -1.899 |
Token | and |
Token ID | 392 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
afort | +3.984 |
nels | +3.270 |
arently | +3.201 |
mt | +3.178 |
insula | +3.159 |
Neg logit contributions | |
ees | -2.811 |
REE | -2.387 |
yip | -2.329 |
hovah | -2.314 |
ealous | -2.306 |
Token | , |
Token ID | 11 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
afort | +1.273 |
nels | +1.036 |
arently | +1.011 |
insula | +0.991 |
mt | +0.990 |
Neg logit contributions | |
ees | -1.018 |
REE | -0.865 |
yip | -0.841 |
lust | -0.835 |
ealous | -0.834 |
Token | where |
Token ID | 810 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
afort | +0.492 |
nels | +0.408 |
arently | +0.399 |
insula | +0.391 |
mt | +0.390 |
Neg logit contributions | |
ees | -0.326 |
REE | -0.270 |
lust | -0.261 |
yip | -0.261 |
ealous | -0.260 |
Token | " |
Token ID | 1 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
afort | +0.201 |
nels | +0.161 |
arently | +0.158 |
insula | +0.154 |
mt | +0.151 |
Neg logit contributions | |
ees | -0.179 |
REE | -0.155 |
lust | -0.150 |
ealous | -0.148 |
sum | -0.147 |
Token | If |
Token ID | 1532 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
afort | +0.705 |
nels | +0.568 |
arently | +0.557 |
insula | +0.544 |
mt | +0.533 |
Neg logit contributions | |
ees | -0.608 |
REE | -0.522 |
lust | -0.508 |
ealous | -0.499 |
sum | -0.495 |
Token | you |
Token ID | 345 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ees | +0.801 |
REE | +0.665 |
sum | +0.649 |
lust | +0.648 |
yip | +0.639 |
Neg logit contributions | |
afort | -1.128 |
nels | -0.928 |
arently | -0.906 |
insula | -0.894 |
mt | -0.884 |
Token | look |
Token ID | 804 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
afort | +1.216 |
nels | +1.012 |
arently | +0.988 |
mt | +0.969 |
insula | +0.968 |
Neg logit contributions | |
ees | -0.774 |
REE | -0.639 |
yip | -0.618 |
lust | -0.613 |
ealous | -0.613 |
Token | at |
Token ID | 379 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
ees | +1.955 |
REE | +1.624 |
sum | +1.612 |
lust | +1.599 |
ealous | +1.566 |
Neg logit contributions | |
afort | -2.571 |
nels | -2.093 |
arently | -2.042 |
insula | -2.027 |
mt | -1.998 |
Token | Assy |
Token ID | 39881 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
ees | +2.282 |
REE | +1.901 |
sum | +1.893 |
lust | +1.846 |
diagnosis | +1.823 |
Neg logit contributions | |
afort | -3.111 |
nels | -2.544 |
arently | -2.504 |
insula | -2.469 |
mt | -2.408 |
Token | rian |
Token ID | 4484 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
ees | +3.864 |
REE | +2.880 |
sum | +2.656 |
lust | +2.513 |
abol | +2.503 |
Neg logit contributions | |
afort | -11.037 |
nels | -9.435 |
insula | -9.404 |
arently | -9.182 |
milo | -8.939 |
Token | culture |
Token ID | 3968 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ees | +3.175 |
REE | +2.732 |
sum | +2.726 |
lust | +2.668 |
diagnosis | +2.639 |
Neg logit contributions | |
afort | -3.143 |
nels | -2.480 |
arently | -2.419 |
insula | -2.391 |
mt | -2.300 |
Token | or |
Token ID | 393 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
afort | +1.445 |
nels | +1.182 |
arently | +1.152 |
insula | +1.130 |
mt | +1.126 |
Neg logit contributions | |
ees | -1.111 |
REE | -0.936 |
lust | -0.906 |
yip | -0.905 |
ealous | -0.903 |
Token | the |
Token ID | 262 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
afort | +0.272 |
nels | +0.224 |
arently | +0.218 |
insula | +0.214 |
mt | +0.213 |
Neg logit contributions | |
ees | -0.201 |
REE | -0.169 |
lust | -0.163 |
yip | -0.163 |
ealous | -0.163 |
Token | Egyptians |
Token ID | 32658 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ees | +0.576 |
REE | +0.481 |
sum | +0.468 |
lust | +0.464 |
ealous | +0.459 |
Neg logit contributions | |
afort | -0.823 |
nels | -0.681 |
arently | -0.663 |
insula | -0.652 |
mt | -0.646 |
Token | crisis |
Token ID | 4902 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ees | +0.929 |
REE | +0.763 |
sum | +0.738 |
lust | +0.737 |
yip | +0.734 |
Neg logit contributions | |
afort | -1.454 |
nels | -1.206 |
arently | -1.179 |
insula | -1.158 |
mt | -1.153 |
Token | — |
Token ID | 851 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ees | +1.214 |
REE | +1.006 |
sum | +0.999 |
lust | +0.995 |
ealous | +0.986 |
Neg logit contributions | |
afort | -1.610 |
nels | -1.314 |
arently | -1.280 |
insula | -1.254 |
mt | -1.250 |
Token | and |
Token ID | 290 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
afort | +1.440 |
nels | +1.180 |
arently | +1.151 |
insula | +1.128 |
mt | +1.126 |
Neg logit contributions | |
ees | -1.081 |
REE | -0.908 |
yip | -0.879 |
lust | -0.878 |
ealous | -0.876 |
Token | win |
Token ID | 1592 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ees | +0.342 |
REE | +0.287 |
lust | +0.279 |
sum | +0.279 |
yip | +0.278 |
Neg logit contributions | |
afort | -0.438 |
nels | -0.357 |
arently | -0.348 |
insula | -0.342 |
mt | -0.340 |
Token | a |
Token ID | 257 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ees | +0.161 |
REE | +0.137 |
yip | +0.134 |
lust | +0.133 |
ealous | +0.133 |
Neg logit contributions | |
afort | -0.195 |
nels | -0.158 |
arently | -0.154 |
insula | -0.151 |
mt | -0.151 |
Token | Nobel |
Token ID | 20715 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
afort | +0.601 |
nels | +0.490 |
arently | +0.477 |
mt | +0.467 |
insula | +0.466 |
Neg logit contributions | |
ees | -0.497 |
REE | -0.423 |
yip | -0.413 |
ealous | -0.408 |
lust | -0.408 |
Token | prize |
Token ID | 11596 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
ees | +5.442 |
sum | +4.423 |
diagnosis | +4.235 |
REE | +4.205 |
lust | +4.172 |
Neg logit contributions | |
afort | -9.553 |
nels | -8.078 |
arently | -7.703 |
insula | -7.664 |
mt | -7.543 |
Token | in |
Token ID | 287 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ees | +3.135 |
sum | +2.598 |
REE | +2.565 |
lust | +2.539 |
ealous | +2.509 |
Neg logit contributions | |
afort | -4.296 |
nels | -3.545 |
arently | -3.429 |
insula | -3.375 |
mt | -3.373 |
Token | the |
Token ID | 262 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ees | +0.221 |
REE | +0.185 |
sum | +0.180 |
lust | +0.179 |
ealous | +0.178 |
Neg logit contributions | |
afort | -0.299 |
nels | -0.245 |
arently | -0.239 |
insula | -0.235 |
mt | -0.233 |
Token | process |
Token ID | 1429 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ees | +0.303 |
REE | +0.252 |
sum | +0.245 |
lust | +0.244 |
ealous | +0.242 |
Neg logit contributions | |
afort | -0.433 |
nels | -0.356 |
arently | -0.346 |
insula | -0.342 |
mt | -0.338 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
afort | +2.067 |
nels | +1.667 |
arently | +1.620 |
insula | +1.586 |
mt | +1.581 |
Neg logit contributions | |
ees | -1.853 |
REE | -1.597 |
yip | -1.556 |
lust | -1.537 |
ealous | -1.535 |
Token | , |
Token ID | 11 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ees | +1.857 |
REE | +1.513 |
lust | +1.476 |
sum | +1.476 |
yip | +1.443 |
Neg logit contributions | |
afort | -3.006 |
nels | -2.489 |
arently | -2.439 |
insula | -2.394 |
mt | -2.386 |
Token | and |
Token ID | 290 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ees | +0.366 |
REE | +0.301 |
lust | +0.290 |
yip | +0.290 |
ealous | +0.289 |
Neg logit contributions | |
afort | -0.570 |
nels | -0.474 |
arently | -0.463 |
insula | -0.455 |
mt | -0.454 |
Token | troubles |
Token ID | 14979 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ees | +0.282 |
REE | +0.234 |
yip | +0.225 |
lust | +0.225 |
ealous | +0.225 |
Neg logit contributions | |
afort | -0.419 |
nels | -0.347 |
arently | -0.339 |
insula | -0.333 |
mt | -0.332 |
Token | in |
Token ID | 287 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
ees | +0.498 |
REE | +0.415 |
lust | +0.403 |
sum | +0.402 |
yip | +0.400 |
Neg logit contributions | |
afort | -0.697 |
nels | -0.573 |
arently | -0.560 |
insula | -0.549 |
mt | -0.547 |
Token | the |
Token ID | 262 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
ees | +0.313 |
REE | +0.262 |
yip | +0.254 |
lust | +0.254 |
ealous | +0.253 |
Neg logit contributions | |
afort | -0.428 |
nels | -0.351 |
arently | -0.343 |
insula | -0.336 |
mt | -0.335 |
Token | eurozone |
Token ID | 37465 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
ees | +0.453 |
REE | +0.380 |
sum | +0.369 |
lust | +0.367 |
ealous | +0.365 |
Neg logit contributions | |
afort | -0.632 |
nels | -0.520 |
arently | -0.506 |
insula | -0.499 |
mt | -0.493 |
Token | have |
Token ID | 423 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ees | +5.863 |
sum | +5.097 |
diagnosis | +4.845 |
lust | +4.836 |
REE | +4.805 |
Neg logit contributions | |
afort | -8.911 |
nels | -7.315 |
arently | -7.166 |
insula | -6.985 |
mt | -6.880 |
Token | prompted |
Token ID | 12053 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ees | +1.470 |
sum | +1.212 |
REE | +1.211 |
lust | +1.201 |
diagnosis | +1.171 |
Neg logit contributions | |
afort | -2.012 |
nels | -1.645 |
arently | -1.601 |
insula | -1.584 |
mt | -1.558 |
Token | some |
Token ID | 617 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
afort | +0.161 |
nels | +0.133 |
arently | +0.130 |
mt | +0.127 |
insula | +0.127 |
Neg logit contributions | |
ees | -0.117 |
REE | -0.098 |
yip | -0.095 |
ealous | -0.094 |
lust | -0.094 |
Token | Bank |
Token ID | 5018 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
afort | +2.385 |
nels | +1.998 |
arently | +1.952 |
mt | +1.922 |
insula | +1.911 |
Neg logit contributions | |
ees | -1.467 |
REE | -1.205 |
yip | -1.170 |
ealous | -1.155 |
hovah | -1.155 |
Token | officials |
Token ID | 2828 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
ees | +2.664 |
REE | +2.177 |
sum | +2.171 |
lust | +2.134 |
ealous | +2.126 |
Neg logit contributions | |
afort | -3.739 |
nels | -3.040 |
arently | -2.995 |
insula | -2.933 |
mt | -2.878 |
Token | National |
Token ID | 2351 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
ees | +2.401 |
REE | +2.008 |
sum | +1.985 |
lust | +1.954 |
yip | +1.929 |
Neg logit contributions | |
afort | -3.338 |
nels | -2.740 |
arently | -2.690 |
insula | -2.610 |
mt | -2.592 |
Token | Park |
Token ID | 3250 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
ees | +1.473 |
REE | +1.162 |
sum | +1.126 |
lust | +1.115 |
ealous | +1.099 |
Neg logit contributions | |
afort | -2.937 |
nels | -2.476 |
arently | -2.433 |
insula | -2.385 |
mt | -2.374 |
Token | under |
Token ID | 739 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
afort | +1.684 |
nels | +1.383 |
arently | +1.344 |
insula | +1.322 |
mt | +1.318 |
Neg logit contributions | |
ees | -1.262 |
REE | -1.061 |
yip | -1.029 |
ealous | -1.028 |
lust | -1.026 |
Token | frost |
Token ID | 21682 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
ees | +0.830 |
REE | +0.698 |
sum | +0.678 |
lust | +0.677 |
yip | +0.671 |
Neg logit contributions | |
afort | -1.090 |
nels | -0.894 |
arently | -0.870 |
insula | -0.858 |
mt | -0.850 |
Token | ed |
Token ID | 276 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
afort | +0.839 |
nels | +0.688 |
arently | +0.671 |
insula | +0.658 |
mt | +0.656 |
Neg logit contributions | |
ees | -0.627 |
REE | -0.527 |
lust | -0.509 |
yip | -0.509 |
ealous | -0.508 |
Token | sequ |
Token ID | 4726 |
Feature activation | +8.73e+00 |
Pos logit contributions | |
afort | +0.853 |
nels | +0.696 |
arently | +0.676 |
mt | +0.664 |
insula | +0.660 |
Neg logit contributions | |
ees | -0.683 |
REE | -0.578 |
yip | -0.567 |
ealous | -0.563 |
hovah | -0.561 |
Token | o |
Token ID | 78 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ees | +6.018 |
REE | +4.587 |
lust | +4.575 |
sum | +4.530 |
ealous | +4.454 |
Neg logit contributions | |
afort | -8.990 |
nels | -7.312 |
arently | -7.150 |
insula | -7.145 |
Cmd | -7.114 |
Token | ias |
Token ID | 4448 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
afort | +1.983 |
nels | +1.634 |
arently | +1.594 |
insula | +1.559 |
mt | +1.553 |
Neg logit contributions | |
ees | -1.435 |
REE | -1.208 |
yip | -1.176 |
lust | -1.170 |
ealous | -1.162 |
Token | and |
Token ID | 290 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ees | +0.188 |
REE | +0.157 |
lust | +0.152 |
sum | +0.152 |
yip | +0.151 |
Neg logit contributions | |
afort | -0.259 |
nels | -0.212 |
arently | -0.208 |
insula | -0.204 |
mt | -0.203 |
Token | frozen |
Token ID | 12912 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
afort | +0.402 |
nels | +0.329 |
arently | +0.320 |
insula | +0.314 |
mt | +0.313 |
Neg logit contributions | |
ees | -0.317 |
REE | -0.267 |
ealous | -0.259 |
yip | -0.259 |
lust | -0.259 |
Token | water |
Token ID | 1660 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
afort | +0.745 |
nels | +0.611 |
arently | +0.595 |
insula | +0.583 |
mt | +0.583 |
Neg logit contributions | |
ees | -0.560 |
REE | -0.469 |
yip | -0.456 |
ealous | -0.456 |
lust | -0.455 |
Token | federal |
Token ID | 2717 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ees | +0.522 |
REE | +0.432 |
lust | +0.418 |
sum | +0.417 |
ealous | +0.416 |
Neg logit contributions | |
afort | -0.782 |
nels | -0.647 |
arently | -0.632 |
insula | -0.621 |
mt | -0.618 |
Token | government |
Token ID | 1230 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ees | +0.867 |
REE | +0.698 |
sum | +0.673 |
ealous | +0.670 |
lust | +0.670 |
Neg logit contributions | |
afort | -1.524 |
nels | -1.274 |
arently | -1.248 |
insula | -1.226 |
mt | -1.219 |
Token | will |
Token ID | 481 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
afort | +1.090 |
nels | +0.889 |
arently | +0.866 |
insula | +0.847 |
mt | +0.846 |
Neg logit contributions | |
ees | -0.878 |
REE | -0.744 |
yip | -0.722 |
lust | -0.720 |
ealous | -0.719 |
Token | now |
Token ID | 783 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
afort | +0.945 |
nels | +0.775 |
arently | +0.756 |
insula | +0.739 |
mt | +0.739 |
Neg logit contributions | |
ees | -0.715 |
REE | -0.602 |
yip | -0.583 |
lust | -0.582 |
ealous | -0.581 |
Token | recognize |
Token ID | 7564 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
afort | +0.169 |
nels | +0.141 |
arently | +0.138 |
insula | +0.135 |
mt | +0.135 |
Neg logit contributions | |
ees | -0.108 |
REE | -0.089 |
lust | -0.086 |
yip | -0.086 |
ealous | -0.086 |
Token | marriages |
Token ID | 20102 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
ees | +3.339 |
REE | +2.697 |
sum | +2.661 |
lust | +2.616 |
diagnosis | +2.603 |
Neg logit contributions | |
afort | -5.232 |
nels | -4.312 |
arently | -4.203 |
insula | -4.196 |
mt | -4.103 |
Token | which |
Token ID | 543 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
ees | +5.594 |
sum | +4.454 |
REE | +4.389 |
diagnosis | +4.265 |
lust | +4.264 |
Neg logit contributions | |
afort | -9.281 |
nels | -7.718 |
insula | -7.506 |
arently | -7.487 |
mt | -7.247 |
Token | their |
Token ID | 511 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
afort | +0.862 |
nels | +0.701 |
arently | +0.686 |
mt | +0.673 |
insula | +0.665 |
Neg logit contributions | |
ees | -0.666 |
REE | -0.565 |
yip | -0.553 |
ealous | -0.550 |
lust | -0.547 |
Token | states |
Token ID | 2585 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ees | +0.951 |
REE | +0.771 |
lust | +0.745 |
sum | +0.742 |
ealous | +0.741 |
Neg logit contributions | |
afort | -1.616 |
nels | -1.350 |
arently | -1.320 |
insula | -1.299 |
mt | -1.292 |
Token | recognize |
Token ID | 7564 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
ees | +1.162 |
REE | +0.961 |
lust | +0.932 |
sum | +0.930 |
ealous | +0.923 |
Neg logit contributions | |
afort | -1.739 |
nels | -1.439 |
arently | -1.400 |
insula | -1.386 |
mt | -1.364 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ees | +3.237 |
REE | +2.641 |
sum | +2.605 |
lust | +2.575 |
ealous | +2.537 |
Neg logit contributions | |
afort | -4.482 |
nels | -3.657 |
arently | -3.597 |
insula | -3.561 |
mt | -3.480 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ees | +2.638 |
REE | +2.171 |
sum | +2.153 |
lust | +2.120 |
ealous | +2.114 |
Neg logit contributions | |
afort | -3.477 |
nels | -2.829 |
arently | -2.768 |
insula | -2.731 |
mt | -2.679 |
Token | O |
Token ID | 440 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ees | +0.128 |
REE | +0.107 |
lust | +0.103 |
ealous | +0.103 |
sum | +0.103 |
Neg logit contributions | |
afort | -0.184 |
nels | -0.151 |
arently | -0.148 |
insula | -0.145 |
mt | -0.144 |
Token | urs |
Token ID | 1834 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ees | +0.263 |
REE | +0.222 |
lust | +0.214 |
ealous | +0.214 |
yip | +0.213 |
Neg logit contributions | |
afort | -0.346 |
nels | -0.283 |
arently | -0.275 |
insula | -0.270 |
mt | -0.269 |
Token | is |
Token ID | 318 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ees | +0.986 |
REE | +0.827 |
lust | +0.803 |
sum | +0.800 |
ealous | +0.799 |
Neg logit contributions | |
afort | -1.257 |
nels | -1.021 |
arently | -0.997 |
insula | -0.981 |
mt | -0.971 |
Token | a |
Token ID | 257 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
afort | +0.952 |
nels | +0.774 |
arently | +0.754 |
insula | +0.739 |
mt | +0.736 |
Neg logit contributions | |
ees | -0.777 |
REE | -0.658 |
lust | -0.638 |
yip | -0.638 |
ealous | -0.636 |
Token | Bachelor |
Token ID | 33399 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
ees | +0.030 |
REE | +0.025 |
lust | +0.024 |
yip | +0.024 |
ealous | +0.024 |
Neg logit contributions | |
afort | -0.042 |
nels | -0.035 |
arently | -0.034 |
insula | -0.033 |
mt | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
ees | +6.015 |
sum | +5.035 |
lust | +4.993 |
REE | +4.991 |
diagnosis | +4.900 |
Neg logit contributions | |
afort | -8.602 |
nels | -6.964 |
arently | -6.729 |
mt | -6.604 |
insula | -6.530 |
Token | Science |
Token ID | 5800 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
afort | +0.610 |
nels | +0.483 |
arently | +0.468 |
insula | +0.457 |
mt | +0.455 |
Neg logit contributions | |
ees | -0.626 |
REE | -0.541 |
lust | -0.527 |
yip | -0.526 |
ealous | -0.525 |
Token | degree |
Token ID | 4922 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
ees | +0.923 |
REE | +0.765 |
lust | +0.737 |
sum | +0.737 |
ealous | +0.732 |
Neg logit contributions | |
afort | -1.401 |
nels | -1.158 |
arently | -1.130 |
insula | -1.109 |
mt | -1.106 |
Token | in |
Token ID | 287 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ees | +2.527 |
REE | +2.091 |
sum | +2.038 |
lust | +2.033 |
ealous | +1.996 |
Neg logit contributions | |
afort | -3.534 |
nels | -2.875 |
arently | -2.800 |
insula | -2.746 |
mt | -2.743 |
Token | business |
Token ID | 1597 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ees | +0.495 |
REE | +0.428 |
sum | +0.417 |
lust | +0.417 |
ealous | +0.415 |
Neg logit contributions | |
afort | -0.479 |
nels | -0.378 |
arently | -0.366 |
insula | -0.358 |
mt | -0.356 |
Token | a |
Token ID | 257 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
ees | +0.537 |
REE | +0.451 |
yip | +0.437 |
lust | +0.437 |
ealous | +0.435 |
Neg logit contributions | |
afort | -0.709 |
nels | -0.581 |
arently | -0.567 |
insula | -0.555 |
mt | -0.554 |
Token | donation |
Token ID | 13784 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
afort | +0.496 |
nels | +0.411 |
arently | +0.402 |
insula | +0.394 |
mt | +0.394 |
Neg logit contributions | |
ees | -0.329 |
REE | -0.272 |
yip | -0.265 |
lust | -0.263 |
ealous | -0.262 |
Token | received |
Token ID | 2722 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
afort | +1.102 |
nels | +0.898 |
arently | +0.877 |
mt | +0.857 |
insula | +0.854 |
Neg logit contributions | |
ees | -0.874 |
REE | -0.747 |
yip | -0.724 |
ealous | -0.720 |
hovah | -0.717 |
Token | by |
Token ID | 416 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
afort | +2.581 |
nels | +2.105 |
arently | +2.056 |
mt | +2.012 |
insula | +2.007 |
Neg logit contributions | |
ees | -2.030 |
REE | -1.724 |
yip | -1.675 |
ealous | -1.673 |
lust | -1.660 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
afort | +0.156 |
nels | +0.128 |
arently | +0.125 |
insula | +0.123 |
mt | +0.122 |
Neg logit contributions | |
ees | -0.114 |
REE | -0.096 |
lust | -0.092 |
yip | -0.092 |
ealous | -0.092 |
Token | Nobel |
Token ID | 20715 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
ees | +0.104 |
REE | +0.086 |
lust | +0.083 |
yip | +0.083 |
ealous | +0.083 |
Neg logit contributions | |
afort | -0.152 |
nels | -0.126 |
arently | -0.123 |
insula | -0.121 |
mt | -0.120 |
Token | Foundation |
Token ID | 5693 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ees | +6.009 |
sum | +4.739 |
REE | +4.608 |
lust | +4.561 |
Kai | +4.452 |
Neg logit contributions | |
afort | -8.908 |
nels | -7.265 |
arently | -7.080 |
insula | -7.012 |
mt | -6.780 |
Token | in |
Token ID | 287 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
ees | +2.273 |
REE | +1.870 |
sum | +1.863 |
lust | +1.814 |
ealous | +1.794 |
Neg logit contributions | |
afort | -3.077 |
nels | -2.528 |
arently | -2.475 |
insula | -2.414 |
mt | -2.387 |
Token | 1968 |
Token ID | 15963 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
afort | +0.066 |
nels | +0.053 |
arently | +0.051 |
insula | +0.050 |
mt | +0.050 |
Neg logit contributions | |
ees | -0.063 |
REE | -0.054 |
lust | -0.052 |
sum | -0.052 |
yip | -0.052 |
Token | from |
Token ID | 422 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
afort | +2.027 |
nels | +1.646 |
arently | +1.604 |
mt | +1.571 |
insula | +1.570 |
Neg logit contributions | |
ees | -1.626 |
REE | -1.382 |
yip | -1.339 |
lust | -1.334 |
ealous | -1.330 |
Token | S |
Token ID | 311 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ees | +0.610 |
REE | +0.508 |
sum | +0.490 |
lust | +0.490 |
yip | +0.488 |
Neg logit contributions | |
afort | -0.875 |
nels | -0.723 |
arently | -0.704 |
insula | -0.693 |
mt | -0.689 |
Token | government |
Token ID | 1230 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ees | +0.511 |
REE | +0.426 |
sum | +0.411 |
lust | +0.411 |
ealous | +0.408 |
Neg logit contributions | |
afort | -0.726 |
nels | -0.598 |
arently | -0.583 |
insula | -0.573 |
mt | -0.570 |
Token | faces |
Token ID | 6698 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
afort | +1.067 |
nels | +0.874 |
arently | +0.853 |
insula | +0.835 |
mt | +0.833 |
Neg logit contributions | |
ees | -0.816 |
REE | -0.688 |
yip | -0.666 |
lust | -0.665 |
ealous | -0.663 |
Token | aboriginal |
Token ID | 48328 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
ees | +0.876 |
REE | +0.730 |
sum | +0.712 |
lust | +0.712 |
yip | +0.707 |
Neg logit contributions | |
afort | -1.180 |
nels | -0.963 |
arently | -0.938 |
insula | -0.925 |
mt | -0.919 |
Token | opposition |
Token ID | 5471 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ees | +5.537 |
sum | +4.526 |
REE | +4.452 |
lust | +4.362 |
diagnosis | +4.285 |
Neg logit contributions | |
afort | -8.208 |
nels | -6.640 |
arently | -6.506 |
insula | -6.466 |
llular | -6.274 |
Token | to |
Token ID | 284 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ees | +0.936 |
REE | +0.780 |
sum | +0.766 |
lust | +0.766 |
ealous | +0.751 |
Neg logit contributions | |
afort | -1.252 |
nels | -1.025 |
arently | -0.996 |
mt | -0.981 |
insula | -0.980 |
Token | Kinder |
Token ID | 46832 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
ees | +0.913 |
REE | +0.771 |
lust | +0.747 |
sum | +0.745 |
yip | +0.739 |
Neg logit contributions | |
afort | -1.192 |
nels | -0.971 |
arently | -0.947 |
insula | -0.930 |
mt | -0.923 |
Token | Morgan |
Token ID | 10805 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ees | +5.232 |
lust | +4.375 |
sum | +4.133 |
Kai | +4.023 |
REE | +4.009 |
Neg logit contributions | |
afort | -9.429 |
arently | -7.748 |
nels | -7.614 |
insula | -7.452 |
llular | -7.319 |
Token | � |
Token ID | 447 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ees | +0.914 |
REE | +0.772 |
lust | +0.750 |
sum | +0.749 |
yip | +0.740 |
Neg logit contributions | |
afort | -1.146 |
nels | -0.926 |
arently | -0.905 |
insula | -0.891 |
mt | -0.881 |
Token | � |
Token ID | 247 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ees | +0.689 |
REE | +0.557 |
sum | +0.539 |
lust | +0.538 |
ealous | +0.533 |
Neg logit contributions | |
afort | -1.207 |
nels | -1.008 |
arently | -0.989 |
insula | -0.968 |
mt | -0.959 |
Token | s |
Token ID | 82 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ees | +0.652 |
REE | +0.526 |
sum | +0.514 |
lust | +0.512 |
ealous | +0.502 |
Neg logit contributions | |
afort | -1.090 |
nels | -0.903 |
arently | -0.886 |
insula | -0.875 |
mt | -0.851 |
Token | Trans |
Token ID | 3602 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ees | +0.778 |
REE | +0.658 |
lust | +0.638 |
yip | +0.638 |
ealous | +0.636 |
Neg logit contributions | |
afort | -0.959 |
nels | -0.780 |
arently | -0.759 |
insula | -0.744 |
mt | -0.741 |
Token | surprised |
Token ID | 6655 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ees | +0.396 |
REE | +0.334 |
sum | +0.328 |
lust | +0.326 |
ealous | +0.323 |
Neg logit contributions | |
afort | -0.464 |
nels | -0.375 |
arently | -0.365 |
insula | -0.360 |
mt | -0.355 |
Token | again |
Token ID | 757 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ees | +1.738 |
REE | +1.431 |
sum | +1.400 |
lust | +1.391 |
yip | +1.378 |
Neg logit contributions | |
afort | -2.376 |
nels | -1.956 |
arently | -1.903 |
insula | -1.894 |
mt | -1.862 |
Token | now |
Token ID | 783 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ees | +0.847 |
REE | +0.711 |
lust | +0.690 |
sum | +0.689 |
yip | +0.686 |
Neg logit contributions | |
afort | -1.092 |
nels | -0.894 |
arently | -0.870 |
insula | -0.857 |
mt | -0.851 |
Token | that |
Token ID | 326 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
afort | +0.675 |
nels | +0.554 |
arently | +0.540 |
insula | +0.528 |
mt | +0.528 |
Neg logit contributions | |
ees | -0.503 |
REE | -0.423 |
yip | -0.410 |
lust | -0.409 |
ealous | -0.408 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ees | +0.377 |
REE | +0.317 |
lust | +0.306 |
yip | +0.306 |
ealous | +0.305 |
Neg logit contributions | |
afort | -0.498 |
nels | -0.408 |
arently | -0.398 |
insula | -0.390 |
mt | -0.389 |
Token | slump |
Token ID | 37758 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
ees | +0.803 |
REE | +0.665 |
sum | +0.646 |
lust | +0.643 |
ealous | +0.636 |
Neg logit contributions | |
afort | -1.231 |
nels | -1.018 |
arently | -0.995 |
insula | -0.980 |
mt | -0.973 |
Token | in |
Token ID | 287 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ees | +5.914 |
diagnosis | +4.852 |
lust | +4.850 |
sum | +4.814 |
REE | +4.603 |
Neg logit contributions | |
afort | -8.734 |
nels | -7.028 |
insula | -6.907 |
arently | -6.880 |
mt | -6.790 |
Token | sales |
Token ID | 4200 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ees | +0.920 |
REE | +0.770 |
lust | +0.748 |
sum | +0.747 |
yip | +0.737 |
Neg logit contributions | |
afort | -1.268 |
nels | -1.044 |
arently | -1.020 |
insula | -1.003 |
mt | -0.994 |
Token | over |
Token ID | 625 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
ees | +0.403 |
REE | +0.337 |
lust | +0.328 |
sum | +0.327 |
yip | +0.325 |
Neg logit contributions | |
afort | -0.545 |
nels | -0.446 |
arently | -0.435 |
insula | -0.428 |
mt | -0.425 |
Token | the |
Token ID | 262 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
afort | +0.660 |
nels | +0.540 |
arently | +0.527 |
insula | +0.517 |
mt | +0.515 |
Neg logit contributions | |
ees | -0.501 |
REE | -0.422 |
lust | -0.408 |
yip | -0.408 |
ealous | -0.407 |
Token | cold |
Token ID | 4692 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ees | +0.618 |
REE | +0.522 |
sum | +0.508 |
lust | +0.506 |
yip | +0.504 |
Neg logit contributions | |
afort | -0.781 |
nels | -0.637 |
arently | -0.620 |
insula | -0.607 |
mt | -0.605 |
Token | iro |
Token ID | 7058 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
ees | +0.955 |
REE | +0.810 |
lust | +0.795 |
ealous | +0.787 |
yip | +0.786 |
Neg logit contributions | |
afort | -1.032 |
nels | -0.826 |
arently | -0.805 |
insula | -0.792 |
mt | -0.784 |
Token | vs |
Token ID | 14259 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ees | +2.070 |
REE | +1.737 |
lust | +1.720 |
sum | +1.720 |
ealous | +1.694 |
Neg logit contributions | |
afort | -2.488 |
nels | -2.006 |
arently | -1.956 |
insula | -1.954 |
mt | -1.868 |
Token | ki |
Token ID | 4106 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ees | +0.759 |
REE | +0.602 |
lust | +0.580 |
sum | +0.580 |
ealous | +0.576 |
Neg logit contributions | |
afort | -1.463 |
nels | -1.241 |
arently | -1.211 |
insula | -1.197 |
mt | -1.183 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ees | +0.862 |
REE | +0.723 |
lust | +0.699 |
yip | +0.698 |
ealous | +0.696 |
Neg logit contributions | |
afort | -1.176 |
nels | -0.966 |
arently | -0.942 |
insula | -0.924 |
mt | -0.921 |
Token | Keith |
Token ID | 14926 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
afort | +1.184 |
nels | +0.975 |
arently | +0.953 |
mt | +0.934 |
insula | +0.929 |
Neg logit contributions | |
ees | -0.844 |
REE | -0.708 |
yip | -0.687 |
ealous | -0.684 |
lust | -0.682 |
Token | Gillespie |
Token ID | 45078 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
ees | +2.207 |
REE | +1.855 |
lust | +1.811 |
sum | +1.801 |
ealous | +1.793 |
Neg logit contributions | |
afort | -2.719 |
nels | -2.213 |
arently | -2.157 |
insula | -2.113 |
mt | -2.095 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
afort | +9.350 |
nels | +7.534 |
arently | +7.280 |
mt | +7.226 |
insula | +6.968 |
Neg logit contributions | |
ees | -8.554 |
yip | -7.480 |
REE | -7.444 |
hovah | -7.355 |
ealous | -7.296 |
Token | David |
Token ID | 3271 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
afort | +1.160 |
nels | +0.955 |
arently | +0.933 |
mt | +0.912 |
insula | +0.911 |
Neg logit contributions | |
ees | -0.831 |
REE | -0.698 |
yip | -0.675 |
ealous | -0.674 |
lust | -0.673 |
Token | Pierce |
Token ID | 23023 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
afort | +1.298 |
nels | +1.064 |
arently | +1.028 |
mt | +1.009 |
insula | +1.000 |
Neg logit contributions | |
ees | -1.044 |
REE | -0.886 |
yip | -0.879 |
ealous | -0.862 |
lust | -0.859 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ees | +0.331 |
REE | +0.277 |
sum | +0.269 |
lust | +0.269 |
yip | +0.267 |
Neg logit contributions | |
afort | -0.442 |
nels | -0.362 |
arently | -0.353 |
insula | -0.348 |
mt | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
afort | +1.541 |
nels | +1.277 |
arently | +1.248 |
insula | +1.226 |
mt | +1.221 |
Neg logit contributions | |
ees | -1.020 |
REE | -0.844 |
lust | -0.814 |
yip | -0.813 |
ealous | -0.811 |
Token | kick |
Token ID | 24585 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ees | +1.333 |
REE | +1.109 |
lust | +1.076 |
yip | +1.072 |
sum | +1.069 |
Neg logit contributions | |
afort | -1.873 |
nels | -1.544 |
arently | -1.506 |
insula | -1.479 |
mt | -1.469 |
Token | past |
Token ID | 1613 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
afort | +1.349 |
nels | +1.105 |
arently | +1.078 |
insula | +1.051 |
mt | +1.049 |
Neg logit contributions | |
ees | -1.069 |
REE | -0.910 |
yip | -0.881 |
ealous | -0.878 |
lust | -0.875 |
Token | Irish |
Token ID | 8685 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
afort | +1.033 |
nels | +0.846 |
arently | +0.824 |
mt | +0.808 |
insula | +0.805 |
Neg logit contributions | |
ees | -0.783 |
REE | -0.663 |
yip | -0.643 |
ealous | -0.640 |
lust | -0.637 |
Token | keeper |
Token ID | 28356 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
ees | +1.132 |
REE | +0.906 |
lust | +0.880 |
sum | +0.878 |
ealous | +0.862 |
Neg logit contributions | |
afort | -1.948 |
nels | -1.631 |
arently | -1.601 |
insula | -1.580 |
mt | -1.548 |
Token | Evan |
Token ID | 21523 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
afort | +0.343 |
nels | +0.283 |
arently | +0.276 |
insula | +0.271 |
mt | +0.271 |
Neg logit contributions | |
ees | -0.242 |
REE | -0.202 |
yip | -0.195 |
lust | -0.195 |
ealous | -0.195 |
Token | Moran |
Token ID | 42705 |
Feature activation | -9.48e+00 |
Pos logit contributions | |
afort | +4.078 |
nels | +3.340 |
arently | +3.215 |
insula | +3.180 |
mt | +3.169 |
Neg logit contributions | |
ees | -3.187 |
REE | -2.751 |
yip | -2.675 |
ealous | -2.641 |
hovah | -2.635 |
Token | with |
Token ID | 351 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
afort | +8.372 |
nels | +6.817 |
arently | +6.494 |
mt | +6.381 |
insula | +6.193 |
Neg logit contributions | |
ees | -7.411 |
REE | -6.555 |
hovah | -6.288 |
yip | -6.257 |
ealous | -6.172 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
afort | +0.282 |
nels | +0.229 |
arently | +0.223 |
insula | +0.220 |
mt | +0.217 |
Neg logit contributions | |
ees | -0.230 |
REE | -0.195 |
lust | -0.189 |
sum | -0.189 |
yip | -0.188 |
Token | pl |
Token ID | 489 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
afort | +1.350 |
nels | +1.112 |
arently | +1.083 |
mt | +1.063 |
insula | +1.061 |
Neg logit contributions | |
ees | -0.994 |
REE | -0.833 |
yip | -0.808 |
ealous | -0.802 |
lust | -0.800 |
Token | omb |
Token ID | 2381 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
afort | +0.669 |
nels | +0.561 |
arently | +0.552 |
mt | +0.540 |
insula | +0.538 |
Neg logit contributions | |
ees | -0.380 |
REE | -0.312 |
yip | -0.303 |
hovah | -0.299 |
lust | -0.296 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ees | +0.148 |
REE | +0.125 |
lust | +0.122 |
sum | +0.122 |
ealous | +0.121 |
Neg logit contributions | |
afort | -0.179 |
nels | -0.145 |
arently | -0.141 |
insula | -0.139 |
mt | -0.138 |
Token | ous |
Token ID | 516 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
afort | +3.439 |
nels | +2.820 |
arently | +2.760 |
mt | +2.710 |
insula | +2.694 |
Neg logit contributions | |
ees | -2.280 |
REE | -1.920 |
yip | -1.863 |
hovah | -1.831 |
lust | -1.826 |
Token | l |
Token ID | 75 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ees | +0.166 |
REE | +0.136 |
lust | +0.133 |
sum | +0.132 |
ealous | +0.132 |
Neg logit contributions | |
afort | -0.260 |
nels | -0.217 |
arently | -0.211 |
insula | -0.208 |
mt | -0.207 |
Token | over |
Token ID | 2502 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ees | +1.458 |
REE | +1.258 |
lust | +1.241 |
ealous | +1.236 |
sum | +1.219 |
Neg logit contributions | |
afort | -1.315 |
nels | -1.047 |
arently | -1.003 |
insula | -0.990 |
mt | -0.968 |
Token | ( |
Token ID | 357 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
afort | +2.528 |
nels | +2.066 |
arently | +2.015 |
mt | +1.974 |
insula | +1.969 |
Neg logit contributions | |
ees | -1.860 |
REE | -1.577 |
yip | -1.526 |
lust | -1.511 |
ealous | -1.507 |
Token | John |
Token ID | 7554 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
afort | +2.227 |
nels | +1.772 |
arently | +1.720 |
insula | +1.681 |
mt | +1.677 |
Neg logit contributions | |
ees | -2.192 |
REE | -1.888 |
yip | -1.840 |
lust | -1.836 |
ealous | -1.832 |
Token | Gavin |
Token ID | 30857 |
Feature activation | -9.14e+00 |
Pos logit contributions | |
afort | +1.490 |
nels | +1.216 |
arently | +1.183 |
mt | +1.161 |
insula | +1.160 |
Neg logit contributions | |
ees | -1.169 |
REE | -0.995 |
yip | -0.964 |
ealous | -0.959 |
lust | -0.957 |
Token | ), |
Token ID | 828 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
afort | +8.014 |
nels | +6.572 |
arently | +6.436 |
insula | +6.212 |
mt | +6.191 |
Neg logit contributions | |
ees | -7.076 |
REE | -6.246 |
yip | -6.133 |
glim | -6.015 |
hovah | -6.010 |
Token | but |
Token ID | 475 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
afort | +1.723 |
nels | +1.418 |
arently | +1.384 |
mt | +1.354 |
insula | +1.353 |
Neg logit contributions | |
ees | -1.230 |
REE | -1.030 |
yip | -0.997 |
lust | -0.994 |
ealous | -0.989 |
Token | Hitchcock |
Token ID | 49817 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
afort | +0.737 |
nels | +0.602 |
arently | +0.586 |
insula | +0.576 |
mt | +0.573 |
Neg logit contributions | |
ees | -0.573 |
REE | -0.482 |
lust | -0.469 |
sum | -0.467 |
ealous | -0.466 |
Token | has |
Token ID | 468 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ees | +0.490 |
REE | +0.410 |
sum | +0.402 |
lust | +0.401 |
ealous | +0.400 |
Neg logit contributions | |
afort | -0.593 |
nels | -0.480 |
arently | -0.468 |
insula | -0.465 |
mt | -0.459 |
Token | other |
Token ID | 584 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
afort | +0.282 |
nels | +0.229 |
arently | +0.222 |
insula | +0.219 |
mt | +0.218 |
Neg logit contributions | |
ees | -0.224 |
REE | -0.188 |
sum | -0.183 |
lust | -0.183 |
ealous | -0.182 |
Token | San |
Token ID | 2986 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
afort | +0.553 |
nels | +0.454 |
arently | +0.442 |
insula | +0.433 |
mt | +0.433 |
Neg logit contributions | |
ees | -0.418 |
REE | -0.351 |
yip | -0.341 |
lust | -0.340 |
ealous | -0.339 |
Token | Diego |
Token ID | 9500 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
afort | +2.631 |
nels | +2.072 |
arently | +1.993 |
mt | +1.976 |
insula | +1.970 |
Neg logit contributions | |
ees | -2.827 |
REE | -2.503 |
ealous | -2.439 |
yip | -2.418 |
glim | -2.392 |
Token | , |
Token ID | 11 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
afort | +2.821 |
nels | +2.271 |
arently | +2.201 |
insula | +2.196 |
mt | +2.159 |
Neg logit contributions | |
ees | -2.497 |
REE | -2.155 |
yip | -2.149 |
ealous | -2.102 |
lust | -2.087 |
Token | Dallas |
Token ID | 8533 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
afort | +0.858 |
nels | +0.705 |
arently | +0.687 |
mt | +0.673 |
insula | +0.673 |
Neg logit contributions | |
ees | -0.630 |
REE | -0.529 |
yip | -0.515 |
lust | -0.512 |
ealous | -0.511 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
afort | +1.855 |
nels | +1.496 |
arently | +1.455 |
insula | +1.426 |
mt | +1.424 |
Neg logit contributions | |
ees | -1.621 |
REE | -1.397 |
yip | -1.376 |
lust | -1.357 |
ealous | -1.356 |
Token | Palm |
Token ID | 18358 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
afort | +1.104 |
nels | +0.902 |
arently | +0.878 |
mt | +0.861 |
insula | +0.860 |
Neg logit contributions | |
ees | -0.857 |
REE | -0.724 |
yip | -0.706 |
lust | -0.701 |
ealous | -0.700 |
Token | Beach |
Token ID | 8511 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
afort | +6.155 |
nels | +4.415 |
insula | +4.349 |
mt | +4.239 |
arently | +4.211 |
Neg logit contributions | |
ees | -8.882 |
yip | -8.170 |
REE | -8.014 |
xual | -7.867 |
lust | -7.846 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
afort | +1.479 |
nels | +1.199 |
arently | +1.168 |
insula | +1.146 |
mt | +1.140 |
Neg logit contributions | |
ees | -1.223 |
REE | -1.038 |
yip | -1.010 |
lust | -1.007 |
ealous | -1.004 |
Token | Florida |
Token ID | 4744 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
afort | +1.367 |
nels | +1.119 |
arently | +1.088 |
insula | +1.067 |
mt | +1.067 |
Neg logit contributions | |
ees | -1.066 |
REE | -0.900 |
yip | -0.881 |
lust | -0.874 |
ealous | -0.873 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
afort | +3.198 |
nels | +2.573 |
arently | +2.501 |
insula | +2.472 |
mt | +2.443 |
Neg logit contributions | |
ees | -2.754 |
REE | -2.357 |
yip | -2.321 |
ealous | -2.290 |
lust | -2.288 |
Token | Moreno |
Token ID | 43269 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
afort | +1.282 |
nels | +1.049 |
arently | +1.020 |
mt | +1.000 |
insula | +0.999 |
Neg logit contributions | |
ees | -1.000 |
REE | -0.845 |
yip | -0.824 |
lust | -0.819 |
ealous | -0.818 |
Token | Christian |
Token ID | 20298 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ees | +1.462 |
REE | +1.267 |
lust | +1.226 |
ealous | +1.204 |
yip | +1.200 |
Neg logit contributions | |
afort | -1.583 |
nels | -1.260 |
arently | -1.236 |
insula | -1.209 |
mt | -1.174 |
Token | philosopher |
Token ID | 23723 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
ees | +0.144 |
REE | +0.121 |
lust | +0.118 |
yip | +0.118 |
ealous | +0.117 |
Neg logit contributions | |
afort | -0.179 |
nels | -0.146 |
arently | -0.142 |
insula | -0.139 |
mt | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
ees | +0.557 |
REE | +0.462 |
lust | +0.446 |
yip | +0.446 |
ealous | +0.444 |
Neg logit contributions | |
afort | -0.819 |
nels | -0.677 |
arently | -0.661 |
insula | -0.649 |
mt | -0.647 |
Token | blogger |
Token ID | 23530 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
afort | +0.053 |
nels | +0.044 |
arently | +0.043 |
mt | +0.042 |
insula | +0.042 |
Neg logit contributions | |
ees | -0.038 |
REE | -0.032 |
yip | -0.031 |
lust | -0.031 |
ealous | -0.030 |
Token | Dr |
Token ID | 1583 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ees | +0.349 |
REE | +0.290 |
lust | +0.280 |
yip | +0.280 |
sum | +0.279 |
Neg logit contributions | |
afort | -0.506 |
nels | -0.418 |
arently | -0.408 |
insula | -0.401 |
mt | -0.399 |
Token | Glenn |
Token ID | 17551 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
ees | +1.185 |
REE | +1.004 |
lust | +0.974 |
yip | +0.971 |
sum | +0.971 |
Neg logit contributions | |
afort | -1.423 |
nels | -1.155 |
arently | -1.124 |
insula | -1.103 |
mt | -1.095 |
Token | Peoples |
Token ID | 41770 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
afort | +8.111 |
nels | +6.451 |
arently | +6.294 |
mt | +6.258 |
insula | +6.226 |
Neg logit contributions | |
ees | -6.667 |
REE | -5.877 |
lust | -5.830 |
yip | -5.763 |
hovah | -5.727 |
Token | is |
Token ID | 318 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
afort | +5.087 |
nels | +4.134 |
arently | +4.008 |
mt | +3.937 |
insula | +3.837 |
Neg logit contributions | |
ees | -4.112 |
REE | -3.505 |
yip | -3.416 |
ealous | -3.403 |
lust | -3.403 |
Token | coming |
Token ID | 2406 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
afort | +1.876 |
nels | +1.528 |
arently | +1.489 |
insula | +1.459 |
mt | +1.454 |
Neg logit contributions | |
ees | -1.503 |
REE | -1.271 |
lust | -1.232 |
yip | -1.231 |
ealous | -1.228 |
Token | to |
Token ID | 284 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
afort | +0.356 |
nels | +0.291 |
arently | +0.283 |
insula | +0.278 |
mt | +0.277 |
Neg logit contributions | |
ees | -0.279 |
REE | -0.235 |
lust | -0.228 |
yip | -0.228 |
ealous | -0.227 |
Token | Auckland |
Token ID | 30422 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ees | +0.268 |
REE | +0.226 |
yip | +0.220 |
lust | +0.219 |
ealous | +0.219 |
Neg logit contributions | |
afort | -0.347 |
nels | -0.283 |
arently | -0.276 |
insula | -0.270 |
mt | -0.270 |
Token | to |
Token ID | 284 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
afort | +2.466 |
nels | +1.994 |
arently | +1.947 |
mt | +1.900 |
insula | +1.891 |
Neg logit contributions | |
ees | -2.003 |
REE | -1.711 |
yip | -1.670 |
lust | -1.646 |
ealous | -1.644 |
Token | the |
Token ID | 262 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
afort | +0.268 |
nels | +0.219 |
arently | +0.214 |
insula | +0.209 |
mt | +0.209 |
Neg logit contributions | |
ees | -0.210 |
REE | -0.177 |
yip | -0.171 |
lust | -0.171 |
ealous | -0.171 |
Token | tragedy |
Token ID | 13574 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
afort | +0.038 |
nels | +0.031 |
arently | +0.030 |
insula | +0.030 |
mt | +0.030 |
Neg logit contributions | |
ees | -0.030 |
REE | -0.025 |
yip | -0.024 |
lust | -0.024 |
ealous | -0.024 |
Token | by |
Token ID | 416 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
afort | +0.696 |
nels | +0.570 |
arently | +0.556 |
insula | +0.546 |
mt | +0.544 |
Neg logit contributions | |
ees | -0.522 |
REE | -0.438 |
lust | -0.424 |
yip | -0.423 |
sum | -0.423 |
Token | immediately |
Token ID | 3393 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
afort | +0.257 |
nels | +0.208 |
arently | +0.202 |
insula | +0.199 |
mt | +0.197 |
Neg logit contributions | |
ees | -0.220 |
REE | -0.187 |
sum | -0.183 |
lust | -0.182 |
yip | -0.181 |
Token | politic |
Token ID | 31723 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
ees | +0.001 |
REE | +0.001 |
sum | +0.001 |
lust | +0.001 |
yip | +0.001 |
Neg logit contributions | |
afort | -0.001 |
nels | -0.001 |
arently | -0.001 |
insula | -0.001 |
mt | -0.001 |
Token | izing |
Token ID | 2890 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
afort | +5.365 |
nels | +3.695 |
arently | +3.565 |
mt | +3.421 |
insula | +3.116 |
Neg logit contributions | |
ees | -9.968 |
REE | -9.031 |
yip | -8.946 |
hovah | -8.800 |
lust | -8.707 |
Token | it |
Token ID | 340 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
afort | +3.933 |
nels | +3.183 |
arently | +3.073 |
mt | +3.038 |
insula | +2.989 |
Neg logit contributions | |
ees | -3.353 |
REE | -2.876 |
yip | -2.806 |
ealous | -2.791 |
hovah | -2.791 |
Token | . |
Token ID | 13 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
ees | +0.377 |
REE | +0.314 |
sum | +0.308 |
lust | +0.306 |
ealous | +0.305 |
Neg logit contributions | |
afort | -0.492 |
nels | -0.403 |
arently | -0.394 |
insula | -0.389 |
mt | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
afort | +0.495 |
nels | +0.409 |
arently | +0.399 |
insula | +0.392 |
mt | +0.389 |
Neg logit contributions | |
ees | -0.346 |
REE | -0.289 |
lust | -0.279 |
ealous | -0.278 |
sum | -0.278 |
Token |
|
Token ID | 198 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
afort | +0.456 |
nels | +0.378 |
arently | +0.374 |
insula | +0.369 |
mt | +0.359 |
Neg logit contributions | |
ees | -0.276 |
REE | -0.226 |
lust | -0.219 |
sum | -0.216 |
ealous | -0.215 |
Token | s |
Token ID | 82 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
ees | +0.891 |
REE | +0.750 |
lust | +0.727 |
sum | +0.724 |
yip | +0.724 |
Neg logit contributions | |
afort | -1.133 |
nels | -0.923 |
arently | -0.902 |
insula | -0.883 |
mt | -0.879 |
Token | executive |
Token ID | 4640 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ees | +0.495 |
REE | +0.409 |
yip | +0.394 |
lust | +0.394 |
ealous | +0.393 |
Neg logit contributions | |
afort | -0.773 |
nels | -0.643 |
arently | -0.628 |
insula | -0.617 |
mt | -0.615 |
Token | director |
Token ID | 3437 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
afort | +1.005 |
nels | +0.806 |
arently | +0.782 |
insula | +0.769 |
mt | +0.764 |
Neg logit contributions | |
ees | -0.925 |
REE | -0.802 |
lust | -0.781 |
yip | -0.781 |
ealous | -0.779 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ees | +0.196 |
REE | +0.166 |
lust | +0.161 |
yip | +0.161 |
ealous | +0.161 |
Neg logit contributions | |
afort | -0.246 |
nels | -0.201 |
arently | -0.196 |
insula | -0.192 |
mt | -0.191 |
Token | Jose |
Token ID | 5264 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
afort | +0.308 |
nels | +0.253 |
arently | +0.247 |
insula | +0.242 |
mt | +0.242 |
Neg logit contributions | |
ees | -0.222 |
REE | -0.186 |
yip | -0.180 |
lust | -0.179 |
ealous | -0.179 |
Token | Gar |
Token ID | 7164 |
Feature activation | -9.02e+00 |
Pos logit contributions | |
ees | +1.867 |
REE | +1.567 |
lust | +1.531 |
yip | +1.520 |
sum | +1.519 |
Neg logit contributions | |
afort | -2.302 |
nels | -1.870 |
arently | -1.830 |
insula | -1.790 |
mt | -1.769 |
Token | za |
Token ID | 4496 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
afort | +7.450 |
nels | +5.979 |
arently | +5.753 |
mt | +5.610 |
insula | +5.476 |
Neg logit contributions | |
ees | -7.552 |
REE | -6.696 |
glim | -6.554 |
hovah | -6.515 |
diagnosis | -6.409 |
Token | , |
Token ID | 11 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
afort | +2.980 |
nels | +2.404 |
arently | +2.305 |
mt | +2.260 |
insula | +2.249 |
Neg logit contributions | |
ees | -2.711 |
REE | -2.347 |
yip | -2.308 |
lust | -2.274 |
ealous | -2.252 |
Token | said |
Token ID | 531 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
afort | +0.826 |
nels | +0.669 |
arently | +0.649 |
insula | +0.634 |
mt | +0.634 |
Neg logit contributions | |
ees | -0.706 |
REE | -0.603 |
yip | -0.586 |
lust | -0.585 |
ealous | -0.583 |
Token | Houston |
Token ID | 6995 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
afort | +2.345 |
nels | +1.934 |
arently | +1.873 |
mt | +1.831 |
insula | +1.829 |
Neg logit contributions | |
ees | -1.843 |
REE | -1.561 |
yip | -1.527 |
lust | -1.512 |
ealous | -1.511 |
Token | has |
Token ID | 468 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
afort | +1.935 |
nels | +1.586 |
arently | +1.546 |
mt | +1.514 |
insula | +1.510 |
Neg logit contributions | |
ees | -1.475 |
REE | -1.247 |
yip | -1.216 |
lust | -1.209 |
ealous | -1.200 |
Token | ary |
Token ID | 560 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ees | +0.571 |
REE | +0.459 |
lust | +0.442 |
ealous | +0.439 |
sum | +0.438 |
Neg logit contributions | |
afort | -1.017 |
nels | -0.854 |
arently | -0.835 |
insula | -0.822 |
mt | -0.817 |
Token | ana |
Token ID | 2271 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ees | +0.881 |
REE | +0.724 |
lust | +0.703 |
sum | +0.702 |
ealous | +0.701 |
Neg logit contributions | |
afort | -1.289 |
nels | -1.066 |
arently | -1.045 |
insula | -1.024 |
mt | -1.014 |
Token | � |
Token ID | 447 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
afort | +2.672 |
nels | +2.153 |
arently | +2.101 |
mt | +2.062 |
insula | +2.045 |
Neg logit contributions | |
ees | -2.359 |
REE | -2.024 |
yip | -1.972 |
ealous | -1.963 |
lust | -1.955 |
Token | � |
Token ID | 247 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
afort | +0.556 |
nels | +0.445 |
arently | +0.433 |
insula | +0.423 |
mt | +0.422 |
Neg logit contributions | |
ees | -0.517 |
REE | -0.443 |
lust | -0.431 |
yip | -0.431 |
ealous | -0.430 |
Token | s |
Token ID | 82 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
afort | +0.682 |
nels | +0.556 |
arently | +0.542 |
insula | +0.531 |
mt | +0.528 |
Neg logit contributions | |
ees | -0.537 |
REE | -0.453 |
lust | -0.439 |
yip | -0.438 |
sum | -0.437 |
Token | Gar |
Token ID | 7164 |
Feature activation | -8.93e+00 |
Pos logit contributions | |
afort | +0.229 |
nels | +0.187 |
arently | +0.183 |
insula | +0.179 |
mt | +0.179 |
Neg logit contributions | |
ees | -0.172 |
REE | -0.144 |
yip | -0.140 |
lust | -0.140 |
ealous | -0.139 |
Token | hi |
Token ID | 5303 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
afort | +7.742 |
nels | +6.400 |
mt | +6.297 |
arently | +6.213 |
station | +5.928 |
Neg logit contributions | |
ees | -6.647 |
REE | -6.123 |
glim | -5.928 |
hovah | -5.846 |
ealous | -5.800 |
Token | H |
Token ID | 367 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ees | +0.046 |
REE | +0.039 |
lust | +0.038 |
yip | +0.038 |
ealous | +0.038 |
Neg logit contributions | |
afort | -0.056 |
nels | -0.045 |
arently | -0.044 |
insula | -0.043 |
mt | -0.043 |
Token | ars |
Token ID | 945 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ees | +0.441 |
REE | +0.366 |
lust | +0.354 |
ealous | +0.352 |
yip | +0.352 |
Neg logit contributions | |
afort | -0.639 |
nels | -0.528 |
arently | -0.515 |
insula | -0.505 |
mt | -0.503 |
Token | aru |
Token ID | 11493 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ees | +1.219 |
REE | +1.033 |
lust | +1.008 |
sum | +1.004 |
ealous | +1.003 |
Neg logit contributions | |
afort | -1.367 |
nels | -1.101 |
arently | -1.075 |
insula | -1.051 |
mt | -1.044 |
Token | Junction |
Token ID | 44410 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ees | +2.628 |
REE | +2.281 |
sum | +2.236 |
lust | +2.226 |
yip | +2.208 |
Neg logit contributions | |
afort | -2.416 |
nels | -1.871 |
arently | -1.820 |
insula | -1.781 |
mt | -1.746 |
Token | Donald |
Token ID | 3759 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
afort | +2.745 |
nels | +2.244 |
arently | +2.183 |
mt | +2.137 |
insula | +2.129 |
Neg logit contributions | |
ees | -2.283 |
REE | -1.932 |
yip | -1.892 |
ealous | -1.874 |
lust | -1.873 |
Token | J |
Token ID | 449 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
afort | +3.789 |
nels | +3.108 |
arently | +2.990 |
mt | +2.973 |
insula | +2.939 |
Neg logit contributions | |
ees | -2.935 |
REE | -2.447 |
yip | -2.423 |
lust | -2.386 |
hovah | -2.376 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ees | +3.158 |
ealous | +2.680 |
REE | +2.621 |
lust | +2.543 |
sum | +2.511 |
Neg logit contributions | |
afort | -4.406 |
arently | -3.661 |
nels | -3.654 |
insula | -3.611 |
mt | -3.422 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
afort | +0.167 |
nels | +0.134 |
arently | +0.133 |
insula | +0.131 |
mt | +0.126 |
Neg logit contributions | |
ees | -0.148 |
REE | -0.129 |
ealous | -0.124 |
lust | -0.123 |
sum | -0.122 |
Token | (@ |
Token ID | 4275 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
afort | +4.310 |
nels | +3.488 |
arently | +3.377 |
mt | +3.308 |
insula | +3.298 |
Neg logit contributions | |
ees | -3.733 |
REE | -3.169 |
yip | -3.105 |
lust | -3.078 |
ealous | -3.076 |
Token | realDonaldTrump |
Token ID | 28024 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
afort | +1.562 |
nels | +1.003 |
arently | +0.929 |
mt | +0.887 |
insula | +0.884 |
Neg logit contributions | |
ees | -3.887 |
REE | -3.517 |
yip | -3.451 |
lust | -3.451 |
sum | -3.445 |
Token | ) |
Token ID | 8 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
afort | +6.019 |
nels | +4.630 |
mt | +4.331 |
arently | +4.197 |
station | +3.969 |
Neg logit contributions | |
ees | -8.737 |
glim | -8.163 |
hovah | -8.135 |
yip | -8.009 |
citiz | -7.954 |
Token | November |
Token ID | 3389 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
afort | +1.842 |
nels | +1.451 |
arently | +1.406 |
insula | +1.372 |
mt | +1.368 |
Neg logit contributions | |
ees | -1.961 |
REE | -1.700 |
yip | -1.657 |
lust | -1.655 |
ealous | -1.652 |
Token | 3 |
Token ID | 513 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
afort | +3.640 |
nels | +2.927 |
mt | +2.795 |
arently | +2.793 |
insula | +2.699 |
Neg logit contributions | |
ees | -3.663 |
yip | -3.168 |
hovah | -3.146 |
REE | -3.145 |
glim | -3.098 |
Token | , |
Token ID | 11 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ees | +0.319 |
REE | +0.268 |
lust | +0.262 |
ealous | +0.257 |
sum | +0.257 |
Neg logit contributions | |
afort | -0.445 |
nels | -0.362 |
arently | -0.361 |
insula | -0.357 |
mt | -0.343 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
afort | +0.746 |
nels | +0.609 |
arently | +0.595 |
insula | +0.585 |
mt | +0.578 |
Neg logit contributions | |
ees | -0.593 |
REE | -0.502 |
sum | -0.486 |
lust | -0.484 |
ealous | -0.483 |
Token | the |
Token ID | 262 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
afort | +0.134 |
nels | +0.110 |
arently | +0.107 |
insula | +0.105 |
mt | +0.105 |
Neg logit contributions | |
ees | -0.103 |
REE | -0.087 |
sum | -0.084 |
lust | -0.084 |
ealous | -0.084 |
Token | same |
Token ID | 976 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ees | +0.353 |
REE | +0.283 |
sum | +0.273 |
ealous | +0.271 |
lust | +0.271 |
Neg logit contributions | |
afort | -0.643 |
nels | -0.542 |
arently | -0.530 |
insula | -0.520 |
mt | -0.519 |
Token | page |
Token ID | 2443 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ees | +1.748 |
REE | +1.493 |
sum | +1.467 |
diagnosis | +1.451 |
lust | +1.449 |
Neg logit contributions | |
afort | -1.921 |
nels | -1.545 |
arently | -1.504 |
insula | -1.455 |
mt | -1.452 |
Token | ? |
Token ID | 30 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
afort | +0.759 |
nels | +0.615 |
arently | +0.599 |
insula | +0.587 |
mt | +0.585 |
Neg logit contributions | |
ees | -0.634 |
REE | -0.538 |
lust | -0.522 |
yip | -0.521 |
ealous | -0.520 |
Token | Claire |
Token ID | 20758 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
ees | +0.759 |
REE | +0.628 |
lust | +0.608 |
sum | +0.601 |
ealous | +0.598 |
Neg logit contributions | |
afort | -1.165 |
nels | -0.963 |
arently | -0.947 |
insula | -0.929 |
mt | -0.918 |
Token | Gast |
Token ID | 31486 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
ees | +0.638 |
REE | +0.537 |
lust | +0.520 |
yip | +0.519 |
ealous | +0.518 |
Neg logit contributions | |
afort | -0.830 |
nels | -0.679 |
arently | -0.662 |
insula | -0.649 |
mt | -0.647 |
Token | an |
Token ID | 272 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
afort | +7.286 |
nels | +5.693 |
arently | +5.493 |
mt | +5.460 |
insula | +5.286 |
Neg logit contributions | |
ees | -7.214 |
REE | -6.516 |
yip | -6.348 |
glim | -6.259 |
ealous | -6.241 |
Token | aga |
Token ID | 8126 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
afort | +2.370 |
nels | +1.903 |
arently | +1.848 |
insula | +1.814 |
mt | +1.797 |
Neg logit contributions | |
ees | -2.148 |
REE | -1.845 |
yip | -1.802 |
ealous | -1.786 |
lust | -1.784 |
Token | , |
Token ID | 11 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
afort | +3.529 |
nels | +2.859 |
arently | +2.759 |
mt | +2.704 |
insula | +2.703 |
Neg logit contributions | |
ees | -3.050 |
REE | -2.619 |
yip | -2.587 |
lust | -2.550 |
ealous | -2.538 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
afort | +0.439 |
nels | +0.359 |
arently | +0.351 |
insula | +0.343 |
mt | +0.342 |
Neg logit contributions | |
ees | -0.340 |
REE | -0.284 |
sum | -0.277 |
lust | -0.276 |
yip | -0.275 |
Token | ACLU |
Token ID | 24381 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
afort | +0.484 |
nels | +0.393 |
arently | +0.382 |
insula | +0.374 |
mt | +0.373 |
Neg logit contributions | |
ees | -0.402 |
REE | -0.340 |
sum | -0.331 |
lust | -0.330 |
ealous | -0.329 |
Token | � |
Token ID | 40367 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
afort | +0.303 |
nels | +0.241 |
arently | +0.233 |
insula | +0.228 |
mt | +0.227 |
Neg logit contributions | |
ees | -0.308 |
REE | -0.266 |
lust | -0.259 |
yip | -0.258 |
ealous | -0.258 |
Token | � |
Token ID | 253 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
afort | +0.318 |
nels | +0.257 |
arently | +0.250 |
insula | +0.245 |
mt | +0.244 |
Neg logit contributions | |
ees | -0.270 |
REE | -0.230 |
lust | -0.223 |
yip | -0.223 |
sum | -0.222 |
Token | � |
Token ID | 161 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
afort | +1.243 |
nels | +0.982 |
arently | +0.955 |
mt | +0.932 |
insula | +0.932 |
Neg logit contributions | |
ees | -1.290 |
REE | -1.111 |
yip | -1.089 |
ealous | -1.084 |
lust | -1.083 |
Token | � |
Token ID | 254 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
afort | +0.422 |
nels | +0.330 |
arently | +0.320 |
insula | +0.312 |
mt | +0.311 |
Neg logit contributions | |
ees | -0.467 |
REE | -0.406 |
lust | -0.395 |
yip | -0.395 |
ealous | -0.394 |
Token | � |
Token ID | 109 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
afort | +0.609 |
nels | +0.467 |
arently | +0.450 |
insula | +0.438 |
mt | +0.436 |
Neg logit contributions | |
ees | -0.780 |
REE | -0.685 |
yip | -0.669 |
lust | -0.669 |
ealous | -0.667 |
Token | � |
Token ID | 27332 |
Feature activation | -8.68e+00 |
Pos logit contributions | |
afort | +2.217 |
nels | +1.758 |
arently | +1.709 |
mt | +1.671 |
insula | +1.667 |
Neg logit contributions | |
ees | -2.267 |
REE | -1.950 |
yip | -1.921 |
ealous | -1.906 |
lust | -1.904 |
Token | � |
Token ID | 121 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
afort | +6.626 |
nels | +5.077 |
arently | +5.054 |
insula | +4.854 |
mt | +4.832 |
Neg logit contributions | |
ees | -7.931 |
REE | -6.920 |
yip | -6.847 |
lust | -6.845 |
sum | -6.714 |
Token | � |
Token ID | 252 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
afort | +3.157 |
nels | +2.479 |
arently | +2.415 |
insula | +2.353 |
mt | +2.346 |
Neg logit contributions | |
ees | -3.410 |
REE | -2.961 |
lust | -2.895 |
yip | -2.894 |
ealous | -2.870 |
Token | Alternative |
Token ID | 27182 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
afort | +3.100 |
nels | +2.465 |
arently | +2.394 |
mt | +2.342 |
insula | +2.340 |
Neg logit contributions | |
ees | -3.135 |
REE | -2.686 |
yip | -2.648 |
lust | -2.632 |
ealous | -2.625 |
Token | Facts |
Token ID | 26972 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
afort | +3.143 |
nels | +2.525 |
arently | +2.452 |
insula | +2.387 |
mt | +2.376 |
Neg logit contributions | |
ees | -2.997 |
REE | -2.589 |
yip | -2.538 |
ealous | -2.517 |
lust | -2.514 |
Token | in |
Token ID | 287 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
afort | +0.183 |
nels | +0.148 |
arently | +0.145 |
insula | +0.142 |
mt | +0.141 |
Neg logit contributions | |
ees | -0.151 |
REE | -0.128 |
lust | -0.124 |
yip | -0.124 |
ealous | -0.124 |
Token | ond |
Token ID | 623 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
afort | +1.441 |
nels | +1.173 |
arently | +1.139 |
insula | +1.116 |
mt | +1.114 |
Neg logit contributions | |
ees | -1.217 |
REE | -1.041 |
yip | -1.012 |
lust | -1.007 |
sum | -1.006 |
Token | ateurs |
Token ID | 45211 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ees | +0.245 |
REE | +0.210 |
lust | +0.205 |
sum | +0.204 |
ealous | +0.204 |
Neg logit contributions | |
afort | -0.254 |
nels | -0.202 |
arently | -0.197 |
insula | -0.193 |
mt | -0.191 |
Token | s |
Token ID | 264 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
afort | +1.843 |
nels | +1.508 |
arently | +1.457 |
insula | +1.427 |
mt | +1.426 |
Neg logit contributions | |
ees | -1.506 |
REE | -1.282 |
yip | -1.242 |
ealous | -1.239 |
lust | -1.235 |
Token | ont |
Token ID | 756 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
ees | +0.157 |
REE | +0.133 |
lust | +0.129 |
yip | +0.129 |
ealous | +0.129 |
Neg logit contributions | |
afort | -0.186 |
nels | -0.151 |
arently | -0.147 |
insula | -0.144 |
mt | -0.143 |
Token | les |
Token ID | 10287 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
afort | +0.037 |
nels | +0.030 |
arently | +0.030 |
insula | +0.029 |
mt | +0.029 |
Neg logit contributions | |
ees | -0.030 |
REE | -0.025 |
lust | -0.024 |
yip | -0.024 |
sum | -0.024 |
Token | gar |
Token ID | 5482 |
Feature activation | -8.66e+00 |
Pos logit contributions | |
ees | +0.421 |
REE | +0.354 |
lust | +0.345 |
sum | +0.344 |
ealous | +0.343 |
Neg logit contributions | |
afort | -0.524 |
nels | -0.427 |
arently | -0.417 |
insula | -0.409 |
mt | -0.407 |
Token | ants |
Token ID | 1187 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
afort | +8.483 |
nels | +7.125 |
arently | +6.809 |
mt | +6.773 |
insula | +6.570 |
Neg logit contributions | |
ees | -5.623 |
REE | -4.971 |
yip | -4.859 |
hovah | -4.851 |
ealous | -4.780 |
Token | des |
Token ID | 748 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
afort | +1.449 |
nels | +1.185 |
arently | +1.147 |
mt | +1.123 |
insula | +1.123 |
Neg logit contributions | |
ees | -1.165 |
REE | -0.990 |
yip | -0.962 |
ealous | -0.958 |
lust | -0.956 |
Token | v |
Token ID | 410 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
afort | +1.071 |
nels | +0.874 |
arently | +0.850 |
insula | +0.833 |
mt | +0.832 |
Neg logit contributions | |
ees | -0.849 |
REE | -0.719 |
yip | -0.697 |
lust | -0.695 |
ealous | -0.694 |
Token | ale |
Token ID | 1000 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ees | +0.390 |
REE | +0.332 |
lust | +0.324 |
ealous | +0.323 |
yip | +0.321 |
Neg logit contributions | |
afort | -0.424 |
nels | -0.340 |
arently | -0.331 |
insula | -0.324 |
mt | -0.322 |
Token | urs |
Token ID | 1834 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
afort | +2.029 |
nels | +1.749 |
arently | +1.703 |
insula | +1.676 |
mt | +1.672 |
Neg logit contributions | |
ees | -0.847 |
REE | -0.665 |
yip | -0.633 |
lust | -0.618 |
ealous | -0.616 |
Token | dance |
Token ID | 9280 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
afort | +0.254 |
nels | +0.207 |
arently | +0.202 |
insula | +0.199 |
mt | +0.197 |
Neg logit contributions | |
ees | -0.201 |
REE | -0.169 |
sum | -0.164 |
lust | -0.164 |
yip | -0.163 |
Token | trou |
Token ID | 4057 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
afort | +3.033 |
nels | +2.472 |
arently | +2.400 |
mt | +2.355 |
insula | +2.345 |
Neg logit contributions | |
ees | -2.439 |
REE | -2.076 |
yip | -2.027 |
ealous | -2.014 |
lust | -2.012 |
Token | pe |
Token ID | 431 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ees | +0.246 |
REE | +0.165 |
lust | +0.154 |
yip | +0.153 |
ealous | +0.151 |
Neg logit contributions | |
afort | -0.864 |
nels | -0.750 |
arently | -0.738 |
insula | -0.728 |
mt | -0.723 |
Token | , |
Token ID | 11 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
afort | +0.098 |
nels | +0.080 |
arently | +0.078 |
insula | +0.077 |
mt | +0.076 |
Neg logit contributions | |
ees | -0.078 |
REE | -0.065 |
sum | -0.063 |
lust | -0.063 |
yip | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
afort | +0.659 |
nels | +0.538 |
arently | +0.525 |
insula | +0.514 |
mt | +0.513 |
Neg logit contributions | |
ees | -0.513 |
REE | -0.433 |
lust | -0.419 |
yip | -0.419 |
ealous | -0.418 |
Token | foam |
Token ID | 19828 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
afort | +0.533 |
nels | +0.435 |
arently | +0.424 |
insula | +0.415 |
mt | +0.414 |
Neg logit contributions | |
ees | -0.422 |
REE | -0.356 |
lust | -0.345 |
yip | -0.345 |
ealous | -0.344 |
Token | parties |
Token ID | 4671 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
afort | +8.023 |
nels | +6.615 |
arently | +6.410 |
mt | +6.315 |
insula | +6.183 |
Neg logit contributions | |
ees | -6.308 |
REE | -5.419 |
lust | -5.282 |
yip | -5.276 |
ealous | -5.257 |
Token | – |
Token ID | 784 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
afort | +1.988 |
nels | +1.622 |
arently | +1.577 |
insula | +1.543 |
mt | +1.542 |
Neg logit contributions | |
ees | -1.609 |
REE | -1.364 |
yip | -1.324 |
lust | -1.322 |
ealous | -1.318 |
Token | Wayne |
Token ID | 13329 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
afort | +2.246 |
nels | +1.830 |
arently | +1.785 |
insula | +1.744 |
mt | +1.742 |
Neg logit contributions | |
ees | -1.790 |
REE | -1.512 |
lust | -1.466 |
yip | -1.464 |
ealous | -1.462 |
Token | Mad |
Token ID | 4627 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
afort | +8.009 |
nels | +6.556 |
mt | +6.235 |
arently | +6.202 |
insula | +6.011 |
Neg logit contributions | |
ees | -6.254 |
REE | -5.437 |
lust | -5.262 |
yip | -5.230 |
ealous | -5.184 |
Token | sen |
Token ID | 6248 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
afort | +2.414 |
nels | +1.961 |
arently | +1.899 |
mt | +1.862 |
insula | +1.859 |
Neg logit contributions | |
ees | -2.052 |
REE | -1.759 |
yip | -1.702 |
lust | -1.698 |
ealous | -1.695 |
Token | " |
Token ID | 1 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
afort | +0.526 |
nels | +0.423 |
arently | +0.412 |
insula | +0.404 |
mt | +0.399 |
Neg logit contributions | |
ees | -0.457 |
REE | -0.391 |
lust | -0.378 |
ealous | -0.376 |
sum | -0.374 |
Token | Classic |
Token ID | 39914 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
afort | +1.232 |
nels | +0.993 |
arently | +0.966 |
insula | +0.945 |
mt | +0.942 |
Neg logit contributions | |
ees | -1.094 |
REE | -0.934 |
lust | -0.907 |
yip | -0.906 |
ealous | -0.904 |
Token | pizza |
Token ID | 14256 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
afort | +2.410 |
nels | +1.972 |
arently | +1.908 |
mt | +1.873 |
insula | +1.859 |
Neg logit contributions | |
ees | -1.977 |
REE | -1.686 |
yip | -1.646 |
ealous | -1.637 |
lust | -1.631 |
Token | party |
Token ID | 2151 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
afort | +4.526 |
nels | +3.708 |
arently | +3.620 |
mt | +3.480 |
insula | +3.479 |
Neg logit contributions | |
ees | -3.724 |
REE | -3.203 |
yip | -3.141 |
hovah | -3.136 |
ealous | -3.106 |
Token | ," |
Token ID | 553 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
afort | +1.426 |
nels | +1.166 |
arently | +1.132 |
mt | +1.107 |
insula | +1.107 |
Neg logit contributions | |
ees | -1.155 |
REE | -0.981 |
yip | -0.953 |
lust | -0.948 |
ealous | -0.948 |
Token | Glenn |
Token ID | 17551 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
afort | +0.147 |
nels | +0.114 |
arently | +0.110 |
insula | +0.108 |
mt | +0.107 |
Neg logit contributions | |
ees | -0.169 |
REE | -0.147 |
lust | -0.143 |
yip | -0.143 |
sum | -0.143 |
Token | said |
Token ID | 531 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
afort | +6.634 |
nels | +5.207 |
arently | +5.005 |
mt | +4.942 |
insula | +4.688 |
Neg logit contributions | |
ees | -7.410 |
REE | -6.719 |
yip | -6.643 |
lust | -6.593 |
hovah | -6.575 |
Token | Friday |
Token ID | 3217 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
afort | +2.180 |
nels | +1.757 |
arently | +1.707 |
mt | +1.663 |
insula | +1.663 |
Neg logit contributions | |
ees | -1.974 |
REE | -1.698 |
yip | -1.656 |
lust | -1.644 |
ealous | -1.641 |
Token | , |
Token ID | 11 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
afort | +2.051 |
nels | +1.664 |
arently | +1.619 |
mt | +1.581 |
insula | +1.579 |
Neg logit contributions | |
ees | -1.731 |
REE | -1.476 |
yip | -1.438 |
lust | -1.428 |
ealous | -1.425 |
Token | after |
Token ID | 706 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
afort | +0.681 |
nels | +0.555 |
arently | +0.541 |
insula | +0.532 |
mt | +0.528 |
Neg logit contributions | |
ees | -0.538 |
REE | -0.452 |
sum | -0.442 |
lust | -0.439 |
ealous | -0.436 |
Token | being |
Token ID | 852 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
afort | +1.126 |
nels | +0.919 |
arently | +0.896 |
insula | +0.876 |
mt | +0.875 |
Neg logit contributions | |
ees | -0.893 |
REE | -0.756 |
yip | -0.734 |
lust | -0.732 |
ealous | -0.732 |
Token | Donald |
Token ID | 3759 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
afort | +2.220 |
nels | +1.788 |
arently | +1.760 |
mt | +1.720 |
insula | +1.712 |
Neg logit contributions | |
ees | -1.861 |
REE | -1.579 |
yip | -1.547 |
ealous | -1.537 |
lust | -1.536 |
Token | J |
Token ID | 449 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
afort | +4.037 |
nels | +3.310 |
arently | +3.199 |
mt | +3.160 |
insula | +3.137 |
Neg logit contributions | |
ees | -3.072 |
REE | -2.566 |
yip | -2.522 |
lust | -2.495 |
ealous | -2.481 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ees | +3.174 |
ealous | +2.652 |
REE | +2.599 |
lust | +2.517 |
sum | +2.515 |
Neg logit contributions | |
afort | -4.514 |
arently | -3.755 |
nels | -3.742 |
insula | -3.721 |
mt | -3.522 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
ees | +0.093 |
REE | +0.081 |
ealous | +0.078 |
lust | +0.078 |
sum | +0.077 |
Neg logit contributions | |
afort | -0.108 |
nels | -0.087 |
arently | -0.086 |
insula | -0.085 |
mt | -0.081 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
afort | +4.416 |
nels | +3.572 |
arently | +3.465 |
mt | +3.386 |
insula | +3.379 |
Neg logit contributions | |
ees | -3.831 |
REE | -3.254 |
yip | -3.188 |
ealous | -3.164 |
lust | -3.163 |
Token | realDonaldTrump |
Token ID | 28024 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
afort | +1.375 |
nels | +0.894 |
arently | +0.843 |
insula | +0.801 |
mt | +0.789 |
Neg logit contributions | |
ees | -3.293 |
REE | -2.970 |
lust | -2.917 |
yip | -2.916 |
ealous | -2.912 |
Token | ) |
Token ID | 8 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
afort | +6.001 |
nels | +4.643 |
mt | +4.309 |
arently | +4.238 |
insula | +4.003 |
Neg logit contributions | |
ees | -8.420 |
hovah | -7.802 |
glim | -7.786 |
yip | -7.680 |
citiz | -7.585 |
Token | June |
Token ID | 2795 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
afort | +1.683 |
nels | +1.330 |
arently | +1.292 |
insula | +1.264 |
mt | +1.254 |
Neg logit contributions | |
ees | -1.732 |
REE | -1.497 |
lust | -1.459 |
sum | -1.454 |
yip | -1.452 |
Token | 3 |
Token ID | 513 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
afort | +3.328 |
nels | +2.668 |
arently | +2.562 |
mt | +2.550 |
insula | +2.481 |
Neg logit contributions | |
ees | -3.289 |
REE | -2.827 |
yip | -2.822 |
hovah | -2.797 |
ealous | -2.767 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ees | +0.549 |
REE | +0.458 |
lust | +0.449 |
ealous | +0.439 |
sum | +0.438 |
Neg logit contributions | |
afort | -0.789 |
arently | -0.643 |
nels | -0.643 |
insula | -0.640 |
mt | -0.608 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
afort | +0.552 |
nels | +0.450 |
arently | +0.439 |
insula | +0.430 |
mt | +0.428 |
Neg logit contributions | |
ees | -0.448 |
REE | -0.380 |
sum | -0.367 |
lust | -0.367 |
ealous | -0.365 |
Token | on |
Token ID | 319 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
afort | +0.304 |
nels | +0.250 |
arently | +0.244 |
insula | +0.238 |
mt | +0.238 |
Neg logit contributions | |
ees | -0.231 |
REE | -0.195 |
yip | -0.188 |
ealous | -0.188 |
lust | -0.188 |
Token | cloth |
Token ID | 16270 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
afort | +1.076 |
nels | +0.883 |
arently | +0.860 |
insula | +0.842 |
mt | +0.842 |
Neg logit contributions | |
ees | -0.813 |
REE | -0.685 |
yip | -0.664 |
ealous | -0.663 |
lust | -0.662 |
Token | and |
Token ID | 290 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
afort | +5.783 |
nels | +4.740 |
arently | +4.606 |
mt | +4.514 |
insula | +4.470 |
Neg logit contributions | |
ees | -4.706 |
REE | -4.067 |
yip | -3.977 |
ealous | -3.965 |
hovah | -3.939 |
Token | packed |
Token ID | 11856 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
afort | +0.292 |
nels | +0.240 |
arently | +0.234 |
insula | +0.229 |
mt | +0.228 |
Neg logit contributions | |
ees | -0.217 |
REE | -0.182 |
lust | -0.176 |
yip | -0.176 |
ealous | -0.175 |
Token | in |
Token ID | 287 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
afort | +0.126 |
nels | +0.104 |
arently | +0.101 |
insula | +0.100 |
mt | +0.099 |
Neg logit contributions | |
ees | -0.092 |
REE | -0.077 |
sum | -0.075 |
lust | -0.075 |
yip | -0.074 |
Token | foam |
Token ID | 19828 |
Feature activation | -8.60e+00 |
Pos logit contributions | |
afort | +0.560 |
nels | +0.455 |
arently | +0.443 |
insula | +0.434 |
mt | +0.433 |
Neg logit contributions | |
ees | -0.457 |
REE | -0.387 |
yip | -0.376 |
lust | -0.375 |
ealous | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
afort | +7.538 |
nels | +6.245 |
arently | +5.914 |
mt | +5.845 |
insula | +5.708 |
Neg logit contributions | |
ees | -6.648 |
REE | -5.879 |
ealous | -5.741 |
yip | -5.736 |
hovah | -5.642 |
Token | the |
Token ID | 262 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
afort | +0.635 |
nels | +0.513 |
arently | +0.500 |
insula | +0.489 |
mt | +0.487 |
Neg logit contributions | |
ees | -0.548 |
REE | -0.467 |
lust | -0.453 |
yip | -0.453 |
ealous | -0.452 |
Token | world |
Token ID | 995 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
afort | +0.669 |
nels | +0.547 |
arently | +0.533 |
insula | +0.522 |
mt | +0.521 |
Neg logit contributions | |
ees | -0.522 |
REE | -0.440 |
yip | -0.426 |
lust | -0.426 |
ealous | -0.425 |
Token | 's |
Token ID | 338 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ees | +0.239 |
REE | +0.204 |
ealous | +0.198 |
yip | +0.198 |
hovah | +0.197 |
Neg logit contributions | |
afort | -0.290 |
nels | -0.236 |
arently | -0.232 |
mt | -0.226 |
insula | -0.224 |
Token | most |
Token ID | 749 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ees | +0.691 |
REE | +0.535 |
sum | +0.511 |
lust | +0.509 |
yip | +0.506 |
Neg logit contributions | |
afort | -1.591 |
nels | -1.358 |
arently | -1.328 |
insula | -1.311 |
mt | -1.302 |
Token | , |
Token ID | 11 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
afort | +0.098 |
nels | +0.080 |
arently | +0.078 |
insula | +0.077 |
mt | +0.076 |
Neg logit contributions | |
ees | -0.078 |
REE | -0.065 |
sum | -0.063 |
lust | -0.063 |
yip | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
afort | +0.659 |
nels | +0.538 |
arently | +0.525 |
insula | +0.514 |
mt | +0.513 |
Neg logit contributions | |
ees | -0.513 |
REE | -0.433 |
lust | -0.419 |
yip | -0.419 |
ealous | -0.418 |
Token | foam |
Token ID | 19828 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
afort | +0.533 |
nels | +0.435 |
arently | +0.424 |
insula | +0.415 |
mt | +0.414 |
Neg logit contributions | |
ees | -0.422 |
REE | -0.356 |
lust | -0.345 |
yip | -0.345 |
ealous | -0.344 |
Token | parties |
Token ID | 4671 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
afort | +8.023 |
nels | +6.615 |
arently | +6.410 |
mt | +6.315 |
insula | +6.183 |
Neg logit contributions | |
ees | -6.308 |
REE | -5.419 |
lust | -5.282 |
yip | -5.276 |
ealous | -5.257 |
Token | – |
Token ID | 784 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
afort | +1.988 |
nels | +1.622 |
arently | +1.577 |
insula | +1.543 |
mt | +1.542 |
Neg logit contributions | |
ees | -1.609 |
REE | -1.364 |
yip | -1.324 |
lust | -1.322 |
ealous | -1.318 |
Token | Wayne |
Token ID | 13329 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
afort | +2.246 |
nels | +1.830 |
arently | +1.785 |
insula | +1.744 |
mt | +1.742 |
Neg logit contributions | |
ees | -1.790 |
REE | -1.512 |
lust | -1.466 |
yip | -1.464 |
ealous | -1.462 |
Token | Mad |
Token ID | 4627 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
afort | +8.009 |
nels | +6.556 |
mt | +6.235 |
arently | +6.202 |
insula | +6.011 |
Neg logit contributions | |
ees | -6.254 |
REE | -5.437 |
lust | -5.262 |
yip | -5.230 |
ealous | -5.184 |
Token | sen |
Token ID | 6248 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
afort | +2.414 |
nels | +1.961 |
arently | +1.899 |
mt | +1.862 |
insula | +1.859 |
Neg logit contributions | |
ees | -2.052 |
REE | -1.759 |
yip | -1.702 |
lust | -1.698 |
ealous | -1.695 |
Token | Report |
Token ID | 6358 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
afort | +1.244 |
nels | +1.012 |
arently | +0.985 |
insula | +0.965 |
mt | +0.962 |
Neg logit contributions | |
ees | -1.013 |
REE | -0.858 |
lust | -0.832 |
yip | -0.832 |
ealous | -0.829 |
Token | https |
Token ID | 3740 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ees | +0.796 |
REE | +0.673 |
sum | +0.651 |
lust | +0.650 |
yip | +0.647 |
Neg logit contributions | |
afort | -0.992 |
nels | -0.807 |
arently | -0.786 |
insula | -0.774 |
mt | -0.768 |
Token | :// |
Token ID | 1378 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
afort | +2.334 |
nels | +1.593 |
arently | +1.495 |
mt | +1.440 |
insula | +1.421 |
Neg logit contributions | |
ees | -4.965 |
REE | -4.462 |
yip | -4.407 |
hovah | -4.379 |
lust | -4.372 |
Token | big |
Token ID | 14261 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
afort | +0.516 |
nels | +0.401 |
arently | +0.388 |
insula | +0.378 |
mt | +0.374 |
Neg logit contributions | |
ees | -0.610 |
REE | -0.532 |
lust | -0.521 |
yip | -0.519 |
sum | -0.518 |
Token | ger |
Token ID | 1362 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
afort | +1.853 |
nels | +1.527 |
arently | +1.479 |
mt | +1.459 |
insula | +1.430 |
Neg logit contributions | |
ees | -1.406 |
REE | -1.180 |
yip | -1.167 |
hovah | -1.161 |
ealous | -1.158 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
afort | +0.462 |
nels | +0.378 |
arently | +0.368 |
insula | +0.360 |
mt | +0.360 |
Neg logit contributions | |
ees | -0.352 |
REE | -0.297 |
yip | -0.288 |
ealous | -0.287 |
lust | -0.287 |
Token | better |
Token ID | 1365 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
afort | +0.141 |
nels | +0.114 |
arently | +0.111 |
insula | +0.109 |
mt | +0.108 |
Neg logit contributions | |
ees | -0.124 |
REE | -0.106 |
sum | -0.103 |
lust | -0.103 |
yip | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
afort | +0.370 |
nels | +0.306 |
arently | +0.299 |
mt | +0.292 |
insula | +0.291 |
Neg logit contributions | |
ees | -0.261 |
REE | -0.218 |
yip | -0.213 |
lust | -0.211 |
ealous | -0.211 |
Token | gre |
Token ID | 10536 |
Feature activation | -8.41e+00 |
Pos logit contributions | |
ees | +0.005 |
REE | +0.005 |
lust | +0.004 |
sum | +0.004 |
yip | +0.004 |
Neg logit contributions | |
afort | -0.006 |
nels | -0.005 |
arently | -0.005 |
insula | -0.005 |
mt | -0.005 |
Token | ener |
Token ID | 877 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
afort | +6.945 |
arently | +5.527 |
nels | +5.509 |
mt | +5.379 |
insula | +5.055 |
Neg logit contributions | |
ees | -6.947 |
REE | -6.228 |
glim | -6.076 |
yip | -6.074 |
diagnosis | -6.046 |
Token | ". |
Token ID | 1911 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
afort | +2.740 |
nels | +2.258 |
arently | +2.204 |
mt | +2.158 |
insula | +2.142 |
Neg logit contributions | |
ees | -2.045 |
REE | -1.720 |
yip | -1.682 |
ealous | -1.673 |
lust | -1.667 |
Token |
|
Token ID | 198 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
afort | +0.735 |
nels | +0.608 |
arently | +0.593 |
mt | +0.581 |
insula | +0.581 |
Neg logit contributions | |
ees | -0.525 |
REE | -0.443 |
yip | -0.433 |
lust | -0.427 |
sum | -0.427 |
Token |
|
Token ID | 198 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
afort | +0.584 |
nels | +0.483 |
arently | +0.476 |
insula | +0.469 |
mt | +0.459 |
Neg logit contributions | |
ees | -0.365 |
REE | -0.299 |
lust | -0.291 |
sum | -0.287 |
ealous | -0.286 |
Token | The |
Token ID | 464 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
afort | +0.635 |
nels | +0.506 |
arently | +0.494 |
insula | +0.483 |
mt | +0.476 |
Neg logit contributions | |
ees | -0.596 |
REE | -0.513 |
lust | -0.497 |
ealous | -0.493 |
sum | -0.490 |
Token | . |
Token ID | 13 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
ees | +0.373 |
REE | +0.315 |
lust | +0.308 |
sum | +0.308 |
ealous | +0.304 |
Neg logit contributions | |
afort | -0.447 |
nels | -0.360 |
arently | -0.351 |
insula | -0.345 |
mt | -0.342 |
Token | View |
Token ID | 3582 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
afort | +0.718 |
nels | +0.588 |
arently | +0.574 |
insula | +0.562 |
mt | +0.561 |
Neg logit contributions | |
ees | -0.545 |
REE | -0.458 |
lust | -0.444 |
yip | -0.444 |
ealous | -0.442 |
Token | Full |
Token ID | 6462 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
afort | +0.144 |
nels | +0.117 |
arently | +0.114 |
insula | +0.112 |
mt | +0.112 |
Neg logit contributions | |
ees | -0.112 |
REE | -0.095 |
lust | -0.092 |
yip | -0.091 |
sum | -0.091 |
Token | Caption |
Token ID | 11260 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ees | +0.113 |
REE | +0.094 |
lust | +0.091 |
sum | +0.091 |
yip | +0.091 |
Neg logit contributions | |
afort | -0.154 |
nels | -0.127 |
arently | -0.124 |
insula | -0.121 |
mt | -0.120 |
Token | Adam |
Token ID | 7244 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
afort | +2.035 |
nels | +1.648 |
arently | +1.603 |
insula | +1.567 |
mt | +1.567 |
Neg logit contributions | |
ees | -1.725 |
REE | -1.460 |
lust | -1.421 |
sum | -1.419 |
ealous | -1.415 |
Token | Glenn |
Token ID | 17551 |
Feature activation | -8.41e+00 |
Pos logit contributions | |
afort | +0.045 |
nels | +0.037 |
arently | +0.036 |
insula | +0.036 |
mt | +0.035 |
Neg logit contributions | |
ees | -0.034 |
REE | -0.029 |
lust | -0.028 |
yip | -0.028 |
ealous | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
afort | +7.749 |
nels | +6.318 |
arently | +6.111 |
mt | +6.058 |
insula | +5.985 |
Neg logit contributions | |
ees | -6.112 |
yip | -5.334 |
REE | -5.266 |
lust | -5.150 |
hovah | -5.092 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
afort | +0.153 |
nels | +0.127 |
arently | +0.126 |
insula | +0.124 |
mt | +0.120 |
Neg logit contributions | |
ees | -0.093 |
REE | -0.076 |
lust | -0.074 |
sum | -0.072 |
ealous | -0.072 |
Token | C |
Token ID | 34 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
afort | +0.278 |
nels | +0.221 |
arently | +0.215 |
insula | +0.209 |
mt | +0.206 |
Neg logit contributions | |
ees | -0.279 |
REE | -0.242 |
lust | -0.235 |
ealous | -0.233 |
sum | -0.233 |
Token | OOK |
Token ID | 15308 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
afort | +0.459 |
nels | +0.371 |
arently | +0.360 |
insula | +0.352 |
mt | +0.350 |
Neg logit contributions | |
ees | -0.406 |
REE | -0.347 |
lust | -0.336 |
ealous | -0.336 |
yip | -0.335 |
Token | COUNTY |
Token ID | 41012 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ees | +1.035 |
REE | +0.862 |
lust | +0.822 |
sum | +0.819 |
ealous | +0.818 |
Neg logit contributions | |
afort | -1.593 |
nels | -1.329 |
arently | -1.293 |
insula | -1.267 |
mt | -1.260 |
Token | D |
Token ID | 360 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
afort | +1.883 |
nels | +1.536 |
arently | +1.484 |
insula | +1.463 |
mt | +1.462 |
Neg logit contributions | |
ees | -1.481 |
REE | -1.256 |
yip | -1.221 |
ealous | -1.213 |
lust | -1.212 |
Token | ool |
Token ID | 970 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
afort | +0.650 |
nels | +0.523 |
arently | +0.510 |
insula | +0.500 |
mt | +0.499 |
Neg logit contributions | |
ees | -0.563 |
REE | -0.481 |
yip | -0.468 |
lust | -0.466 |
sum | -0.465 |
Token | ittle |
Token ID | 1206 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
afort | +3.357 |
nels | +2.812 |
arently | +2.734 |
mt | +2.696 |
insula | +2.677 |
Neg logit contributions | |
ees | -1.862 |
REE | -1.545 |
yip | -1.481 |
hovah | -1.460 |
glim | -1.458 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ees | +0.983 |
REE | +0.815 |
sum | +0.788 |
lust | +0.786 |
ealous | +0.783 |
Neg logit contributions | |
afort | -1.449 |
nels | -1.199 |
arently | -1.173 |
insula | -1.153 |
mt | -1.142 |
Token | Kevin |
Token ID | 7939 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
afort | +0.126 |
nels | +0.104 |
arently | +0.101 |
insula | +0.099 |
mt | +0.099 |
Neg logit contributions | |
ees | -0.091 |
REE | -0.076 |
lust | -0.073 |
yip | -0.073 |
ealous | -0.073 |
Token | Donovan |
Token ID | 31565 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
afort | +2.585 |
nels | +2.095 |
arently | +2.026 |
mt | +2.005 |
insula | +1.989 |
Neg logit contributions | |
ees | -2.153 |
REE | -1.830 |
yip | -1.814 |
ealous | -1.789 |
lust | -1.780 |
Token | , |
Token ID | 11 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
afort | +7.833 |
nels | +6.280 |
arently | +6.094 |
mt | +6.041 |
insula | +5.887 |
Neg logit contributions | |
ees | -6.198 |
REE | -5.356 |
yip | -5.230 |
ealous | -5.111 |
hovah | -5.100 |
Token | of |
Token ID | 286 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
afort | +0.640 |
nels | +0.523 |
arently | +0.509 |
insula | +0.499 |
mt | +0.497 |
Neg logit contributions | |
ees | -0.503 |
REE | -0.424 |
lust | -0.411 |
yip | -0.410 |
sum | -0.409 |
Token | the |
Token ID | 262 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
afort | +2.552 |
nels | +2.065 |
arently | +2.013 |
insula | +1.973 |
mt | +1.969 |
Neg logit contributions | |
ees | -2.124 |
REE | -1.806 |
yip | -1.764 |
ealous | -1.747 |
lust | -1.743 |
Token | Toronto |
Token ID | 6586 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
afort | +0.695 |
nels | +0.567 |
arently | +0.552 |
insula | +0.541 |
mt | +0.538 |
Neg logit contributions | |
ees | -0.553 |
REE | -0.467 |
lust | -0.454 |
sum | -0.452 |
yip | -0.451 |
Token | Star |
Token ID | 2907 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
afort | +1.247 |
nels | +1.014 |
arently | +0.987 |
insula | +0.965 |
mt | +0.962 |
Neg logit contributions | |
ees | -1.035 |
REE | -0.877 |
lust | -0.852 |
ealous | -0.849 |
sum | -0.849 |
Token | overly |
Token ID | 17698 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
afort | +0.437 |
nels | +0.355 |
arently | +0.346 |
insula | +0.339 |
mt | +0.338 |
Neg logit contributions | |
ees | -0.355 |
REE | -0.300 |
lust | -0.291 |
sum | -0.291 |
ealous | -0.290 |
Token | precise |
Token ID | 7141 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
afort | +0.495 |
nels | +0.407 |
arently | +0.397 |
insula | +0.389 |
mt | +0.388 |
Neg logit contributions | |
ees | -0.362 |
REE | -0.303 |
yip | -0.294 |
lust | -0.293 |
ealous | -0.292 |
Token | render |
Token ID | 8543 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ees | +0.310 |
REE | +0.262 |
sum | +0.255 |
lust | +0.255 |
ealous | +0.253 |
Neg logit contributions | |
afort | -0.381 |
nels | -0.308 |
arently | -0.302 |
insula | -0.296 |
mt | -0.294 |
Token | ings |
Token ID | 654 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
afort | +0.012 |
nels | +0.010 |
arently | +0.010 |
insula | +0.010 |
mt | +0.010 |
Neg logit contributions | |
ees | -0.006 |
REE | -0.005 |
yip | -0.004 |
lust | -0.004 |
ealous | -0.004 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ees | +0.490 |
REE | +0.412 |
lust | +0.402 |
sum | +0.401 |
ealous | +0.399 |
Neg logit contributions | |
afort | -0.617 |
nels | -0.502 |
arently | -0.489 |
insula | -0.481 |
mt | -0.478 |
Token | match |
Token ID | 2872 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
ees | +1.298 |
REE | +1.092 |
lust | +1.058 |
yip | +1.057 |
ealous | +1.054 |
Neg logit contributions | |
afort | -1.686 |
nels | -1.378 |
arently | -1.344 |
insula | -1.318 |
mt | -1.313 |
Token | the |
Token ID | 262 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ees | +3.792 |
sum | +3.081 |
REE | +3.071 |
ealous | +3.009 |
lust | +2.997 |
Neg logit contributions | |
afort | -5.077 |
nels | -4.175 |
arently | -4.055 |
insula | -4.003 |
mt | -3.982 |
Token | cold |
Token ID | 4692 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ees | +0.420 |
REE | +0.353 |
sum | +0.347 |
lust | +0.344 |
ealous | +0.341 |
Neg logit contributions | |
afort | -0.535 |
nels | -0.435 |
arently | -0.426 |
insula | -0.417 |
mt | -0.415 |
Token | tension |
Token ID | 12097 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
afort | +1.241 |
nels | +1.023 |
arently | +0.995 |
insula | +0.979 |
mt | +0.975 |
Neg logit contributions | |
ees | -0.899 |
REE | -0.754 |
yip | -0.730 |
ealous | -0.726 |
lust | -0.725 |
Token | in |
Token ID | 287 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
afort | +0.316 |
nels | +0.259 |
arently | +0.253 |
insula | +0.248 |
mt | +0.247 |
Neg logit contributions | |
ees | -0.239 |
REE | -0.201 |
lust | -0.195 |
yip | -0.194 |
sum | -0.194 |
Token | Moore |
Token ID | 8877 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
afort | +0.167 |
nels | +0.135 |
arently | +0.132 |
insula | +0.129 |
mt | +0.128 |
Neg logit contributions | |
ees | -0.144 |
REE | -0.122 |
sum | -0.119 |
lust | -0.119 |
ealous | -0.118 |
Token | laboratories |
Token ID | 35650 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
afort | +4.740 |
nels | +3.993 |
arently | +3.863 |
mt | +3.842 |
insula | +3.769 |
Neg logit contributions | |
ees | -2.898 |
yip | -2.415 |
REE | -2.406 |
hovah | -2.356 |
ealous | -2.329 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ees | +3.136 |
sum | +2.585 |
REE | +2.565 |
diagnosis | +2.526 |
lust | +2.496 |
Neg logit contributions | |
afort | -4.410 |
nels | -3.618 |
arently | -3.579 |
insula | -3.494 |
mt | -3.408 |
Token | Two |
Token ID | 4930 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ees | +0.113 |
REE | +0.094 |
lust | +0.091 |
ealous | +0.091 |
sum | +0.090 |
Neg logit contributions | |
afort | -0.160 |
nels | -0.132 |
arently | -0.129 |
insula | -0.127 |
mt | -0.126 |
Token | types |
Token ID | 3858 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
afort | +0.118 |
nels | +0.096 |
arently | +0.094 |
insula | +0.092 |
mt | +0.091 |
Neg logit contributions | |
ees | -0.091 |
REE | -0.076 |
sum | -0.074 |
lust | -0.074 |
ealous | -0.074 |
Token | of |
Token ID | 286 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
afort | +1.723 |
nels | +1.383 |
arently | +1.327 |
mt | +1.305 |
insula | +1.292 |
Neg logit contributions | |
ees | -1.685 |
REE | -1.457 |
yip | -1.423 |
ealous | -1.412 |
lust | -1.404 |
Token | antibody |
Token ID | 35757 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
afort | +1.046 |
nels | +0.872 |
arently | +0.853 |
insula | +0.839 |
mt | +0.834 |
Neg logit contributions | |
ees | -0.644 |
REE | -0.528 |
lust | -0.508 |
sum | -0.507 |
yip | -0.506 |
Token | tests |
Token ID | 5254 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
ees | +3.525 |
REE | +2.866 |
sum | +2.856 |
diagnosis | +2.854 |
lust | +2.778 |
Neg logit contributions | |
afort | -5.047 |
nels | -4.195 |
arently | -4.144 |
insula | -4.094 |
mt | -3.960 |
Token | for |
Token ID | 329 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
ees | +3.973 |
sum | +3.280 |
REE | +3.259 |
diagnosis | +3.207 |
lust | +3.184 |
Neg logit contributions | |
afort | -5.303 |
nels | -4.362 |
arently | -4.281 |
insula | -4.218 |
mt | -4.127 |
Token | infections |
Token ID | 16079 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
afort | +1.009 |
nels | +0.845 |
arently | +0.826 |
insula | +0.812 |
mt | +0.810 |
Neg logit contributions | |
ees | -0.590 |
REE | -0.480 |
lust | -0.461 |
yip | -0.461 |
ealous | -0.459 |
Token | older |
Token ID | 4697 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ees | +1.473 |
REE | +1.229 |
sum | +1.205 |
lust | +1.197 |
ealous | +1.192 |
Neg logit contributions | |
afort | -1.890 |
nels | -1.547 |
arently | -1.508 |
insula | -1.483 |
mt | -1.466 |
Token | than |
Token ID | 621 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ees | +0.979 |
REE | +0.824 |
lust | +0.798 |
yip | +0.796 |
ealous | +0.795 |
Neg logit contributions | |
afort | -1.281 |
nels | -1.048 |
arently | -1.022 |
insula | -1.003 |
mt | -0.998 |
Token | have |
Token ID | 423 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
ees | +0.555 |
REE | +0.451 |
lust | +0.433 |
yip | +0.433 |
ealous | +0.432 |
Neg logit contributions | |
afort | -0.956 |
nels | -0.801 |
arently | -0.783 |
insula | -0.770 |
mt | -0.767 |
Token | a |
Token ID | 257 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
ees | +2.044 |
REE | +1.648 |
sum | +1.624 |
lust | +1.598 |
yip | +1.566 |
Neg logit contributions | |
afort | -3.294 |
nels | -2.723 |
arently | -2.665 |
insula | -2.646 |
mt | -2.620 |
Token | dense |
Token ID | 15715 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
ees | +0.771 |
REE | +0.655 |
lust | +0.635 |
yip | +0.635 |
ealous | +0.633 |
Neg logit contributions | |
afort | -0.923 |
nels | -0.748 |
arently | -0.728 |
insula | -0.713 |
mt | -0.711 |
Token | composition |
Token ID | 11742 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ees | +2.832 |
REE | +2.417 |
sum | +2.396 |
lust | +2.335 |
diagnosis | +2.300 |
Neg logit contributions | |
afort | -3.358 |
nels | -2.684 |
arently | -2.642 |
insula | -2.597 |
mt | -2.587 |
Token | of |
Token ID | 286 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ees | +0.321 |
REE | +0.270 |
lust | +0.262 |
sum | +0.261 |
yip | +0.261 |
Neg logit contributions | |
afort | -0.413 |
nels | -0.336 |
arently | -0.328 |
insula | -0.322 |
mt | -0.320 |
Token | rocks |
Token ID | 12586 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
afort | +0.329 |
nels | +0.270 |
arently | +0.264 |
insula | +0.259 |
mt | +0.258 |
Neg logit contributions | |
ees | -0.238 |
REE | -0.199 |
lust | -0.192 |
yip | -0.192 |
sum | -0.192 |
Token | and |
Token ID | 290 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ees | +3.653 |
sum | +2.978 |
REE | +2.961 |
lust | +2.878 |
ealous | +2.827 |
Neg logit contributions | |
afort | -5.620 |
nels | -4.597 |
arently | -4.519 |
insula | -4.516 |
mt | -4.418 |
Token | other |
Token ID | 584 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ees | +0.422 |
REE | +0.353 |
lust | +0.342 |
sum | +0.342 |
yip | +0.340 |
Neg logit contributions | |
afort | -0.564 |
nels | -0.461 |
arently | -0.450 |
insula | -0.443 |
mt | -0.440 |
Token | sol |
Token ID | 1540 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
afort | +3.104 |
nels | +2.549 |
arently | +2.477 |
mt | +2.429 |
insula | +2.400 |
Neg logit contributions | |
ees | -2.482 |
REE | -2.110 |
yip | -2.087 |
ealous | -2.061 |
lust | -2.051 |
Token | ids |
Token ID | 2340 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
afort | +2.616 |
nels | +2.213 |
arently | +2.143 |
mt | +2.116 |
insula | +2.111 |
Neg logit contributions | |
ees | -1.446 |
REE | -1.196 |
yip | -1.157 |
lust | -1.129 |
hovah | -1.128 |
Token | . |
Token ID | 13 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ees | +2.629 |
REE | +2.172 |
sum | +2.151 |
lust | +2.097 |
ealous | +2.062 |
Neg logit contributions | |
afort | -3.640 |
nels | -2.949 |
arently | -2.904 |
insula | -2.885 |
mt | -2.829 |
Token | like |
Token ID | 588 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
afort | +0.307 |
nels | +0.250 |
arently | +0.244 |
insula | +0.239 |
mt | +0.238 |
Neg logit contributions | |
ees | -0.246 |
REE | -0.208 |
yip | -0.202 |
lust | -0.201 |
ealous | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
ees | +0.874 |
REE | +0.738 |
sum | +0.725 |
diagnosis | +0.716 |
yip | +0.715 |
Neg logit contributions | |
afort | -1.091 |
nels | -0.889 |
arently | -0.864 |
insula | -0.856 |
mt | -0.839 |
Token | dead |
Token ID | 2636 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ees | +0.554 |
REE | +0.464 |
sum | +0.454 |
lust | +0.448 |
yip | +0.447 |
Neg logit contributions | |
afort | -0.773 |
nels | -0.639 |
arently | -0.619 |
insula | -0.612 |
mt | -0.605 |
Token | lier |
Token ID | 2505 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ees | +1.097 |
REE | +0.929 |
lust | +0.910 |
sum | +0.909 |
diagnosis | +0.891 |
Neg logit contributions | |
afort | -1.391 |
nels | -1.127 |
arently | -1.099 |
insula | -1.083 |
mt | -1.069 |
Token | bird |
Token ID | 6512 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
ees | +1.877 |
sum | +1.556 |
REE | +1.556 |
diagnosis | +1.545 |
lust | +1.514 |
Neg logit contributions | |
afort | -2.673 |
nels | -2.200 |
arently | -2.143 |
insula | -2.120 |
mt | -2.078 |
Token | flu |
Token ID | 6562 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
ees | +0.548 |
REE | +0.441 |
lust | +0.429 |
sum | +0.427 |
yip | +0.425 |
Neg logit contributions | |
afort | -0.971 |
nels | -0.817 |
arently | -0.800 |
insula | -0.786 |
mt | -0.781 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ees | +4.075 |
diagnosis | +3.400 |
sum | +3.357 |
REE | +3.350 |
lust | +3.262 |
Neg logit contributions | |
afort | -6.011 |
nels | -5.037 |
arently | -4.879 |
insula | -4.778 |
mt | -4.683 |
Token | " |
Token ID | 366 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ees | +0.203 |
REE | +0.170 |
lust | +0.164 |
sum | +0.163 |
ealous | +0.163 |
Neg logit contributions | |
afort | -0.283 |
nels | -0.232 |
arently | -0.227 |
insula | -0.223 |
mt | -0.221 |
Token | It |
Token ID | 1026 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ees | +0.131 |
REE | +0.112 |
lust | +0.109 |
ealous | +0.107 |
sum | +0.107 |
Neg logit contributions | |
afort | -0.157 |
nels | -0.127 |
arently | -0.124 |
insula | -0.122 |
mt | -0.119 |
Token | was |
Token ID | 373 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ees | +1.294 |
REE | +1.072 |
sum | +1.060 |
lust | +1.051 |
yip | +1.042 |
Neg logit contributions | |
afort | -1.670 |
nels | -1.361 |
arently | -1.330 |
insula | -1.317 |
mt | -1.299 |
Token | believed |
Token ID | 4762 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
afort | +1.153 |
nels | +0.938 |
arently | +0.914 |
insula | +0.896 |
mt | +0.893 |
Neg logit contributions | |
ees | -0.933 |
REE | -0.790 |
lust | -0.765 |
yip | -0.765 |
ealous | -0.763 |
Token | 11 |
Token ID | 1157 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
afort | +0.309 |
nels | +0.253 |
arently | +0.247 |
insula | +0.243 |
mt | +0.243 |
Neg logit contributions | |
ees | -0.222 |
REE | -0.188 |
yip | -0.182 |
ealous | -0.180 |
lust | -0.180 |
Token | : |
Token ID | 25 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
afort | +2.523 |
nels | +2.018 |
arently | +1.957 |
mt | +1.915 |
insula | +1.913 |
Neg logit contributions | |
ees | -2.414 |
REE | -2.079 |
yip | -2.019 |
lust | -2.018 |
ealous | -2.016 |
Token | File |
Token ID | 9220 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
afort | +0.449 |
nels | +0.368 |
arently | +0.359 |
insula | +0.352 |
mt | +0.349 |
Neg logit contributions | |
ees | -0.343 |
REE | -0.288 |
lust | -0.279 |
sum | -0.278 |
yip | -0.278 |
Token | photo |
Token ID | 4590 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
afort | +0.512 |
nels | +0.411 |
arently | +0.400 |
insula | +0.391 |
mt | +0.390 |
Neg logit contributions | |
ees | -0.472 |
REE | -0.404 |
lust | -0.393 |
yip | -0.392 |
ealous | -0.391 |
Token | by |
Token ID | 416 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
ees | +0.143 |
REE | +0.123 |
lust | +0.120 |
sum | +0.120 |
ealous | +0.120 |
Neg logit contributions | |
afort | -0.139 |
nels | -0.110 |
arently | -0.106 |
insula | -0.104 |
mt | -0.103 |
Token | J |
Token ID | 449 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
afort | +0.850 |
nels | +0.702 |
arently | +0.685 |
insula | +0.673 |
mt | +0.672 |
Neg logit contributions | |
ees | -0.588 |
REE | -0.490 |
yip | -0.474 |
lust | -0.473 |
ealous | -0.472 |
Token | iji |
Token ID | 20770 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
ees | +4.108 |
REE | +3.493 |
ealous | +3.397 |
lust | +3.318 |
yip | +3.292 |
Neg logit contributions | |
afort | -4.709 |
nels | -3.874 |
arently | -3.751 |
insula | -3.628 |
mt | -3.574 |
Token | Press |
Token ID | 4332 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ees | +0.428 |
REE | +0.351 |
lust | +0.339 |
sum | +0.338 |
ealous | +0.337 |
Neg logit contributions | |
afort | -0.685 |
nels | -0.571 |
arently | -0.558 |
insula | -0.548 |
mt | -0.546 |
Token | , |
Token ID | 11 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
afort | +3.653 |
nels | +2.942 |
arently | +2.859 |
insula | +2.805 |
mt | +2.796 |
Neg logit contributions | |
ees | -3.327 |
REE | -2.863 |
yip | -2.802 |
ealous | -2.786 |
lust | -2.776 |
Token | AFP |
Token ID | 8916 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
afort | +0.633 |
nels | +0.516 |
arently | +0.503 |
insula | +0.493 |
mt | +0.491 |
Neg logit contributions | |
ees | -0.504 |
REE | -0.426 |
lust | -0.413 |
yip | -0.413 |
sum | -0.412 |
Token | / |
Token ID | 14 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
afort | +1.987 |
nels | +1.605 |
arently | +1.566 |
insula | +1.536 |
mt | +1.531 |
Neg logit contributions | |
ees | -1.767 |
REE | -1.511 |
yip | -1.480 |
ealous | -1.471 |
lust | -1.463 |
Token | volatile |
Token ID | 22750 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
afort | +3.563 |
nels | +2.933 |
arently | +2.884 |
mt | +2.811 |
insula | +2.770 |
Neg logit contributions | |
ees | -2.652 |
REE | -2.230 |
yip | -2.221 |
hovah | -2.174 |
ealous | -2.144 |
Token | ) |
Token ID | 8 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
afort | +1.764 |
nels | +1.366 |
arently | +1.335 |
insula | +1.272 |
mt | +1.270 |
Neg logit contributions | |
ees | -2.205 |
REE | -1.936 |
yip | -1.902 |
lust | -1.887 |
ealous | -1.883 |
Token | one |
Token ID | 530 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
afort | +1.078 |
nels | +0.881 |
arently | +0.859 |
insula | +0.840 |
mt | +0.839 |
Neg logit contributions | |
ees | -0.849 |
REE | -0.719 |
yip | -0.701 |
lust | -0.696 |
ealous | -0.694 |
Token | , |
Token ID | 11 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
afort | +0.456 |
nels | +0.370 |
arently | +0.360 |
insula | +0.352 |
mt | +0.351 |
Neg logit contributions | |
ees | -0.385 |
REE | -0.327 |
lust | -0.318 |
yip | -0.317 |
ealous | -0.317 |
Token | especially |
Token ID | 2592 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
afort | +0.077 |
nels | +0.064 |
arently | +0.062 |
insula | +0.061 |
mt | +0.061 |
Neg logit contributions | |
ees | -0.051 |
REE | -0.042 |
lust | -0.040 |
sum | -0.040 |
yip | -0.040 |
Token | after |
Token ID | 706 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
afort | +1.647 |
nels | +1.358 |
arently | +1.325 |
insula | +1.296 |
mt | +1.294 |
Neg logit contributions | |
ees | -1.182 |
REE | -0.993 |
yip | -0.963 |
ealous | -0.957 |
lust | -0.955 |
Token | this |
Token ID | 428 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
afort | +0.375 |
nels | +0.306 |
arently | +0.298 |
insula | +0.292 |
mt | +0.291 |
Neg logit contributions | |
ees | -0.295 |
REE | -0.249 |
yip | -0.242 |
lust | -0.241 |
ealous | -0.240 |
Token | season |
Token ID | 1622 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
afort | +1.595 |
nels | +1.313 |
arently | +1.285 |
mt | +1.258 |
insula | +1.255 |
Neg logit contributions | |
ees | -1.186 |
REE | -1.003 |
yip | -0.981 |
lust | -0.964 |
ealous | -0.963 |
Token | 's |
Token ID | 338 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ees | +0.135 |
REE | +0.115 |
yip | +0.113 |
ealous | +0.112 |
lust | +0.111 |
Neg logit contributions | |
afort | -0.160 |
nels | -0.131 |
arently | -0.127 |
mt | -0.124 |
insula | -0.124 |
Token | Teen |
Token ID | 21432 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ees | +1.031 |
REE | +0.858 |
sum | +0.834 |
lust | +0.832 |
ealous | +0.828 |
Neg logit contributions | |
afort | -1.456 |
nels | -1.200 |
arently | -1.168 |
insula | -1.149 |
mt | -1.140 |
Token | Mom |
Token ID | 11254 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ees | +1.152 |
REE | +0.897 |
lust | +0.876 |
sum | +0.868 |
ealous | +0.864 |
Neg logit contributions | |
afort | -2.297 |
nels | -1.951 |
arently | -1.912 |
insula | -1.876 |
mt | -1.864 |
Token | there |
Token ID | 612 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
afort | +0.031 |
nels | +0.025 |
arently | +0.025 |
insula | +0.024 |
mt | +0.024 |
Neg logit contributions | |
ees | -0.022 |
REE | -0.019 |
lust | -0.018 |
sum | -0.018 |
ealous | -0.018 |
Token | were |
Token ID | 547 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
afort | +0.713 |
nels | +0.580 |
arently | +0.566 |
insula | +0.554 |
mt | +0.552 |
Neg logit contributions | |
ees | -0.574 |
REE | -0.486 |
lust | -0.471 |
yip | -0.470 |
ealous | -0.469 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
afort | +0.770 |
nels | +0.616 |
arently | +0.598 |
insula | +0.589 |
mt | +0.582 |
Neg logit contributions | |
ees | -0.706 |
REE | -0.604 |
sum | -0.589 |
lust | -0.587 |
yip | -0.584 |
Token | Nim |
Token ID | 27168 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
afort | +2.772 |
nels | +2.259 |
arently | +2.208 |
mt | +2.164 |
insula | +2.160 |
Neg logit contributions | |
ees | -2.211 |
REE | -1.869 |
yip | -1.821 |
lust | -1.814 |
ealous | -1.811 |
Token | itz |
Token ID | 4224 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ees | +3.944 |
lust | +3.151 |
REE | +3.108 |
oglu | +3.086 |
sum | +3.080 |
Neg logit contributions | |
afort | -4.495 |
nels | -3.538 |
insula | -3.498 |
arently | -3.471 |
llular | -3.346 |
Token | - |
Token ID | 12 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ees | +2.457 |
REE | +2.010 |
sum | +1.953 |
lust | +1.911 |
diagnosis | +1.886 |
Neg logit contributions | |
afort | -3.709 |
nels | -3.075 |
arently | -3.009 |
insula | -2.947 |
mt | -2.918 |
Token | class |
Token ID | 4871 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ees | +1.578 |
REE | +1.334 |
lust | +1.284 |
sum | +1.280 |
ealous | +1.270 |
Neg logit contributions | |
afort | -1.890 |
nels | -1.527 |
arently | -1.482 |
insula | -1.454 |
mt | -1.421 |
Token | carriers |
Token ID | 16651 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ees | +1.623 |
REE | +1.349 |
sum | +1.319 |
lust | +1.297 |
diagnosis | +1.284 |
Neg logit contributions | |
afort | -2.176 |
nels | -1.768 |
arently | -1.737 |
insula | -1.704 |
mt | -1.690 |
Token | in |
Token ID | 287 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ees | +0.240 |
REE | +0.200 |
sum | +0.194 |
lust | +0.194 |
ealous | +0.192 |
Neg logit contributions | |
afort | -0.323 |
nels | -0.265 |
arently | -0.258 |
insula | -0.253 |
mt | -0.252 |
Token | service |
Token ID | 2139 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
afort | +0.491 |
nels | +0.402 |
arently | +0.392 |
insula | +0.385 |
mt | +0.382 |
Neg logit contributions | |
ees | -0.377 |
REE | -0.316 |
sum | -0.307 |
lust | -0.307 |
yip | -0.304 |
Token | ( |
Token ID | 357 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
afort | +3.594 |
nels | +2.937 |
arently | +2.859 |
mt | +2.811 |
insula | +2.803 |
Neg logit contributions | |
ees | -2.815 |
REE | -2.409 |
yip | -2.346 |
ealous | -2.331 |
lust | -2.312 |
Token | Giant |
Token ID | 17384 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
afort | +0.067 |
nels | +0.055 |
arently | +0.054 |
insula | +0.053 |
mt | +0.053 |
Neg logit contributions | |
ees | -0.047 |
REE | -0.039 |
lust | -0.038 |
yip | -0.038 |
sum | -0.038 |
Token | Lie |
Token ID | 12060 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
afort | +0.340 |
nels | +0.277 |
arently | +0.270 |
insula | +0.265 |
mt | +0.264 |
Neg logit contributions | |
ees | -0.273 |
REE | -0.230 |
yip | -0.223 |
lust | -0.223 |
ealous | -0.223 |
Token | Factory |
Token ID | 19239 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ees | +6.002 |
REE | +4.995 |
lust | +4.991 |
diagnosis | +4.938 |
ealous | +4.938 |
Neg logit contributions | |
afort | -7.514 |
nels | -6.002 |
arently | -5.959 |
insula | -5.883 |
mt | -5.690 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
afort | +0.016 |
nels | +0.013 |
arently | +0.013 |
insula | +0.012 |
mt | +0.012 |
Neg logit contributions | |
ees | -0.013 |
REE | -0.011 |
lust | -0.011 |
yip | -0.011 |
ealous | -0.011 |
Token | Perhaps |
Token ID | 8673 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ees | +0.126 |
REE | +0.105 |
lust | +0.102 |
ealous | +0.101 |
sum | +0.101 |
Neg logit contributions | |
afort | -0.181 |
nels | -0.149 |
arently | -0.145 |
insula | -0.143 |
mt | -0.142 |
Token | it |
Token ID | 340 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
afort | +0.597 |
nels | +0.487 |
arently | +0.474 |
insula | +0.466 |
mt | +0.463 |
Neg logit contributions | |
ees | -0.468 |
REE | -0.394 |
lust | -0.382 |
sum | -0.382 |
yip | -0.382 |
Token | 's |
Token ID | 338 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ees | +0.636 |
REE | +0.533 |
sum | +0.519 |
lust | +0.519 |
ealous | +0.517 |
Neg logit contributions | |
afort | -0.812 |
nels | -0.663 |
arently | -0.647 |
insula | -0.636 |
mt | -0.632 |
Token | some |
Token ID | 617 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ees | +0.839 |
REE | +0.701 |
sum | +0.690 |
lust | +0.686 |
diagnosis | +0.676 |
Neg logit contributions | |
afort | -1.107 |
nels | -0.907 |
arently | -0.882 |
insula | -0.871 |
mt | -0.858 |
Token | last |
Token ID | 938 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
afort | +2.206 |
nels | +1.785 |
arently | +1.739 |
mt | +1.696 |
insula | +1.695 |
Neg logit contributions | |
ees | -1.984 |
REE | -1.698 |
yip | -1.651 |
lust | -1.642 |
ealous | -1.639 |
Token | - |
Token ID | 12 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ees | +0.341 |
REE | +0.280 |
lust | +0.271 |
sum | +0.269 |
yip | +0.269 |
Neg logit contributions | |
afort | -0.542 |
nels | -0.451 |
arently | -0.441 |
insula | -0.433 |
mt | -0.431 |
Token | minute |
Token ID | 11374 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ees | +1.995 |
REE | +1.656 |
lust | +1.634 |
sum | +1.611 |
yip | +1.588 |
Neg logit contributions | |
afort | -2.678 |
nels | -2.194 |
arently | -2.145 |
insula | -2.115 |
mt | -2.063 |
Token | love |
Token ID | 1842 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ees | +0.689 |
REE | +0.573 |
sum | +0.559 |
lust | +0.557 |
ealous | +0.553 |
Neg logit contributions | |
afort | -1.004 |
nels | -0.828 |
arently | -0.810 |
insula | -0.800 |
mt | -0.789 |
Token | her |
Token ID | 607 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ees | +1.089 |
REE | +0.902 |
sum | +0.879 |
lust | +0.870 |
yip | +0.867 |
Neg logit contributions | |
afort | -1.562 |
nels | -1.283 |
arently | -1.260 |
insula | -1.235 |
mt | -1.223 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ees | +0.239 |
REE | +0.199 |
lust | +0.193 |
sum | +0.192 |
ealous | +0.192 |
Neg logit contributions | |
afort | -0.334 |
nels | -0.275 |
arently | -0.269 |
insula | -0.264 |
mt | -0.262 |
Token | death |
Token ID | 1918 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ees | +1.065 |
REE | +0.890 |
sum | +0.867 |
lust | +0.861 |
ealous | +0.858 |
Neg logit contributions | |
afort | -1.428 |
nels | -1.168 |
arently | -1.144 |
insula | -1.122 |
mt | -1.108 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
afort | +0.136 |
nels | +0.111 |
arently | +0.108 |
insula | +0.106 |
mt | +0.106 |
Neg logit contributions | |
ees | -0.105 |
REE | -0.089 |
lust | -0.086 |
yip | -0.086 |
ealous | -0.086 |
Token | She |
Token ID | 1375 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
ees | +0.192 |
REE | +0.159 |
lust | +0.154 |
sum | +0.153 |
ealous | +0.153 |
Neg logit contributions | |
afort | -0.284 |
nels | -0.235 |
arently | -0.230 |
insula | -0.226 |
mt | -0.224 |
Token | is |
Token ID | 318 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
ees | +0.226 |
REE | +0.189 |
sum | +0.184 |
lust | +0.184 |
ealous | +0.183 |
Neg logit contributions | |
afort | -0.293 |
nels | -0.239 |
arently | -0.234 |
insula | -0.231 |
mt | -0.228 |
Token | like |
Token ID | 588 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
afort | +0.906 |
nels | +0.738 |
arently | +0.719 |
insula | +0.704 |
mt | +0.703 |
Neg logit contributions | |
ees | -0.729 |
REE | -0.617 |
yip | -0.598 |
lust | -0.597 |
ealous | -0.596 |
Token | a |
Token ID | 257 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
ees | +1.084 |
REE | +0.907 |
lust | +0.881 |
sum | +0.879 |
yip | +0.877 |
Neg logit contributions | |
afort | -1.452 |
nels | -1.192 |
arently | -1.162 |
insula | -1.142 |
mt | -1.135 |
Token | sister |
Token ID | 6621 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
ees | +0.003 |
REE | +0.002 |
yip | +0.002 |
ealous | +0.002 |
lust | +0.002 |
Neg logit contributions | |
afort | -0.005 |
nels | -0.004 |
arently | -0.004 |
mt | -0.004 |
insula | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
ees | +3.885 |
sum | +3.241 |
lust | +3.220 |
REE | +3.186 |
diagnosis | +3.146 |
Neg logit contributions | |
afort | -5.440 |
nels | -4.523 |
arently | -4.361 |
insula | -4.357 |
mt | -4.293 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ees | +0.465 |
REE | +0.392 |
lust | +0.379 |
sum | +0.379 |
yip | +0.378 |
Neg logit contributions | |
afort | -0.593 |
nels | -0.485 |
arently | -0.472 |
insula | -0.463 |
mt | -0.461 |
Token | naval |
Token ID | 19014 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
afort | +1.110 |
nels | +0.914 |
arently | +0.890 |
mt | +0.876 |
insula | +0.872 |
Neg logit contributions | |
ees | -0.809 |
REE | -0.678 |
yip | -0.660 |
ealous | -0.656 |
lust | -0.652 |
Token | adventure |
Token ID | 8855 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
afort | +1.832 |
nels | +1.501 |
arently | +1.468 |
mt | +1.436 |
insula | +1.435 |
Neg logit contributions | |
ees | -1.380 |
REE | -1.171 |
yip | -1.135 |
ealous | -1.125 |
lust | -1.122 |
Token | set |
Token ID | 900 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
afort | +0.514 |
nels | +0.422 |
arently | +0.411 |
insula | +0.403 |
mt | +0.402 |
Neg logit contributions | |
ees | -0.381 |
REE | -0.320 |
yip | -0.310 |
lust | -0.309 |
ealous | -0.309 |
Token | during |
Token ID | 1141 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
afort | +0.889 |
nels | +0.723 |
arently | +0.704 |
insula | +0.690 |
mt | +0.688 |
Neg logit contributions | |
ees | -0.726 |
REE | -0.615 |
lust | -0.597 |
yip | -0.596 |
ealous | -0.594 |
Token | the |
Token ID | 262 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
afort | +2.114 |
nels | +1.710 |
arently | +1.667 |
insula | +1.630 |
mt | +1.624 |
Neg logit contributions | |
ees | -1.795 |
REE | -1.534 |
yip | -1.486 |
ealous | -1.485 |
lust | -1.479 |
Token | Nap |
Token ID | 14332 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
afort | +0.351 |
nels | +0.290 |
arently | +0.283 |
insula | +0.278 |
mt | +0.277 |
Neg logit contributions | |
ees | -0.243 |
REE | -0.202 |
sum | -0.196 |
lust | -0.195 |
ealous | -0.194 |
Token | ole |
Token ID | 2305 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
afort | +1.604 |
nels | +1.303 |
arently | +1.270 |
insula | +1.243 |
mt | +1.241 |
Neg logit contributions | |
ees | -1.312 |
REE | -1.110 |
lust | -1.079 |
yip | -1.076 |
sum | -1.074 |
Token | onic |
Token ID | 9229 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
afort | +4.089 |
nels | +3.507 |
arently | +3.415 |
insula | +3.397 |
mt | +3.386 |
Neg logit contributions | |
ees | -1.683 |
REE | -1.342 |
hovah | -1.259 |
yip | -1.250 |
ealous | -1.234 |
Token | Wars |
Token ID | 6176 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
afort | +2.013 |
nels | +1.704 |
arently | +1.671 |
insula | +1.648 |
mt | +1.634 |
Neg logit contributions | |
ees | -1.004 |
REE | -0.803 |
yip | -0.772 |
lust | -0.763 |
ealous | -0.759 |
Token | . |
Token ID | 13 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
afort | +0.533 |
nels | +0.433 |
arently | +0.423 |
insula | +0.414 |
mt | +0.412 |
Neg logit contributions | |
ees | -0.431 |
REE | -0.363 |
sum | -0.354 |
lust | -0.353 |
ealous | -0.351 |
Token | model |
Token ID | 2746 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ees | +0.398 |
REE | +0.329 |
sum | +0.319 |
lust | +0.318 |
yip | +0.316 |
Neg logit contributions | |
afort | -0.587 |
nels | -0.485 |
arently | -0.473 |
insula | -0.465 |
mt | -0.463 |
Token | ine |
Token ID | 500 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ees | +0.703 |
REE | +0.561 |
lust | +0.539 |
yip | +0.536 |
sum | +0.536 |
Neg logit contributions | |
afort | -1.339 |
nels | -1.128 |
arently | -1.104 |
insula | -1.086 |
mt | -1.083 |
Token | are |
Token ID | 389 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
ees | +1.732 |
REE | +1.442 |
sum | +1.423 |
lust | +1.395 |
yip | +1.388 |
Neg logit contributions | |
afort | -2.184 |
nels | -1.772 |
arently | -1.738 |
insula | -1.701 |
mt | -1.683 |
Token | used |
Token ID | 973 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
ees | +0.029 |
REE | +0.024 |
lust | +0.023 |
sum | +0.023 |
yip | +0.023 |
Neg logit contributions | |
afort | -0.044 |
nels | -0.037 |
arently | -0.036 |
insula | -0.035 |
mt | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
afort | +3.492 |
nels | +2.806 |
arently | +2.716 |
mt | +2.671 |
insula | +2.665 |
Neg logit contributions | |
ees | -3.166 |
REE | -2.749 |
yip | -2.678 |
hovah | -2.656 |
lust | -2.650 |
Token | Thus |
Token ID | 6660 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
ees | +0.399 |
REE | +0.334 |
sum | +0.325 |
lust | +0.324 |
ealous | +0.322 |
Neg logit contributions | |
afort | -0.523 |
nels | -0.427 |
arently | -0.417 |
insula | -0.408 |
mt | -0.405 |
Token | if |
Token ID | 611 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
afort | +0.771 |
nels | +0.629 |
arently | +0.612 |
insula | +0.600 |
mt | +0.598 |
Neg logit contributions | |
ees | -0.610 |
REE | -0.515 |
lust | -0.499 |
yip | -0.498 |
ealous | -0.497 |
Token | you |
Token ID | 345 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
ees | +1.362 |
REE | +1.126 |
sum | +1.102 |
lust | +1.089 |
yip | +1.083 |
Neg logit contributions | |
afort | -1.944 |
nels | -1.601 |
arently | -1.558 |
insula | -1.534 |
mt | -1.521 |
Token | manually |
Token ID | 14500 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
afort | +0.884 |
nels | +0.725 |
arently | +0.707 |
insula | +0.693 |
mt | +0.691 |
Neg logit contributions | |
ees | -0.659 |
REE | -0.553 |
lust | -0.535 |
yip | -0.535 |
ealous | -0.533 |
Token | changed |
Token ID | 3421 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ees | +0.711 |
REE | +0.595 |
sum | +0.581 |
lust | +0.575 |
ealous | +0.572 |
Neg logit contributions | |
afort | -0.951 |
nels | -0.778 |
arently | -0.760 |
insula | -0.748 |
mt | -0.741 |
Token | a |
Token ID | 257 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
afort | +1.222 |
nels | +0.998 |
arently | +0.972 |
insula | +0.952 |
mt | +0.950 |
Neg logit contributions | |
ees | -0.960 |
REE | -0.813 |
ealous | -0.789 |
lust | -0.787 |
yip | -0.787 |
Token | care |
Token ID | 1337 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ees | +1.187 |
REE | +0.979 |
sum | +0.965 |
lust | +0.952 |
ealous | +0.944 |
Neg logit contributions | |
afort | -1.782 |
nels | -1.476 |
arently | -1.441 |
insula | -1.424 |
mt | -1.402 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
afort | +0.621 |
nels | +0.504 |
arently | +0.490 |
insula | +0.479 |
mt | +0.479 |
Neg logit contributions | |
ees | -0.523 |
REE | -0.445 |
yip | -0.432 |
lust | -0.431 |
ealous | -0.430 |
Token | They |
Token ID | 1119 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ees | +0.226 |
REE | +0.192 |
lust | +0.187 |
ealous | +0.186 |
sum | +0.186 |
Neg logit contributions | |
afort | -0.275 |
nels | -0.223 |
arently | -0.218 |
insula | -0.214 |
mt | -0.211 |
Token | love |
Token ID | 1842 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
afort | +0.229 |
nels | +0.185 |
arently | +0.180 |
insula | +0.177 |
mt | +0.175 |
Neg logit contributions | |
ees | -0.191 |
REE | -0.162 |
sum | -0.158 |
ealous | -0.157 |
lust | -0.157 |
Token | their |
Token ID | 511 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ees | +1.091 |
REE | +0.910 |
sum | +0.900 |
lust | +0.890 |
ealous | +0.882 |
Neg logit contributions | |
afort | -1.426 |
nels | -1.153 |
arently | -1.138 |
insula | -1.118 |
mt | -1.099 |
Token | power |
Token ID | 1176 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
ees | +0.331 |
REE | +0.277 |
lust | +0.269 |
sum | +0.268 |
ealous | +0.267 |
Neg logit contributions | |
afort | -0.451 |
nels | -0.369 |
arently | -0.361 |
insula | -0.354 |
mt | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
afort | +4.121 |
nels | +3.390 |
arently | +3.264 |
mt | +3.219 |
insula | +3.189 |
Neg logit contributions | |
ees | -3.414 |
REE | -2.903 |
yip | -2.840 |
hovah | -2.806 |
ealous | -2.805 |
Token | Tomorrow |
Token ID | 25939 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
ees | +0.359 |
REE | +0.302 |
lust | +0.293 |
ealous | +0.292 |
sum | +0.292 |
Neg logit contributions | |
afort | -0.472 |
nels | -0.386 |
arently | -0.377 |
insula | -0.370 |
mt | -0.366 |
Token | they |
Token ID | 484 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
afort | +0.526 |
nels | +0.428 |
arently | +0.417 |
insula | +0.409 |
mt | +0.407 |
Neg logit contributions | |
ees | -0.419 |
REE | -0.353 |
lust | -0.344 |
sum | -0.343 |
ealous | -0.342 |
Token | would |
Token ID | 561 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
afort | +0.349 |
nels | +0.283 |
arently | +0.276 |
insula | +0.272 |
mt | +0.268 |
Neg logit contributions | |
ees | -0.281 |
REE | -0.237 |
sum | -0.230 |
lust | -0.230 |
ealous | -0.229 |
Token | find |
Token ID | 1064 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
afort | +1.978 |
nels | +1.623 |
arently | +1.583 |
insula | +1.551 |
mt | +1.548 |
Neg logit contributions | |
ees | -1.471 |
REE | -1.234 |
yip | -1.194 |
lust | -1.193 |
ealous | -1.190 |
Token | to |
Token ID | 284 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ees | +0.450 |
REE | +0.385 |
lust | +0.373 |
yip | +0.373 |
ealous | +0.372 |
Neg logit contributions | |
afort | -0.515 |
nels | -0.416 |
arently | -0.405 |
insula | -0.396 |
mt | -0.395 |
Token | meet |
Token ID | 1826 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ees | +0.107 |
REE | +0.089 |
lust | +0.086 |
yip | +0.086 |
ealous | +0.085 |
Neg logit contributions | |
afort | -0.157 |
nels | -0.129 |
arently | -0.126 |
insula | -0.124 |
mt | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
ees | +2.709 |
sum | +2.149 |
REE | +2.139 |
lust | +2.119 |
ealous | +2.079 |
Neg logit contributions | |
afort | -4.065 |
nels | -3.336 |
insula | -3.242 |
arently | -3.224 |
mt | -3.183 |
Token | 19 |
Token ID | 678 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ees | +0.543 |
REE | +0.445 |
sum | +0.432 |
lust | +0.432 |
ealous | +0.429 |
Neg logit contributions | |
afort | -0.847 |
nels | -0.702 |
arently | -0.685 |
insula | -0.675 |
mt | -0.671 |
Token | - |
Token ID | 12 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ees | +1.360 |
REE | +1.118 |
sum | +1.099 |
ealous | +1.094 |
lust | +1.093 |
Neg logit contributions | |
afort | -1.909 |
nels | -1.561 |
arently | -1.515 |
insula | -1.499 |
mt | -1.482 |
Token | member |
Token ID | 19522 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ees | +1.915 |
REE | +1.598 |
lust | +1.574 |
ealous | +1.572 |
sum | +1.565 |
Neg logit contributions | |
afort | -2.359 |
nels | -1.921 |
arently | -1.835 |
insula | -1.816 |
mt | -1.768 |
Token | threshold |
Token ID | 11387 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
afort | +0.536 |
nels | +0.443 |
arently | +0.432 |
insula | +0.424 |
mt | +0.423 |
Neg logit contributions | |
ees | -0.375 |
REE | -0.314 |
yip | -0.303 |
lust | -0.302 |
ealous | -0.301 |
Token | he |
Token ID | 339 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
ees | +0.639 |
REE | +0.531 |
sum | +0.518 |
lust | +0.517 |
yip | +0.513 |
Neg logit contributions | |
afort | -0.884 |
nels | -0.726 |
arently | -0.709 |
insula | -0.696 |
mt | -0.690 |
Token | needs |
Token ID | 2476 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
afort | +0.630 |
nels | +0.528 |
arently | +0.514 |
mt | +0.506 |
insula | +0.501 |
Neg logit contributions | |
ees | -0.391 |
REE | -0.326 |
yip | -0.315 |
lust | -0.311 |
ealous | -0.310 |
Token | to |
Token ID | 284 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ees | +0.912 |
REE | +0.771 |
sum | +0.751 |
lust | +0.751 |
ealous | +0.748 |
Neg logit contributions | |
afort | -1.093 |
nels | -0.886 |
arently | -0.863 |
insula | -0.848 |
mt | -0.841 |
Token | bring |
Token ID | 2222 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ees | +0.327 |
REE | +0.267 |
lust | +0.257 |
yip | +0.256 |
sum | +0.256 |
Neg logit contributions | |
afort | -0.549 |
nels | -0.459 |
arently | -0.449 |
insula | -0.441 |
mt | -0.440 |
Token | m |
Token ID | 76 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ees | +1.102 |
REE | +0.941 |
lust | +0.919 |
sum | +0.915 |
ealous | +0.915 |
Neg logit contributions | |
afort | -1.217 |
nels | -0.978 |
arently | -0.946 |
insula | -0.936 |
mt | -0.916 |
Token | sending |
Token ID | 7216 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
afort | +1.166 |
nels | +0.958 |
arently | +0.934 |
insula | +0.917 |
mt | +0.913 |
Neg logit contributions | |
ees | -0.858 |
REE | -0.718 |
lust | -0.695 |
yip | -0.694 |
ealous | -0.693 |
Token | to |
Token ID | 284 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
afort | +1.095 |
nels | +0.890 |
arently | +0.867 |
insula | +0.849 |
mt | +0.846 |
Neg logit contributions | |
ees | -0.896 |
REE | -0.759 |
lust | -0.736 |
yip | -0.735 |
ealous | -0.734 |
Token | a |
Token ID | 257 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ees | +0.062 |
REE | +0.052 |
lust | +0.050 |
yip | +0.050 |
ealous | +0.050 |
Neg logit contributions | |
afort | -0.084 |
nels | -0.069 |
arently | -0.068 |
insula | -0.066 |
mt | -0.066 |
Token | developer |
Token ID | 8517 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
afort | +0.507 |
nels | +0.416 |
arently | +0.406 |
insula | +0.398 |
mt | +0.397 |
Neg logit contributions | |
ees | -0.378 |
REE | -0.317 |
lust | -0.307 |
yip | -0.307 |
ealous | -0.306 |
Token | of |
Token ID | 286 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ees | +0.301 |
REE | +0.252 |
sum | +0.246 |
lust | +0.244 |
ealous | +0.242 |
Neg logit contributions | |
afort | -0.398 |
nels | -0.327 |
arently | -0.319 |
insula | -0.313 |
mt | -0.310 |
Token | the |
Token ID | 262 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
afort | +1.231 |
nels | +1.010 |
arently | +0.985 |
insula | +0.966 |
mt | +0.963 |
Neg logit contributions | |
ees | -0.913 |
REE | -0.766 |
lust | -0.741 |
yip | -0.740 |
ealous | -0.738 |
Token | host |
Token ID | 2583 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ees | +0.341 |
REE | +0.283 |
sum | +0.273 |
lust | +0.272 |
yip | +0.272 |
Neg logit contributions | |
afort | -0.512 |
nels | -0.425 |
arently | -0.414 |
insula | -0.407 |
mt | -0.403 |
Token | shield |
Token ID | 7614 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
afort | +0.377 |
nels | +0.307 |
arently | +0.299 |
insula | +0.294 |
mt | +0.291 |
Neg logit contributions | |
ees | -0.294 |
REE | -0.247 |
sum | -0.239 |
lust | -0.239 |
yip | -0.238 |
Token | library |
Token ID | 5888 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
afort | +4.489 |
nels | +3.660 |
arently | +3.572 |
mt | +3.522 |
insula | +3.476 |
Neg logit contributions | |
ees | -3.686 |
REE | -3.152 |
ealous | -3.052 |
yip | -3.048 |
lust | -3.047 |
Token | ( |
Token ID | 357 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ees | +1.195 |
REE | +1.001 |
sum | +0.979 |
lust | +0.967 |
yip | +0.966 |
Neg logit contributions | |
afort | -1.561 |
nels | -1.273 |
arently | -1.243 |
insula | -1.225 |
mt | -1.201 |
Token | currently |
Token ID | 3058 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
afort | +1.783 |
nels | +1.450 |
arently | +1.415 |
mt | +1.385 |
insula | +1.378 |
Neg logit contributions | |
ees | -1.436 |
REE | -1.220 |
yip | -1.187 |
lust | -1.180 |
ealous | -1.179 |
Token | the |
Token ID | 262 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ees | +0.009 |
REE | +0.008 |
lust | +0.008 |
sum | +0.008 |
yip | +0.008 |
Neg logit contributions | |
afort | -0.012 |
nels | -0.010 |
arently | -0.010 |
insula | -0.010 |
mt | -0.010 |
Token | Stars |
Token ID | 10271 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ees | +0.447 |
REE | +0.366 |
sum | +0.354 |
lust | +0.354 |
ealous | +0.352 |
Neg logit contributions | |
afort | -0.702 |
nels | -0.583 |
arently | -0.570 |
insula | -0.562 |
mt | -0.557 |
Token | � |
Token ID | 447 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ees | +2.551 |
REE | +1.967 |
sum | +1.910 |
lust | +1.904 |
ealous | +1.873 |
Neg logit contributions | |
afort | -5.544 |
nels | -4.725 |
arently | -4.611 |
insula | -4.575 |
mt | -4.497 |
Token | � |
Token ID | 247 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ees | +0.796 |
REE | +0.646 |
lust | +0.621 |
sum | +0.619 |
ealous | +0.615 |
Neg logit contributions | |
afort | -1.456 |
nels | -1.227 |
arently | -1.200 |
mt | -1.170 |
insula | -1.169 |
Token | general |
Token ID | 2276 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ees | +0.434 |
REE | +0.361 |
lust | +0.349 |
yip | +0.348 |
ealous | +0.347 |
Neg logit contributions | |
afort | -0.619 |
nels | -0.511 |
arently | -0.498 |
insula | -0.489 |
mt | -0.487 |
Token | manager |
Token ID | 4706 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
afort | +0.679 |
nels | +0.553 |
arently | +0.538 |
insula | +0.528 |
mt | +0.526 |
Neg logit contributions | |
ees | -0.544 |
REE | -0.459 |
lust | -0.445 |
sum | -0.444 |
ealous | -0.444 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
afort | +0.002 |
nels | +0.001 |
arently | +0.001 |
insula | +0.001 |
mt | +0.001 |
Neg logit contributions | |
ees | -0.001 |
REE | -0.001 |
lust | -0.001 |
yip | -0.001 |
ealous | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
afort | +0.221 |
nels | +0.179 |
arently | +0.174 |
insula | +0.170 |
mt | +0.169 |
Neg logit contributions | |
ees | -0.192 |
REE | -0.164 |
lust | -0.159 |
yip | -0.159 |
ealous | -0.158 |
Token | Devils |
Token ID | 26199 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
ees | +0.156 |
REE | +0.130 |
lust | +0.125 |
yip | +0.125 |
ealous | +0.125 |
Neg logit contributions | |
afort | -0.221 |
nels | -0.182 |
arently | -0.178 |
insula | -0.174 |
mt | -0.174 |
Token | re |
Token ID | 302 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ees | +2.208 |
REE | +1.819 |
sum | +1.794 |
lust | +1.764 |
ealous | +1.748 |
Neg logit contributions | |
afort | -3.147 |
nels | -2.592 |
arently | -2.529 |
insula | -2.517 |
mt | -2.466 |
Token | : |
Token ID | 25 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
ees | +1.469 |
lust | +1.133 |
REE | +1.121 |
sum | +1.109 |
ealous | +1.095 |
Neg logit contributions | |
afort | -2.779 |
arently | -2.336 |
nels | -2.321 |
insula | -2.310 |
mt | -2.204 |
Token | Clive |
Token ID | 47722 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
afort | +0.070 |
nels | +0.057 |
arently | +0.056 |
insula | +0.055 |
mt | +0.054 |
Neg logit contributions | |
ees | -0.051 |
REE | -0.043 |
lust | -0.041 |
sum | -0.041 |
ealous | -0.041 |
Token | Brun |
Token ID | 15700 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ees | +1.733 |
REE | +1.415 |
sum | +1.359 |
lust | +1.349 |
yip | +1.340 |
Neg logit contributions | |
afort | -2.732 |
nels | -2.297 |
arently | -2.236 |
insula | -2.221 |
mt | -2.179 |
Token | skill |
Token ID | 42401 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
ees | +2.519 |
lust | +2.117 |
ealous | +2.053 |
REE | +2.041 |
sum | +2.035 |
Neg logit contributions | |
afort | -2.668 |
insula | -2.120 |
arently | -2.106 |
nels | -2.084 |
mt | -2.027 |
Token | / |
Token ID | 14 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ees | +0.060 |
REE | +0.050 |
lust | +0.049 |
yip | +0.049 |
ealous | +0.048 |
Neg logit contributions | |
afort | -0.081 |
nels | -0.067 |
arently | -0.065 |
insula | -0.064 |
mt | -0.064 |
Token | Getty |
Token ID | 6633 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
afort | +1.528 |
nels | +1.221 |
arently | +1.188 |
insula | +1.160 |
mt | +1.153 |
Neg logit contributions | |
ees | -1.447 |
REE | -1.243 |
lust | -1.208 |
ealous | -1.204 |
yip | -1.202 |
Token | Images |
Token ID | 5382 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
afort | +4.587 |
nels | +3.509 |
arently | +3.373 |
insula | +3.313 |
mt | +3.233 |
Neg logit contributions | |
ees | -6.016 |
yip | -5.523 |
REE | -5.469 |
hovah | -5.291 |
sum | -5.249 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
afort | +1.647 |
nels | +1.358 |
arently | +1.321 |
insula | +1.303 |
mt | +1.298 |
Neg logit contributions | |
ees | -1.149 |
REE | -0.969 |
yip | -0.952 |
ealous | -0.929 |
lust | -0.927 |
Token |
|
Token ID | 198 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
ees | +0.009 |
REE | +0.007 |
lust | +0.007 |
sum | +0.007 |
ealous | +0.007 |
Neg logit contributions | |
afort | -0.015 |
nels | -0.013 |
arently | -0.012 |
insula | -0.012 |
mt | -0.012 |
Token | That |
Token ID | 2504 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
afort | +0.066 |
nels | +0.053 |
arently | +0.052 |
insula | +0.051 |
mt | +0.050 |
Neg logit contributions | |
ees | -0.057 |
REE | -0.049 |
lust | -0.048 |
ealous | -0.047 |
sum | -0.047 |
Token | low |
Token ID | 1877 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
ees | +0.059 |
REE | +0.049 |
lust | +0.048 |
sum | +0.048 |
ealous | +0.047 |
Neg logit contributions | |
afort | -0.081 |
nels | -0.066 |
arently | -0.065 |
insula | -0.064 |
mt | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ees | +0.076 |
REE | +0.064 |
yip | +0.062 |
lust | +0.062 |
ealous | +0.062 |
Neg logit contributions | |
afort | -0.097 |
nels | -0.079 |
arently | -0.077 |
insula | -0.076 |
mt | -0.076 |
Token | Clara |
Token ID | 27443 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ees | +0.102 |
REE | +0.086 |
yip | +0.084 |
lust | +0.084 |
ealous | +0.083 |
Neg logit contributions | |
afort | -0.133 |
nels | -0.109 |
arently | -0.106 |
insula | -0.104 |
mt | -0.104 |
Token | Mohammed |
Token ID | 19773 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ees | +1.704 |
REE | +1.425 |
lust | +1.377 |
sum | +1.375 |
ealous | +1.369 |
Neg logit contributions | |
afort | -2.290 |
nels | -1.871 |
arently | -1.831 |
insula | -1.793 |
mt | -1.785 |
Token | School |
Token ID | 3961 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
afort | +3.106 |
nels | +2.590 |
arently | +2.499 |
mt | +2.460 |
insula | +2.455 |
Neg logit contributions | |
ees | -2.261 |
REE | -1.919 |
yip | -1.902 |
lust | -1.868 |
ealous | -1.866 |
Token | and |
Token ID | 290 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ees | +0.906 |
REE | +0.761 |
lust | +0.736 |
sum | +0.734 |
yip | +0.730 |
Neg logit contributions | |
afort | -1.202 |
nels | -0.981 |
arently | -0.960 |
insula | -0.940 |
mt | -0.938 |
Token | Carter |
Token ID | 10831 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
ees | +0.212 |
REE | +0.178 |
yip | +0.173 |
lust | +0.173 |
ealous | +0.172 |
Neg logit contributions | |
afort | -0.282 |
nels | -0.231 |
arently | -0.225 |
insula | -0.221 |
mt | -0.220 |
Token | 's |
Token ID | 338 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
afort | +5.724 |
nels | +4.786 |
arently | +4.603 |
mt | +4.523 |
insula | +4.506 |
Neg logit contributions | |
ees | -4.208 |
REE | -3.578 |
yip | -3.578 |
ealous | -3.536 |
glim | -3.495 |
Token | Christian |
Token ID | 4302 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ees | +0.893 |
REE | +0.746 |
lust | +0.721 |
yip | +0.720 |
ealous | +0.718 |
Neg logit contributions | |
afort | -1.241 |
nels | -1.021 |
arently | -0.996 |
insula | -0.977 |
mt | -0.974 |
Token | Academy |
Token ID | 8581 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
afort | +0.312 |
nels | +0.259 |
arently | +0.253 |
insula | +0.248 |
mt | +0.247 |
Neg logit contributions | |
ees | -0.208 |
REE | -0.173 |
yip | -0.167 |
lust | -0.167 |
ealous | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
ees | +1.162 |
REE | +0.983 |
sum | +0.952 |
lust | +0.949 |
yip | +0.942 |
Neg logit contributions | |
afort | -1.454 |
nels | -1.177 |
arently | -1.151 |
insula | -1.126 |
mt | -1.123 |
Token | In |
Token ID | 554 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
afort | +0.246 |
nels | +0.202 |
arently | +0.197 |
insula | +0.194 |
mt | +0.193 |
Neg logit contributions | |
ees | -0.182 |
REE | -0.152 |
lust | -0.147 |
ealous | -0.147 |
yip | -0.146 |
Token | usual |
Token ID | 6678 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ees | +0.314 |
REE | +0.262 |
yip | +0.254 |
lust | +0.254 |
ealous | +0.253 |
Neg logit contributions | |
afort | -0.442 |
nels | -0.365 |
arently | -0.356 |
insula | -0.349 |
mt | -0.348 |
Token | � |
Token ID | 564 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
afort | +0.130 |
nels | +0.108 |
arently | +0.105 |
insula | +0.103 |
mt | +0.103 |
Neg logit contributions | |
ees | -0.089 |
REE | -0.074 |
lust | -0.071 |
yip | -0.071 |
ealous | -0.071 |
Token | � |
Token ID | 246 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
afort | +2.535 |
nels | +1.901 |
arently | +1.836 |
insula | +1.795 |
mt | +1.779 |
Neg logit contributions | |
ees | -3.573 |
REE | -3.159 |
yip | -3.116 |
lust | -3.078 |
sum | -3.074 |
Token | Elect |
Token ID | 19453 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
afort | +0.114 |
nels | +0.091 |
arently | +0.088 |
insula | +0.086 |
mt | +0.085 |
Neg logit contributions | |
ees | -0.111 |
REE | -0.095 |
lust | -0.093 |
ealous | -0.093 |
yip | -0.092 |
Token | rom |
Token ID | 398 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
afort | +5.519 |
nels | +4.327 |
arently | +4.273 |
mt | +4.171 |
insula | +4.149 |
Neg logit contributions | |
ees | -5.779 |
REE | -5.080 |
yip | -5.039 |
lust | -4.968 |
ealous | -4.968 |
Token | agnetic |
Token ID | 25145 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
afort | +0.203 |
nels | +0.156 |
arently | +0.151 |
insula | +0.147 |
mt | +0.146 |
Neg logit contributions | |
ees | -0.256 |
REE | -0.224 |
yip | -0.219 |
lust | -0.219 |
ealous | -0.218 |
Token | field |
Token ID | 2214 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
afort | +5.663 |
nels | +4.595 |
arently | +4.465 |
mt | +4.419 |
insula | +4.416 |
Neg logit contributions | |
ees | -4.426 |
REE | -3.742 |
lust | -3.666 |
ealous | -3.646 |
yip | -3.640 |
Token | � |
Token ID | 447 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
afort | +1.197 |
nels | +0.964 |
arently | +0.937 |
insula | +0.917 |
mt | +0.914 |
Neg logit contributions | |
ees | -1.076 |
REE | -0.921 |
yip | -0.894 |
lust | -0.894 |
ealous | -0.892 |
Token | � |
Token ID | 247 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
afort | +0.307 |
nels | +0.257 |
arently | +0.251 |
insula | +0.246 |
mt | +0.246 |
Neg logit contributions | |
ees | -0.182 |
REE | -0.148 |
lust | -0.143 |
sum | -0.142 |
ealous | -0.142 |
Token | or |
Token ID | 393 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
afort | +0.295 |
nels | +0.241 |
arently | +0.235 |
insula | +0.230 |
mt | +0.229 |
Neg logit contributions | |
ees | -0.223 |
REE | -0.187 |
lust | -0.181 |
sum | -0.181 |
yip | -0.181 |
Token | � |
Token ID | 564 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
afort | +1.016 |
nels | +0.828 |
arently | +0.806 |
insula | +0.790 |
mt | +0.788 |
Neg logit contributions | |
ees | -0.816 |
REE | -0.690 |
lust | -0.669 |
yip | -0.668 |
ealous | -0.667 |
Token | the |
Token ID | 262 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
afort | +1.624 |
nels | +1.336 |
arently | +1.308 |
insula | +1.282 |
mt | +1.268 |
Neg logit contributions | |
ees | -1.184 |
REE | -0.989 |
lust | -0.962 |
sum | -0.954 |
ealous | -0.954 |
Token | Year |
Token ID | 6280 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ees | +0.003 |
REE | +0.003 |
yip | +0.003 |
lust | +0.003 |
ealous | +0.003 |
Neg logit contributions | |
afort | -0.004 |
nels | -0.004 |
arently | -0.004 |
insula | -0.003 |
mt | -0.003 |
Token | voting |
Token ID | 6709 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
ees | +1.452 |
REE | +1.194 |
sum | +1.163 |
lust | +1.144 |
diagnosis | +1.124 |
Neg logit contributions | |
afort | -2.249 |
nels | -1.860 |
arently | -1.825 |
insula | -1.806 |
mt | -1.778 |
Token | to |
Token ID | 284 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
afort | +0.467 |
nels | +0.382 |
arently | +0.373 |
insula | +0.366 |
mt | +0.364 |
Neg logit contributions | |
ees | -0.358 |
REE | -0.301 |
lust | -0.291 |
yip | -0.291 |
ealous | -0.290 |
Token | Marcus |
Token ID | 17068 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
ees | +0.018 |
REE | +0.015 |
lust | +0.014 |
sum | +0.014 |
yip | +0.014 |
Neg logit contributions | |
afort | -0.024 |
nels | -0.019 |
arently | -0.019 |
insula | -0.019 |
mt | -0.019 |
Token | Paige |
Token ID | 42847 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
ees | +2.692 |
REE | +2.253 |
sum | +2.223 |
lust | +2.200 |
ealous | +2.173 |
Neg logit contributions | |
afort | -3.348 |
nels | -2.728 |
arently | -2.672 |
insula | -2.631 |
mt | -2.575 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
afort | +5.245 |
nels | +4.213 |
arently | +4.068 |
mt | +3.961 |
insula | +3.916 |
Neg logit contributions | |
ees | -4.706 |
yip | -4.081 |
REE | -4.052 |
ealous | -3.953 |
hovah | -3.921 |
Token | 103 |
Token ID | 15197 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
afort | +0.800 |
nels | +0.583 |
arently | +0.558 |
mt | +0.539 |
insula | +0.536 |
Neg logit contributions | |
ees | -1.323 |
REE | -1.178 |
yip | -1.159 |
lust | -1.153 |
ealous | -1.152 |
Token | ] |
Token ID | 60 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
afort | +2.219 |
nels | +1.639 |
arently | +1.607 |
mt | +1.531 |
insula | +1.518 |
Neg logit contributions | |
ees | -3.427 |
REE | -3.085 |
yip | -3.017 |
hovah | -2.973 |
sum | -2.968 |
Token | He |
Token ID | 679 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
afort | +0.741 |
nels | +0.609 |
arently | +0.593 |
insula | +0.582 |
mt | +0.581 |
Neg logit contributions | |
ees | -0.544 |
REE | -0.456 |
yip | -0.445 |
lust | -0.441 |
ealous | -0.440 |
Token | was |
Token ID | 373 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
afort | +0.750 |
nels | +0.616 |
arently | +0.600 |
insula | +0.590 |
mt | +0.587 |
Neg logit contributions | |
ees | -0.553 |
REE | -0.462 |
lust | -0.448 |
sum | -0.446 |
yip | -0.446 |
Token | � |
Token ID | 447 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
afort | +0.452 |
nels | +0.370 |
arently | +0.360 |
insula | +0.353 |
mt | +0.353 |
Neg logit contributions | |
ees | -0.349 |
REE | -0.295 |
yip | -0.286 |
lust | -0.285 |
ealous | -0.284 |
Token | � |
Token ID | 251 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
afort | +0.518 |
nels | +0.418 |
arently | +0.408 |
insula | +0.401 |
mt | +0.398 |
Neg logit contributions | |
ees | -0.444 |
REE | -0.380 |
yip | -0.369 |
lust | -0.367 |
ealous | -0.366 |
Token | bloggers |
Token ID | 30357 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
afort | +0.979 |
nels | +0.806 |
arently | +0.786 |
insula | +0.771 |
mt | +0.771 |
Neg logit contributions | |
ees | -0.699 |
REE | -0.588 |
lust | -0.568 |
yip | -0.567 |
ealous | -0.565 |
Token | like |
Token ID | 588 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ees | +0.597 |
REE | +0.500 |
sum | +0.485 |
lust | +0.484 |
yip | +0.484 |
Neg logit contributions | |
afort | -0.783 |
nels | -0.641 |
arently | -0.625 |
insula | -0.613 |
mt | -0.610 |
Token | John |
Token ID | 1757 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
afort | +0.321 |
nels | +0.264 |
arently | +0.257 |
insula | +0.252 |
mt | +0.252 |
Neg logit contributions | |
ees | -0.235 |
REE | -0.197 |
lust | -0.190 |
yip | -0.190 |
ealous | -0.190 |
Token | Scal |
Token ID | 34529 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
afort | +0.545 |
nels | +0.445 |
arently | +0.434 |
insula | +0.425 |
mt | +0.424 |
Neg logit contributions | |
ees | -0.425 |
REE | -0.359 |
yip | -0.347 |
lust | -0.347 |
ealous | -0.346 |
Token | zi |
Token ID | 17027 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
afort | +4.914 |
nels | +3.813 |
mt | +3.641 |
arently | +3.636 |
insula | +3.475 |
Neg logit contributions | |
ees | -5.883 |
REE | -5.186 |
yip | -5.114 |
hovah | -5.027 |
lust | -4.969 |
Token | — |
Token ID | 960 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
afort | +0.597 |
nels | +0.487 |
arently | +0.474 |
mt | +0.463 |
insula | +0.463 |
Neg logit contributions | |
ees | -0.464 |
REE | -0.392 |
yip | -0.381 |
lust | -0.379 |
ealous | -0.376 |
Token | from |
Token ID | 6738 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ees | +0.228 |
REE | +0.194 |
lust | +0.189 |
ealous | +0.187 |
yip | +0.187 |
Neg logit contributions | |
afort | -0.270 |
nels | -0.219 |
arently | -0.213 |
insula | -0.209 |
mt | -0.207 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ees | +0.167 |
REE | +0.141 |
sum | +0.137 |
lust | +0.137 |
yip | +0.136 |
Neg logit contributions | |
afort | -0.208 |
nels | -0.169 |
arently | -0.165 |
insula | -0.162 |
mt | -0.161 |
Token | sweeping |
Token ID | 18404 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
afort | +1.992 |
nels | +1.615 |
arently | +1.574 |
mt | +1.536 |
insula | +1.530 |
Neg logit contributions | |
ees | -1.639 |
REE | -1.402 |
yip | -1.359 |
lust | -1.350 |
ealous | -1.350 |