Token | hospitalized |
Token ID | 31736 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
aredevil | +2.292 |
vez | +2.178 |
rams | +2.101 |
emies | +2.028 |
subp | +1.974 |
Neg logit contributions | |
Sigma | -2.554 |
alist | -2.103 |
Lange | -2.101 |
Cantor | -2.019 |
sonian | -1.990 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
aredevil | +0.014 |
vez | +0.014 |
rams | +0.013 |
emies | +0.013 |
subp | +0.013 |
Neg logit contributions | |
Sigma | -0.013 |
Lange | -0.011 |
alist | -0.011 |
Cantor | -0.010 |
chamber | -0.010 |
Token | could |
Token ID | 714 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
aredevil | +0.539 |
vez | +0.514 |
rams | +0.497 |
emies | +0.481 |
subp | +0.468 |
Neg logit contributions | |
Sigma | -0.518 |
Lange | -0.419 |
alist | -0.418 |
Cantor | -0.401 |
sonian | -0.394 |
Token | not |
Token ID | 407 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Sigma | +0.526 |
alist | +0.423 |
Lange | +0.423 |
Cantor | +0.404 |
chamber | +0.397 |
Neg logit contributions | |
aredevil | -0.572 |
vez | -0.546 |
rams | -0.529 |
emies | -0.512 |
subp | -0.497 |
Token | be |
Token ID | 307 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
aredevil | +0.973 |
vez | +0.927 |
rams | +0.895 |
emies | +0.867 |
subp | +0.848 |
Neg logit contributions | |
Sigma | -0.918 |
Lange | -0.741 |
alist | -0.739 |
Cantor | -0.709 |
sonian | -0.699 |
Token | reached |
Token ID | 4251 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Sigma | +1.610 |
Lange | +1.351 |
alist | +1.339 |
Cantor | +1.302 |
chamber | +1.283 |
Neg logit contributions | |
aredevil | -1.252 |
vez | -1.158 |
rams | -1.141 |
emies | -1.104 |
irez | -1.057 |
Token | for |
Token ID | 329 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
Sigma | +5.516 |
Lange | +4.471 |
alist | +4.395 |
Cantor | +4.237 |
Sachs | +4.150 |
Neg logit contributions | |
aredevil | -6.588 |
vez | -6.089 |
rams | -6.047 |
emies | -5.924 |
subp | -5.810 |
Token | comment |
Token ID | 2912 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
Sigma | +2.186 |
Lange | +1.698 |
alist | +1.693 |
Cantor | +1.605 |
Sachs | +1.556 |
Neg logit contributions | |
aredevil | -3.132 |
vez | -3.002 |
rams | -2.919 |
emies | -2.853 |
subp | -2.775 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Sigma | +2.374 |
Lange | +1.909 |
alist | +1.891 |
Cantor | +1.822 |
Sachs | +1.773 |
Neg logit contributions | |
aredevil | -2.715 |
vez | -2.566 |
rams | -2.487 |
emies | -2.438 |
subp | -2.364 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Sigma | +0.747 |
Lange | +0.613 |
alist | +0.610 |
Cantor | +0.590 |
Sachs | +0.579 |
Neg logit contributions | |
aredevil | -0.683 |
vez | -0.651 |
rams | -0.627 |
emies | -0.606 |
subp | -0.590 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Sigma | +0.611 |
alist | +0.503 |
Lange | +0.503 |
Cantor | +0.485 |
sonian | +0.477 |
Neg logit contributions | |
aredevil | -0.537 |
vez | -0.509 |
rams | -0.491 |
emies | -0.474 |
subp | -0.460 |
Token | memory |
Token ID | 4088 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
aredevil | +0.156 |
vez | +0.149 |
rams | +0.144 |
emies | +0.139 |
subp | +0.135 |
Neg logit contributions | |
Sigma | -0.161 |
Lange | -0.131 |
alist | -0.131 |
Cantor | -0.126 |
sonian | -0.124 |
Token | ( |
Token ID | 357 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
aredevil | +1.317 |
vez | +1.256 |
rams | +1.214 |
emies | +1.175 |
subp | +1.144 |
Neg logit contributions | |
Sigma | -1.313 |
alist | -1.069 |
Lange | -1.068 |
Cantor | -1.024 |
sonian | -1.009 |
Token | Intel |
Token ID | 24123 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
Sigma | +1.765 |
alist | +1.450 |
Lange | +1.447 |
Cantor | +1.392 |
sonian | +1.363 |
Neg logit contributions | |
aredevil | -1.668 |
vez | -1.569 |
rams | -1.515 |
emies | -1.487 |
subp | -1.435 |
Token | VT |
Token ID | 32751 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
aredevil | +0.225 |
vez | +0.214 |
rams | +0.208 |
emies | +0.202 |
irez | +0.196 |
Neg logit contributions | |
Sigma | -0.189 |
Lange | -0.150 |
alist | -0.149 |
Cantor | -0.143 |
sonian | -0.140 |
Token | - |
Token ID | 12 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
aredevil | +1.953 |
vez | +1.845 |
rams | +1.775 |
emies | +1.697 |
subp | +1.641 |
Neg logit contributions | |
Sigma | -2.785 |
alist | -2.348 |
Lange | -2.340 |
Cantor | -2.272 |
sonian | -2.243 |
Token | x |
Token ID | 87 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Sigma | +1.373 |
alist | +1.135 |
Lange | +1.127 |
Cantor | +1.079 |
sonian | +1.055 |
Neg logit contributions | |
aredevil | -1.314 |
vez | -1.234 |
rams | -1.185 |
emies | -1.171 |
subp | -1.135 |
Token | , |
Token ID | 11 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Sigma | +5.933 |
Lange | +4.733 |
alist | +4.653 |
chamber | +4.550 |
Cantor | +4.387 |
Neg logit contributions | |
aredevil | -6.242 |
vez | -5.870 |
rams | -5.645 |
emies | -5.560 |
subp | -5.397 |
Token | AMD |
Token ID | 10324 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Sigma | +1.585 |
Lange | +1.246 |
alist | +1.236 |
Cantor | +1.190 |
chamber | +1.164 |
Neg logit contributions | |
aredevil | -1.853 |
vez | -1.755 |
rams | -1.706 |
emies | -1.665 |
irez | -1.630 |
Token | - |
Token ID | 12 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Sigma | +0.968 |
Lange | +0.757 |
alist | +0.754 |
Cantor | +0.723 |
chamber | +0.704 |
Neg logit contributions | |
aredevil | -1.216 |
vez | -1.155 |
rams | -1.126 |
emies | -1.094 |
irez | -1.061 |
Token | V |
Token ID | 53 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Sigma | +1.089 |
alist | +0.890 |
Lange | +0.885 |
Cantor | +0.854 |
sonian | +0.846 |
Neg logit contributions | |
aredevil | -1.060 |
vez | -0.994 |
rams | -0.968 |
emies | -0.945 |
subp | -0.918 |
Token | ). |
Token ID | 737 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Sigma | +2.621 |
Lange | +2.129 |
alist | +2.102 |
Cantor | +2.006 |
chamber | +1.969 |
Neg logit contributions | |
aredevil | -2.551 |
vez | -2.413 |
rams | -2.321 |
emies | -2.282 |
subp | -2.245 |
Token | by |
Token ID | 416 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Sigma | +0.688 |
alist | +0.565 |
Lange | +0.564 |
Cantor | +0.542 |
sonian | +0.532 |
Neg logit contributions | |
aredevil | -0.636 |
vez | -0.603 |
rams | -0.581 |
emies | -0.561 |
subp | -0.547 |
Token | a |
Token ID | 257 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Sigma | +0.754 |
Lange | +0.603 |
alist | +0.602 |
Cantor | +0.576 |
chamber | +0.563 |
Neg logit contributions | |
aredevil | -0.875 |
vez | -0.835 |
rams | -0.808 |
emies | -0.786 |
subp | -0.764 |
Token | deaf |
Token ID | 21815 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Sigma | +0.838 |
Lange | +0.674 |
alist | +0.672 |
Cantor | +0.644 |
chamber | +0.633 |
Neg logit contributions | |
aredevil | -0.926 |
vez | -0.883 |
rams | -0.857 |
emies | -0.833 |
subp | -0.807 |
Token | ening |
Token ID | 3101 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Sigma | +0.514 |
alist | +0.430 |
Lange | +0.429 |
Cantor | +0.414 |
sonian | +0.409 |
Neg logit contributions | |
aredevil | -0.388 |
vez | -0.367 |
rams | -0.353 |
emies | -0.339 |
subp | -0.328 |
Token | th |
Token ID | 294 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
aredevil | +0.797 |
vez | +0.764 |
rams | +0.741 |
emies | +0.720 |
subp | +0.706 |
Neg logit contributions | |
Sigma | -0.584 |
alist | -0.455 |
Lange | -0.454 |
Cantor | -0.431 |
sonian | -0.426 |
Token | ud |
Token ID | 463 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Sigma | +1.385 |
alist | +1.108 |
Lange | +1.094 |
Cantor | +1.046 |
sonian | +1.035 |
Neg logit contributions | |
aredevil | -1.675 |
vez | -1.597 |
rams | -1.542 |
emies | -1.514 |
subp | -1.487 |
Token | from |
Token ID | 422 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Sigma | +5.386 |
alist | +4.281 |
Lange | +4.240 |
chamber | +4.135 |
Cantor | +4.076 |
Neg logit contributions | |
aredevil | -6.522 |
vez | -6.189 |
rams | -5.975 |
emies | -5.806 |
subp | -5.652 |
Token | the |
Token ID | 262 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
Sigma | +1.337 |
Lange | +1.055 |
alist | +1.050 |
Cantor | +1.006 |
chamber | +0.981 |
Neg logit contributions | |
aredevil | -1.663 |
vez | -1.591 |
rams | -1.542 |
emies | -1.495 |
subp | -1.460 |
Token | collapsing |
Token ID | 30792 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Sigma | +0.214 |
Lange | +0.172 |
alist | +0.172 |
Cantor | +0.164 |
sonian | +0.161 |
Neg logit contributions | |
aredevil | -0.236 |
vez | -0.225 |
rams | -0.218 |
emies | -0.211 |
subp | -0.206 |
Token | monster |
Token ID | 9234 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Sigma | +0.741 |
Lange | +0.591 |
alist | +0.588 |
Cantor | +0.566 |
chamber | +0.557 |
Neg logit contributions | |
aredevil | -0.850 |
vez | -0.811 |
rams | -0.785 |
emies | -0.761 |
irez | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
Sigma | +1.820 |
alist | +1.465 |
Lange | +1.461 |
Cantor | +1.400 |
chamber | +1.389 |
Neg logit contributions | |
aredevil | -1.967 |
vez | -1.883 |
rams | -1.818 |
emies | -1.755 |
irez | -1.708 |
Token | 3 |
Token ID | 18 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Sigma | +2.032 |
alist | +1.684 |
Lange | +1.654 |
Cantor | +1.589 |
chamber | +1.569 |
Neg logit contributions | |
aredevil | -1.963 |
vez | -1.885 |
rams | -1.788 |
emies | -1.753 |
subp | -1.700 |
Token | . |
Token ID | 13 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
Sigma | +2.233 |
alist | +1.789 |
Lange | +1.786 |
Cantor | +1.713 |
sonian | +1.677 |
Neg logit contributions | |
aredevil | -2.499 |
vez | -2.375 |
rams | -2.297 |
emies | -2.221 |
subp | -2.183 |
Token | In |
Token ID | 554 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Sigma | +2.398 |
Lange | +1.928 |
alist | +1.862 |
Cantor | +1.845 |
Sachs | +1.812 |
Neg logit contributions | |
aredevil | -2.606 |
vez | -2.487 |
rams | -2.392 |
emies | -2.331 |
subp | -2.273 |
Token | a |
Token ID | 257 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Sigma | +2.110 |
Lange | +1.661 |
alist | +1.634 |
chamber | +1.559 |
Cantor | +1.557 |
Neg logit contributions | |
aredevil | -2.767 |
vez | -2.641 |
rams | -2.564 |
emies | -2.485 |
irez | -2.433 |
Token | large |
Token ID | 1588 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Sigma | +1.921 |
Lange | +1.511 |
alist | +1.465 |
chamber | +1.416 |
Cantor | +1.408 |
Neg logit contributions | |
aredevil | -2.635 |
vez | -2.518 |
rams | -2.448 |
emies | -2.389 |
irez | -2.326 |
Token | bowl |
Token ID | 9396 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Sigma | +2.643 |
Lange | +2.012 |
alist | +1.944 |
chamber | +1.911 |
Cantor | +1.869 |
Neg logit contributions | |
aredevil | -4.358 |
vez | -4.167 |
rams | -4.049 |
emies | -3.979 |
irez | -3.892 |
Token | , |
Token ID | 11 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
Sigma | +5.154 |
alist | +4.100 |
chamber | +4.088 |
Lange | +4.000 |
Cantor | +3.824 |
Neg logit contributions | |
aredevil | -6.267 |
vez | -6.067 |
rams | -5.710 |
emies | -5.577 |
irez | -5.424 |
Token | combine |
Token ID | 12082 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Sigma | +2.256 |
alist | +1.863 |
Lange | +1.849 |
chamber | +1.822 |
Cantor | +1.791 |
Neg logit contributions | |
aredevil | -1.901 |
vez | -1.792 |
rams | -1.688 |
emies | -1.650 |
irez | -1.594 |
Token | the |
Token ID | 262 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Sigma | +4.657 |
Lange | +3.719 |
alist | +3.663 |
chamber | +3.621 |
Cantor | +3.575 |
Neg logit contributions | |
aredevil | -4.839 |
vez | -4.535 |
rams | -4.401 |
emies | -4.291 |
irez | -4.271 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
Sigma | +1.203 |
Lange | +0.984 |
alist | +0.982 |
Cantor | +0.948 |
chamber | +0.938 |
Neg logit contributions | |
aredevil | -1.082 |
vez | -1.020 |
rams | -0.985 |
emies | -0.954 |
irez | -0.927 |
Token | pieces |
Token ID | 5207 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
aredevil | +0.294 |
vez | +0.280 |
rams | +0.271 |
emies | +0.262 |
subp | +0.255 |
Neg logit contributions | |
Sigma | -0.284 |
Lange | -0.230 |
alist | -0.230 |
Cantor | -0.220 |
sonian | -0.217 |
Token | on |
Token ID | 261 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Sigma | +0.569 |
alist | +0.479 |
Lange | +0.476 |
Cantor | +0.461 |
sonian | +0.451 |
Neg logit contributions | |
aredevil | -0.435 |
vez | -0.411 |
rams | -0.393 |
emies | -0.378 |
subp | -0.372 |
Token | � |
Token ID | 447 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Sigma | +2.479 |
alist | +1.955 |
Lange | +1.936 |
Cantor | +1.847 |
chamber | +1.836 |
Neg logit contributions | |
aredevil | -3.257 |
vez | -3.094 |
rams | -3.025 |
subp | -2.869 |
emies | -2.859 |
Token | � |
Token ID | 247 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Sigma | +1.256 |
Lange | +1.101 |
alist | +1.086 |
Cantor | +1.056 |
chamber | +1.044 |
Neg logit contributions | |
aredevil | -0.618 |
vez | -0.554 |
rams | -0.531 |
emies | -0.499 |
subp | -0.479 |
Token | t |
Token ID | 83 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Sigma | +0.966 |
alist | +0.769 |
Lange | +0.767 |
Cantor | +0.735 |
chamber | +0.720 |
Neg logit contributions | |
aredevil | -1.174 |
vez | -1.110 |
rams | -1.076 |
emies | -1.049 |
subp | -1.025 |
Token | this |
Token ID | 428 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Sigma | +1.335 |
Lange | +1.114 |
alist | +1.099 |
Cantor | +1.069 |
chamber | +1.051 |
Neg logit contributions | |
aredevil | -1.070 |
vez | -1.009 |
rams | -0.967 |
emies | -0.933 |
subp | -0.910 |
Token | impact |
Token ID | 2928 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Sigma | +1.400 |
Lange | +1.131 |
alist | +1.123 |
Cantor | +1.083 |
chamber | +1.066 |
Neg logit contributions | |
aredevil | -1.489 |
vez | -1.413 |
rams | -1.368 |
emies | -1.327 |
subp | -1.288 |
Token | on |
Token ID | 319 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Sigma | +5.391 |
Lange | +4.318 |
alist | +4.313 |
Cantor | +4.175 |
chamber | +4.160 |
Neg logit contributions | |
aredevil | -5.873 |
vez | -5.560 |
rams | -5.321 |
emies | -5.171 |
subp | -5.056 |
Token | your |
Token ID | 534 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Sigma | +1.624 |
Lange | +1.332 |
alist | +1.318 |
Cantor | +1.278 |
chamber | +1.262 |
Neg logit contributions | |
aredevil | -1.505 |
vez | -1.418 |
rams | -1.366 |
emies | -1.324 |
irez | -1.283 |
Token | career |
Token ID | 3451 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Sigma | +0.879 |
Lange | +0.695 |
alist | +0.691 |
Cantor | +0.666 |
chamber | +0.661 |
Neg logit contributions | |
aredevil | -1.026 |
vez | -0.973 |
rams | -0.941 |
emies | -0.913 |
irez | -0.892 |
Token | ? |
Token ID | 30 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
Sigma | +0.742 |
alist | +0.609 |
Lange | +0.604 |
Cantor | +0.584 |
chamber | +0.577 |
Neg logit contributions | |
aredevil | -0.698 |
vez | -0.659 |
rams | -0.639 |
emies | -0.616 |
irez | -0.597 |
Token | Won |
Token ID | 23306 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
aredevil | +0.326 |
vez | +0.311 |
rams | +0.300 |
emies | +0.291 |
subp | +0.283 |
Neg logit contributions | |
Sigma | -0.320 |
Lange | -0.259 |
alist | -0.258 |
Cantor | -0.249 |
sonian | -0.243 |
Token | struggling |
Token ID | 9648 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
aredevil | +1.131 |
vez | +1.078 |
rams | +1.043 |
emies | +1.009 |
subp | +0.982 |
Neg logit contributions | |
Sigma | -1.129 |
alist | -0.918 |
Lange | -0.915 |
Cantor | -0.879 |
sonian | -0.868 |
Token | ." |
Token ID | 526 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
aredevil | +0.107 |
vez | +0.102 |
rams | +0.099 |
emies | +0.096 |
subp | +0.093 |
Neg logit contributions | |
Sigma | -0.097 |
Lange | -0.078 |
alist | -0.078 |
Cantor | -0.075 |
sonian | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
aredevil | +1.383 |
vez | +1.316 |
rams | +1.271 |
emies | +1.220 |
subp | +1.180 |
Neg logit contributions | |
Sigma | -1.655 |
alist | -1.372 |
Lange | -1.365 |
Cantor | -1.315 |
sonian | -1.304 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
aredevil | +0.666 |
vez | +0.633 |
rams | +0.610 |
emies | +0.590 |
subp | +0.568 |
Neg logit contributions | |
Sigma | -0.810 |
Lange | -0.674 |
alist | -0.672 |
Cantor | -0.647 |
sonian | -0.638 |
Token | After |
Token ID | 3260 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
aredevil | +0.385 |
vez | +0.365 |
rams | +0.352 |
emies | +0.343 |
subp | +0.336 |
Neg logit contributions | |
Sigma | -0.371 |
alist | -0.303 |
Lange | -0.301 |
Cantor | -0.289 |
sonian | -0.284 |
Token | consulting |
Token ID | 18158 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
aredevil | +0.635 |
vez | +0.605 |
rams | +0.585 |
emies | +0.567 |
subp | +0.551 |
Neg logit contributions | |
Sigma | -0.606 |
Lange | -0.490 |
alist | -0.490 |
Cantor | -0.469 |
sonian | -0.460 |
Token | Sty |
Token ID | 42378 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Sigma | +5.118 |
Lange | +4.224 |
alist | +4.047 |
Cantor | +4.009 |
Sachs | +3.931 |
Neg logit contributions | |
aredevil | -6.140 |
vez | -5.744 |
rams | -5.556 |
emies | -5.530 |
irez | -5.432 |
Token | ra |
Token ID | 430 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Sigma | +0.863 |
alist | +0.733 |
Lange | +0.721 |
Cantor | +0.696 |
sonian | +0.691 |
Neg logit contributions | |
aredevil | -0.670 |
vez | -0.628 |
rams | -0.599 |
emies | -0.588 |
subp | -0.579 |
Token | Av |
Token ID | 5184 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aredevil | +0.073 |
vez | +0.069 |
rams | +0.067 |
emies | +0.065 |
subp | +0.063 |
Neg logit contributions | |
Sigma | -0.068 |
Lange | -0.055 |
alist | -0.055 |
Cantor | -0.053 |
Sachs | -0.051 |
Token | ins |
Token ID | 1040 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Sigma | +4.041 |
alist | +3.460 |
Lange | +3.413 |
Cantor | +3.285 |
sonian | +3.242 |
Neg logit contributions | |
aredevil | -2.993 |
vez | -2.766 |
rams | -2.596 |
emies | -2.580 |
subp | -2.570 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Sigma | +0.608 |
Lange | +0.495 |
alist | +0.494 |
Cantor | +0.475 |
Sachs | +0.465 |
Neg logit contributions | |
aredevil | -0.616 |
vez | -0.585 |
rams | -0.565 |
emies | -0.549 |
subp | -0.535 |
Token | � |
Token ID | 250 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
Sigma | +0.403 |
Lange | +0.352 |
alist | +0.350 |
Cantor | +0.341 |
Sachs | +0.337 |
Neg logit contributions | |
aredevil | -0.162 |
vez | -0.145 |
rams | -0.139 |
emies | -0.129 |
subp | -0.122 |
Token | It |
Token ID | 1026 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
aredevil | +0.115 |
vez | +0.109 |
rams | +0.106 |
emies | +0.102 |
subp | +0.100 |
Neg logit contributions | |
Sigma | -0.113 |
Lange | -0.092 |
alist | -0.092 |
Cantor | -0.088 |
Sachs | -0.086 |
Token | 's |
Token ID | 338 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
aredevil | +1.837 |
vez | +1.763 |
rams | +1.694 |
emies | +1.649 |
subp | +1.598 |
Neg logit contributions | |
Sigma | -1.876 |
Lange | -1.523 |
alist | -1.515 |
Cantor | -1.467 |
sonian | -1.442 |
Token | not |
Token ID | 407 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
Sigma | +0.395 |
Lange | +0.320 |
alist | +0.318 |
Cantor | +0.307 |
Sachs | +0.300 |
Neg logit contributions | |
aredevil | -0.409 |
vez | -0.389 |
rams | -0.377 |
emies | -0.365 |
subp | -0.354 |
Token | economically |
Token ID | 20324 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
aredevil | +0.310 |
vez | +0.295 |
rams | +0.286 |
emies | +0.277 |
subp | +0.269 |
Neg logit contributions | |
Sigma | -0.295 |
Lange | -0.239 |
alist | -0.238 |
Cantor | -0.229 |
Sachs | -0.224 |
Token | wise |
Token ID | 10787 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
aredevil | +0.229 |
vez | +0.218 |
rams | +0.211 |
emies | +0.204 |
subp | +0.198 |
Neg logit contributions | |
Sigma | -0.229 |
Lange | -0.186 |
alist | -0.186 |
Cantor | -0.179 |
Sachs | -0.175 |
Token | to |
Token ID | 284 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Sigma | +4.827 |
alist | +3.792 |
Lange | +3.742 |
chamber | +3.566 |
Cantor | +3.562 |
Neg logit contributions | |
aredevil | -6.304 |
vez | -5.945 |
rams | -5.756 |
emies | -5.582 |
irez | -5.478 |
Token | have |
Token ID | 423 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Sigma | +1.819 |
alist | +1.468 |
Lange | +1.463 |
Cantor | +1.403 |
chamber | +1.381 |
Neg logit contributions | |
aredevil | -1.921 |
vez | -1.831 |
rams | -1.770 |
emies | -1.711 |
subp | -1.661 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Sigma | +0.344 |
Lange | +0.276 |
alist | +0.275 |
Cantor | +0.264 |
Sachs | +0.258 |
Neg logit contributions | |
aredevil | -0.383 |
vez | -0.365 |
rams | -0.353 |
emies | -0.343 |
subp | -0.333 |
Token | gang |
Token ID | 7706 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Sigma | +0.369 |
Lange | +0.298 |
alist | +0.297 |
Cantor | +0.285 |
chamber | +0.280 |
Neg logit contributions | |
aredevil | -0.388 |
vez | -0.369 |
rams | -0.358 |
emies | -0.346 |
subp | -0.337 |
Token | war |
Token ID | 1175 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
aredevil | +0.535 |
vez | +0.509 |
rams | +0.492 |
emies | +0.475 |
subp | +0.462 |
Neg logit contributions | |
Sigma | -0.558 |
alist | -0.456 |
Lange | -0.456 |
Cantor | -0.438 |
sonian | -0.430 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
aredevil | +1.582 |
vez | +1.512 |
rams | +1.457 |
emies | +1.415 |
subp | +1.378 |
Neg logit contributions | |
Sigma | -1.590 |
alist | -1.308 |
Lange | -1.292 |
Cantor | -1.241 |
sonian | -1.223 |
Token | The |
Token ID | 383 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Sigma | +0.885 |
Lange | +0.701 |
alist | +0.693 |
Cantor | +0.667 |
Sachs | +0.651 |
Neg logit contributions | |
aredevil | -1.082 |
vez | -1.035 |
rams | -1.004 |
emies | -0.974 |
subp | -0.950 |
Token | Kepler |
Token ID | 40294 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
Sigma | +1.013 |
Lange | +0.818 |
alist | +0.805 |
Cantor | +0.779 |
chamber | +0.767 |
Neg logit contributions | |
aredevil | -1.059 |
vez | -1.009 |
rams | -0.982 |
emies | -0.949 |
irez | -0.919 |
Token | - |
Token ID | 12 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
aredevil | +0.098 |
vez | +0.093 |
rams | +0.089 |
emies | +0.086 |
subp | +0.083 |
Neg logit contributions | |
Sigma | -0.128 |
Lange | -0.106 |
alist | -0.106 |
Cantor | -0.102 |
sonian | -0.101 |
Token | 10 |
Token ID | 940 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Sigma | +1.108 |
alist | +0.896 |
Lange | +0.895 |
Cantor | +0.855 |
sonian | +0.847 |
Neg logit contributions | |
aredevil | -1.173 |
vez | -1.113 |
rams | -1.075 |
emies | -1.046 |
subp | -1.022 |
Token | planetary |
Token ID | 27047 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Sigma | +1.879 |
Lange | +1.500 |
alist | +1.488 |
Cantor | +1.432 |
chamber | +1.424 |
Neg logit contributions | |
aredevil | -2.084 |
vez | -1.963 |
rams | -1.918 |
emies | -1.856 |
irez | -1.813 |
Token | system |
Token ID | 1080 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Sigma | +4.524 |
Lange | +3.521 |
alist | +3.425 |
chamber | +3.424 |
sonian | +3.217 |
Neg logit contributions | |
aredevil | -6.572 |
vez | -6.195 |
rams | -6.166 |
emies | -5.864 |
irez | -5.823 |
Token | revis |
Token ID | 22124 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Sigma | +1.939 |
Lange | +1.571 |
alist | +1.550 |
Cantor | +1.493 |
chamber | +1.480 |
Neg logit contributions | |
aredevil | -2.063 |
vez | -1.965 |
rams | -1.912 |
emies | -1.854 |
irez | -1.804 |
Token | ited |
Token ID | 863 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
Sigma | +1.339 |
alist | +1.063 |
Lange | +1.030 |
Cantor | +0.983 |
sonian | +0.959 |
Neg logit contributions | |
aredevil | -1.975 |
vez | -1.885 |
rams | -1.826 |
emies | -1.793 |
subp | -1.759 |
Token | by |
Token ID | 416 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Sigma | +0.831 |
Lange | +0.672 |
alist | +0.670 |
Cantor | +0.644 |
chamber | +0.630 |
Neg logit contributions | |
aredevil | -0.868 |
vez | -0.825 |
rams | -0.799 |
emies | -0.776 |
irez | -0.752 |
Token | HAR |
Token ID | 43638 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Sigma | +0.448 |
alist | +0.358 |
Lange | +0.358 |
Cantor | +0.342 |
sonian | +0.336 |
Neg logit contributions | |
aredevil | -0.512 |
vez | -0.490 |
rams | -0.474 |
emies | -0.460 |
subp | -0.448 |
Token | owns |
Token ID | 12216 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
aredevil | +1.075 |
vez | +1.025 |
rams | +0.992 |
emies | +0.962 |
subp | +0.935 |
Neg logit contributions | |
Sigma | -1.002 |
alist | -0.808 |
Lange | -0.807 |
Cantor | -0.773 |
sonian | -0.760 |
Token | in |
Token ID | 287 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
Sigma | +0.694 |
alist | +0.557 |
Lange | +0.557 |
Cantor | +0.536 |
chamber | +0.523 |
Neg logit contributions | |
aredevil | -0.766 |
vez | -0.729 |
rams | -0.708 |
emies | -0.687 |
irez | -0.666 |
Token | partnership |
Token ID | 10413 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
aredevil | +0.130 |
vez | +0.124 |
rams | +0.120 |
emies | +0.117 |
subp | +0.113 |
Neg logit contributions | |
Sigma | -0.114 |
Lange | -0.091 |
alist | -0.091 |
Cantor | -0.088 |
sonian | -0.085 |
Token | with |
Token ID | 351 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Sigma | +1.902 |
alist | +1.513 |
Lange | +1.505 |
Cantor | +1.441 |
Sachs | +1.407 |
Neg logit contributions | |
aredevil | -2.335 |
vez | -2.237 |
rams | -2.161 |
emies | -2.101 |
irez | -2.044 |
Token | V |
Token ID | 569 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Sigma | +1.053 |
Lange | +0.840 |
alist | +0.834 |
Cantor | +0.808 |
Sachs | +0.786 |
Neg logit contributions | |
aredevil | -1.214 |
vez | -1.158 |
rams | -1.123 |
emies | -1.092 |
subp | -1.061 |
Token | orn |
Token ID | 1211 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Sigma | +2.118 |
Lange | +1.733 |
alist | +1.715 |
Cantor | +1.651 |
Sachs | +1.627 |
Neg logit contributions | |
aredevil | -2.081 |
vez | -1.956 |
rams | -1.881 |
emies | -1.853 |
subp | -1.840 |
Token | ado |
Token ID | 4533 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Sigma | +5.144 |
Lange | +4.172 |
alist | +4.142 |
Cantor | +4.007 |
Sachs | +3.908 |
Neg logit contributions | |
aredevil | -6.020 |
vez | -5.530 |
rams | -5.522 |
emies | -5.349 |
subp | -5.305 |
Token | Re |
Token ID | 797 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Sigma | +0.353 |
Lange | +0.284 |
alist | +0.283 |
Cantor | +0.273 |
Sachs | +0.266 |
Neg logit contributions | |
aredevil | -0.391 |
vez | -0.372 |
rams | -0.361 |
emies | -0.349 |
subp | -0.340 |
Token | alty |
Token ID | 6017 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Sigma | +0.653 |
Lange | +0.535 |
alist | +0.535 |
Cantor | +0.514 |
sonian | +0.504 |
Neg logit contributions | |
aredevil | -0.600 |
vez | -0.568 |
rams | -0.548 |
emies | -0.531 |
subp | -0.516 |
Token | Trust |
Token ID | 9870 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
aredevil | +1.694 |
vez | +1.617 |
rams | +1.562 |
emies | +1.517 |
subp | +1.474 |
Neg logit contributions | |
Sigma | -1.675 |
alist | -1.361 |
Lange | -1.359 |
Cantor | -1.298 |
sonian | -1.287 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
Sigma | +1.048 |
Lange | +0.844 |
alist | +0.839 |
Cantor | +0.820 |
Sachs | +0.799 |
Neg logit contributions | |
aredevil | -1.146 |
vez | -1.086 |
rams | -1.047 |
emies | -1.009 |
irez | -0.989 |
Token | � |
Token ID | 247 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
aredevil | +0.136 |
vez | +0.123 |
rams | +0.120 |
emies | +0.115 |
subp | +0.110 |
Neg logit contributions | |
Sigma | -0.201 |
Lange | -0.171 |
alist | -0.169 |
Cantor | -0.165 |
sonian | -0.162 |
Token | t |
Token ID | 83 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Sigma | +0.519 |
alist | +0.414 |
Lange | +0.412 |
Cantor | +0.395 |
chamber | +0.387 |
Neg logit contributions | |
aredevil | -0.608 |
vez | -0.575 |
rams | -0.557 |
emies | -0.542 |
subp | -0.530 |
Token | make |
Token ID | 787 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Sigma | +0.430 |
Lange | +0.348 |
alist | +0.348 |
Cantor | +0.333 |
sonian | +0.327 |
Neg logit contributions | |
aredevil | -0.445 |
vez | -0.425 |
rams | -0.411 |
emies | -0.398 |
subp | -0.387 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Sigma | +0.599 |
Lange | +0.485 |
alist | +0.481 |
Cantor | +0.465 |
Sachs | +0.454 |
Neg logit contributions | |
aredevil | -0.637 |
vez | -0.607 |
rams | -0.588 |
emies | -0.570 |
irez | -0.552 |
Token | same |
Token ID | 976 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Sigma | +0.367 |
Lange | +0.300 |
alist | +0.298 |
Cantor | +0.288 |
chamber | +0.282 |
Neg logit contributions | |
aredevil | -0.368 |
vez | -0.350 |
rams | -0.338 |
emies | -0.327 |
irez | -0.317 |
Token | mistake |
Token ID | 7457 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Sigma | +0.390 |
Lange | +0.297 |
alist | +0.295 |
Cantor | +0.281 |
chamber | +0.273 |
Neg logit contributions | |
aredevil | -0.615 |
vez | -0.592 |
rams | -0.575 |
emies | -0.560 |
irez | -0.547 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Sigma | +5.030 |
Lange | +4.084 |
alist | +3.952 |
Cantor | +3.912 |
chamber | +3.765 |
Neg logit contributions | |
aredevil | -5.991 |
vez | -5.639 |
rams | -5.472 |
emies | -5.315 |
irez | -5.258 |
Token | The |
Token ID | 383 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Sigma | +0.643 |
Lange | +0.524 |
alist | +0.517 |
Cantor | +0.503 |
Sachs | +0.490 |
Neg logit contributions | |
aredevil | -0.650 |
vez | -0.617 |
rams | -0.599 |
emies | -0.578 |
subp | -0.565 |
Token | high |
Token ID | 1029 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Sigma | +0.746 |
Lange | +0.599 |
alist | +0.597 |
Cantor | +0.574 |
chamber | +0.561 |
Neg logit contributions | |
aredevil | -0.836 |
vez | -0.798 |
rams | -0.774 |
emies | -0.749 |
subp | -0.728 |
Token | point |
Token ID | 966 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
Sigma | +1.604 |
Lange | +1.310 |
alist | +1.308 |
Cantor | +1.263 |
chamber | +1.246 |
Neg logit contributions | |
aredevil | -1.549 |
vez | -1.475 |
rams | -1.421 |
emies | -1.370 |
irez | -1.337 |
Token | of |
Token ID | 286 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
aredevil | +0.183 |
vez | +0.173 |
rams | +0.167 |
emies | +0.161 |
subp | +0.156 |
Neg logit contributions | |
Sigma | -0.215 |
Lange | -0.178 |
alist | -0.178 |
Cantor | -0.172 |
sonian | -0.169 |
Token | them |
Token ID | 606 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
aredevil | +0.010 |
vez | +0.010 |
rams | +0.009 |
emies | +0.009 |
subp | +0.009 |
Neg logit contributions | |
Sigma | -0.010 |
Lange | -0.008 |
alist | -0.008 |
Cantor | -0.007 |
Sachs | -0.007 |
Token | for |
Token ID | 329 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Sigma | +0.027 |
Lange | +0.022 |
alist | +0.022 |
Cantor | +0.021 |
sonian | +0.020 |
Neg logit contributions | |
aredevil | -0.027 |
vez | -0.026 |
rams | -0.025 |
emies | -0.024 |
subp | -0.024 |
Token | their |
Token ID | 511 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Sigma | +0.590 |
Lange | +0.480 |
alist | +0.479 |
Cantor | +0.461 |
Sachs | +0.451 |
Neg logit contributions | |
aredevil | -0.587 |
vez | -0.559 |
rams | -0.540 |
emies | -0.522 |
irez | -0.506 |
Token | inability |
Token ID | 16612 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Sigma | +0.847 |
Lange | +0.682 |
alist | +0.680 |
Cantor | +0.654 |
chamber | +0.640 |
Neg logit contributions | |
aredevil | -0.923 |
vez | -0.880 |
rams | -0.852 |
emies | -0.827 |
subp | -0.800 |
Token | to |
Token ID | 284 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Sigma | +0.784 |
Lange | +0.628 |
alist | +0.627 |
Cantor | +0.600 |
sonian | +0.589 |
Neg logit contributions | |
aredevil | -0.885 |
vez | -0.844 |
rams | -0.817 |
emies | -0.794 |
subp | -0.774 |
Token | answer |
Token ID | 3280 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Sigma | +1.975 |
alist | +1.577 |
Lange | +1.569 |
Cantor | +1.501 |
chamber | +1.493 |
Neg logit contributions | |
aredevil | -2.288 |
vez | -2.193 |
rams | -2.122 |
emies | -2.057 |
irez | -2.003 |
Token | his |
Token ID | 465 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
Sigma | +4.717 |
Lange | +3.692 |
alist | +3.599 |
Cantor | +3.538 |
Sachs | +3.493 |
Neg logit contributions | |
aredevil | -6.281 |
vez | -5.850 |
rams | -5.772 |
emies | -5.685 |
irez | -5.539 |
Token | questions |
Token ID | 2683 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Sigma | +2.652 |
Lange | +2.091 |
alist | +2.080 |
Cantor | +2.012 |
chamber | +1.979 |
Neg logit contributions | |
aredevil | -3.317 |
vez | -3.168 |
rams | -3.058 |
emies | -2.990 |
irez | -2.934 |
Token | — |
Token ID | 960 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Sigma | +1.771 |
Lange | +1.422 |
alist | +1.415 |
Cantor | +1.361 |
chamber | +1.338 |
Neg logit contributions | |
aredevil | -1.978 |
vez | -1.877 |
rams | -1.823 |
emies | -1.772 |
irez | -1.718 |
Token | many |
Token ID | 21834 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Sigma | +0.483 |
alist | +0.392 |
Lange | +0.389 |
Cantor | +0.373 |
sonian | +0.365 |
Neg logit contributions | |
aredevil | -0.518 |
vez | -0.492 |
rams | -0.475 |
emies | -0.462 |
subp | -0.451 |
Token | of |
Token ID | 286 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Sigma | +0.685 |
Lange | +0.568 |
alist | +0.565 |
Cantor | +0.546 |
chamber | +0.537 |
Neg logit contributions | |
aredevil | -0.583 |
vez | -0.554 |
rams | -0.534 |
emies | -0.514 |
subp | -0.496 |
Token | analysts |
Token ID | 13440 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Sigma | +0.026 |
Lange | +0.021 |
alist | +0.021 |
Cantor | +0.020 |
sonian | +0.019 |
Neg logit contributions | |
aredevil | -0.027 |
vez | -0.026 |
rams | -0.025 |
emies | -0.024 |
subp | -0.023 |
Token | try |
Token ID | 1949 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
aredevil | +1.186 |
vez | +1.131 |
rams | +1.094 |
emies | +1.063 |
subp | +1.036 |
Neg logit contributions | |
Sigma | -1.098 |
Lange | -0.888 |
alist | -0.886 |
Cantor | -0.845 |
sonian | -0.833 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aredevil | +1.690 |
vez | +1.598 |
rams | +1.559 |
emies | +1.505 |
subp | +1.479 |
Neg logit contributions | |
Sigma | -1.621 |
Lange | -1.311 |
alist | -1.297 |
Cantor | -1.245 |
sonian | -1.224 |
Token | gauge |
Token ID | 18266 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
aredevil | +0.482 |
vez | +0.457 |
rams | +0.446 |
emies | +0.430 |
subp | +0.422 |
Neg logit contributions | |
Sigma | -0.447 |
Lange | -0.362 |
alist | -0.359 |
Cantor | -0.346 |
sonian | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Sigma | +1.390 |
alist | +1.102 |
Lange | +1.101 |
Cantor | +1.054 |
Sachs | +1.028 |
Neg logit contributions | |
aredevil | -1.675 |
vez | -1.603 |
rams | -1.553 |
emies | -1.512 |
subp | -1.465 |
Token | impact |
Token ID | 2928 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Sigma | +1.366 |
Lange | +1.088 |
alist | +1.080 |
Cantor | +1.042 |
chamber | +1.027 |
Neg logit contributions | |
aredevil | -1.562 |
vez | -1.490 |
rams | -1.439 |
emies | -1.402 |
irez | -1.361 |
Token | on |
Token ID | 319 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Sigma | +5.618 |
Lange | +4.553 |
alist | +4.534 |
Cantor | +4.470 |
chamber | +4.387 |
Neg logit contributions | |
aredevil | -5.266 |
vez | -5.125 |
rams | -4.839 |
emies | -4.687 |
irez | -4.584 |
Token | Ireland |
Token ID | 7517 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
Sigma | +0.415 |
alist | +0.333 |
Lange | +0.333 |
Cantor | +0.318 |
sonian | +0.312 |
Neg logit contributions | |
aredevil | -0.468 |
vez | -0.447 |
rams | -0.433 |
emies | -0.420 |
subp | -0.409 |
Token | from |
Token ID | 422 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
aredevil | +0.271 |
vez | +0.258 |
rams | +0.249 |
emies | +0.241 |
subp | +0.234 |
Neg logit contributions | |
Sigma | -0.272 |
alist | -0.221 |
Lange | -0.221 |
Cantor | -0.212 |
sonian | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
Sigma | +1.183 |
Lange | +0.938 |
alist | +0.937 |
Cantor | +0.898 |
chamber | +0.876 |
Neg logit contributions | |
aredevil | -1.433 |
vez | -1.368 |
rams | -1.323 |
emies | -1.287 |
subp | -1.250 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
aredevil | +0.140 |
vez | +0.134 |
rams | +0.130 |
emies | +0.126 |
subp | +0.123 |
Neg logit contributions | |
Sigma | -0.124 |
Lange | -0.099 |
alist | -0.099 |
Cantor | -0.095 |
sonian | -0.093 |
Token | do |
Token ID | 466 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Sigma | +0.051 |
Lange | +0.041 |
alist | +0.041 |
Cantor | +0.039 |
sonian | +0.038 |
Neg logit contributions | |
aredevil | -0.056 |
vez | -0.054 |
rams | -0.052 |
emies | -0.050 |
subp | -0.049 |
Token | most |
Token ID | 749 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
aredevil | +1.138 |
vez | +1.092 |
rams | +1.055 |
emies | +1.020 |
subp | +1.002 |
Neg logit contributions | |
Sigma | -0.997 |
alist | -0.802 |
Lange | -0.801 |
Cantor | -0.764 |
sonian | -0.752 |
Token | of |
Token ID | 286 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Sigma | +0.740 |
Lange | +0.610 |
alist | +0.609 |
Cantor | +0.589 |
chamber | +0.581 |
Neg logit contributions | |
aredevil | -0.610 |
vez | -0.579 |
rams | -0.558 |
emies | -0.539 |
irez | -0.517 |
Token | our |
Token ID | 674 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Sigma | +0.621 |
Lange | +0.488 |
alist | +0.488 |
Cantor | +0.466 |
sonian | +0.454 |
Neg logit contributions | |
aredevil | -0.782 |
vez | -0.747 |
rams | -0.727 |
emies | -0.707 |
subp | -0.685 |
Token | optical |
Token ID | 18480 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
Sigma | +2.366 |
Lange | +1.875 |
alist | +1.862 |
Cantor | +1.801 |
chamber | +1.788 |
Neg logit contributions | |
aredevil | -2.603 |
vez | -2.475 |
rams | -2.399 |
emies | -2.336 |
irez | -2.265 |
Token | adjustments |
Token ID | 16895 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Sigma | +2.145 |
Lange | +1.703 |
alist | +1.700 |
Cantor | +1.626 |
chamber | +1.620 |
Neg logit contributions | |
aredevil | -2.477 |
vez | -2.373 |
rams | -2.289 |
emies | -2.223 |
irez | -2.168 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Sigma | +5.000 |
alist | +3.908 |
Lange | +3.902 |
chamber | +3.772 |
Cantor | +3.731 |
Neg logit contributions | |
aredevil | -5.946 |
vez | -5.658 |
rams | -5.480 |
emies | -5.347 |
irez | -5.232 |
Token | from |
Token ID | 422 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Sigma | +0.388 |
Lange | +0.309 |
alist | +0.309 |
Cantor | +0.295 |
sonian | +0.289 |
Neg logit contributions | |
aredevil | -0.458 |
vez | -0.438 |
rams | -0.425 |
emies | -0.412 |
subp | -0.402 |
Token | long |
Token ID | 890 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Sigma | +1.425 |
Lange | +1.143 |
alist | +1.136 |
Cantor | +1.092 |
chamber | +1.072 |
Neg logit contributions | |
aredevil | -1.532 |
vez | -1.462 |
rams | -1.416 |
emies | -1.374 |
irez | -1.333 |
Token | experience |
Token ID | 1998 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Sigma | +0.584 |
Lange | +0.453 |
alist | +0.453 |
Cantor | +0.430 |
sonian | +0.422 |
Neg logit contributions | |
aredevil | -0.794 |
vez | -0.761 |
rams | -0.738 |
emies | -0.719 |
subp | -0.700 |
Token | I |
Token ID | 314 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Sigma | +0.762 |
Lange | +0.616 |
alist | +0.614 |
Cantor | +0.590 |
sonian | +0.578 |
Neg logit contributions | |
aredevil | -0.790 |
vez | -0.753 |
rams | -0.728 |
emies | -0.706 |
subp | -0.684 |
Token | face |
Token ID | 1986 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Sigma | +2.081 |
Lange | +1.653 |
alist | +1.638 |
Cantor | +1.582 |
chamber | +1.579 |
Neg logit contributions | |
aredevil | -2.371 |
vez | -2.248 |
rams | -2.177 |
emies | -2.125 |
irez | -2.062 |
Token | gently |
Token ID | 15165 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Sigma | +1.792 |
Lange | +1.448 |
alist | +1.434 |
Cantor | +1.380 |
chamber | +1.365 |
Neg logit contributions | |
aredevil | -2.001 |
vez | -1.898 |
rams | -1.849 |
emies | -1.778 |
irez | -1.740 |
Token | with |
Token ID | 351 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
Sigma | +4.186 |
Lange | +3.370 |
alist | +3.323 |
Cantor | +3.218 |
chamber | +3.204 |
Neg logit contributions | |
aredevil | -5.019 |
vez | -4.705 |
rams | -4.607 |
emies | -4.417 |
irez | -4.358 |
Token | his |
Token ID | 465 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
aredevil | +0.175 |
vez | +0.167 |
rams | +0.162 |
emies | +0.158 |
subp | +0.153 |
Neg logit contributions | |
Sigma | -0.139 |
Lange | -0.110 |
alist | -0.109 |
Cantor | -0.104 |
sonian | -0.102 |
Token | boxing |
Token ID | 21576 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Sigma | +1.580 |
Lange | +1.275 |
alist | +1.265 |
Cantor | +1.223 |
chamber | +1.206 |
Neg logit contributions | |
aredevil | -1.619 |
vez | -1.535 |
rams | -1.482 |
emies | -1.444 |
irez | -1.399 |
Token | glove |
Token ID | 29144 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Sigma | +2.334 |
Lange | +1.794 |
alist | +1.764 |
Cantor | +1.701 |
chamber | +1.686 |
Neg logit contributions | |
aredevil | -3.273 |
vez | -3.132 |
rams | -3.024 |
emies | -2.970 |
irez | -2.893 |
Token | � |
Token ID | 447 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Sigma | +4.889 |
Lange | +3.863 |
alist | +3.798 |
chamber | +3.678 |
Cantor | +3.664 |
Neg logit contributions | |
aredevil | -5.907 |
vez | -5.631 |
rams | -5.446 |
emies | -5.250 |
subp | -5.159 |
Token | � |
Token ID | 247 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Sigma | +1.761 |
Lange | +1.517 |
alist | +1.507 |
Cantor | +1.463 |
chamber | +1.443 |
Neg logit contributions | |
aredevil | -1.018 |
vez | -0.927 |
rams | -0.892 |
emies | -0.850 |
subp | -0.816 |
Token | s |
Token ID | 82 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Sigma | +0.804 |
Lange | +0.653 |
alist | +0.649 |
Cantor | +0.626 |
chamber | +0.613 |
Neg logit contributions | |
aredevil | -0.828 |
vez | -0.786 |
rams | -0.760 |
emies | -0.735 |
subp | -0.716 |
Token | padded |
Token ID | 44582 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
aredevil | +0.050 |
vez | +0.048 |
rams | +0.046 |
emies | +0.045 |
subp | +0.043 |
Neg logit contributions | |
Sigma | -0.050 |
Lange | -0.041 |
alist | -0.041 |
Cantor | -0.039 |
sonian | -0.039 |
Token | red |
Token ID | 2266 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Sigma | +1.665 |
Lange | +1.333 |
alist | +1.319 |
Cantor | +1.271 |
chamber | +1.263 |
Neg logit contributions | |
aredevil | -1.825 |
vez | -1.739 |
rams | -1.684 |
emies | -1.636 |
irez | -1.595 |
Token | officer |
Token ID | 3818 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
Sigma | +1.207 |
alist | +1.012 |
Lange | +1.011 |
Cantor | +0.979 |
Sachs | +0.962 |
Neg logit contributions | |
aredevil | -0.892 |
vez | -0.844 |
rams | -0.811 |
emies | -0.780 |
subp | -0.752 |
Token | ; |
Token ID | 26 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
aredevil | +0.238 |
vez | +0.228 |
rams | +0.220 |
emies | +0.213 |
subp | +0.208 |
Neg logit contributions | |
Sigma | -0.217 |
Lange | -0.175 |
alist | -0.174 |
Cantor | -0.167 |
sonian | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Sigma | +2.864 |
Lange | +2.316 |
alist | +2.278 |
Cantor | +2.259 |
Sachs | +2.216 |
Neg logit contributions | |
aredevil | -3.008 |
vez | -2.868 |
rams | -2.775 |
emies | -2.665 |
irez | -2.622 |
Token | CEO |
Token ID | 6123 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
aredevil | +0.870 |
vez | +0.832 |
rams | +0.804 |
emies | +0.781 |
subp | +0.761 |
Neg logit contributions | |
Sigma | -0.810 |
alist | -0.658 |
Lange | -0.651 |
sonian | -0.619 |
Cantor | -0.618 |
Token | Lloyd |
Token ID | 22361 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
aredevil | +1.201 |
vez | +1.150 |
rams | +1.115 |
emies | +1.085 |
subp | +1.056 |
Neg logit contributions | |
Sigma | -1.045 |
alist | -0.841 |
Lange | -0.833 |
Cantor | -0.792 |
sonian | -0.790 |
Token | Blank |
Token ID | 31990 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Sigma | +1.605 |
Lange | +1.110 |
alist | +1.078 |
Sachs | +1.073 |
Cantor | +1.057 |
Neg logit contributions | |
aredevil | -3.606 |
vez | -3.468 |
rams | -3.355 |
irez | -3.269 |
emies | -3.269 |
Token | fe |
Token ID | 5036 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Sigma | +5.266 |
Lange | +4.258 |
alist | +4.215 |
Sachs | +4.160 |
Cantor | +4.068 |
Neg logit contributions | |
aredevil | -5.670 |
vez | -5.249 |
rams | -5.069 |
emies | -4.872 |
irez | -4.847 |
Token | in |
Token ID | 259 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
aredevil | +0.114 |
vez | +0.109 |
rams | +0.106 |
emies | +0.103 |
subp | +0.100 |
Neg logit contributions | |
Sigma | -0.087 |
Lange | -0.068 |
alist | -0.068 |
Cantor | -0.065 |
sonian | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Sigma | +0.467 |
Lange | +0.378 |
alist | +0.377 |
Cantor | +0.362 |
sonian | +0.355 |
Neg logit contributions | |
aredevil | -0.490 |
vez | -0.467 |
rams | -0.452 |
emies | -0.437 |
subp | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
Sigma | +0.602 |
Lange | +0.489 |
alist | +0.487 |
Cantor | +0.469 |
Sachs | +0.459 |
Neg logit contributions | |
aredevil | -0.616 |
vez | -0.586 |
rams | -0.567 |
emies | -0.549 |
subp | -0.535 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
aredevil | +0.081 |
vez | +0.077 |
rams | +0.074 |
emies | +0.072 |
subp | +0.069 |
Neg logit contributions | |
Sigma | -0.096 |
Lange | -0.079 |
alist | -0.079 |
Cantor | -0.076 |
sonian | -0.075 |
Token | written |
Token ID | 3194 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Sigma | +0.047 |
Lange | +0.038 |
alist | +0.037 |
Cantor | +0.036 |
chamber | +0.035 |
Neg logit contributions | |
aredevil | -0.052 |
vez | -0.050 |
rams | -0.048 |
emies | -0.047 |
irez | -0.045 |
Token | in |
Token ID | 287 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
Sigma | +0.828 |
Lange | +0.670 |
alist | +0.668 |
Cantor | +0.637 |
chamber | +0.630 |
Neg logit contributions | |
aredevil | -0.915 |
vez | -0.869 |
rams | -0.841 |
emies | -0.819 |
irez | -0.790 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Sigma | +0.254 |
Lange | +0.203 |
alist | +0.202 |
Cantor | +0.193 |
chamber | +0.189 |
Neg logit contributions | |
aredevil | -0.296 |
vez | -0.283 |
rams | -0.273 |
emies | -0.266 |
subp | -0.258 |
Token | children |
Token ID | 1751 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
Sigma | +0.398 |
Lange | +0.325 |
alist | +0.324 |
Cantor | +0.310 |
chamber | +0.306 |
Neg logit contributions | |
aredevil | -0.400 |
vez | -0.380 |
rams | -0.368 |
emies | -0.357 |
irez | -0.345 |
Token | 's |
Token ID | 338 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Sigma | +0.246 |
alist | +0.198 |
Lange | +0.198 |
Cantor | +0.189 |
sonian | +0.186 |
Neg logit contributions | |
aredevil | -0.271 |
vez | -0.259 |
rams | -0.251 |
emies | -0.243 |
subp | -0.236 |
Token | pop |
Token ID | 1461 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Sigma | +0.872 |
Lange | +0.707 |
alist | +0.706 |
Cantor | +0.674 |
chamber | +0.667 |
Neg logit contributions | |
aredevil | -0.922 |
vez | -0.879 |
rams | -0.850 |
emies | -0.826 |
irez | -0.799 |
Token | music |
Token ID | 2647 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
Sigma | +4.840 |
alist | +4.024 |
Lange | +3.976 |
chamber | +3.829 |
sonian | +3.764 |
Neg logit contributions | |
aredevil | -5.686 |
vez | -5.342 |
rams | -5.247 |
emies | -5.124 |
irez | -4.976 |
Token | style |
Token ID | 3918 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Sigma | +1.473 |
alist | +1.205 |
Lange | +1.204 |
Cantor | +1.147 |
chamber | +1.140 |
Neg logit contributions | |
aredevil | -1.491 |
vez | -1.411 |
rams | -1.368 |
emies | -1.328 |
irez | -1.283 |
Token | and |
Token ID | 290 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Sigma | +0.915 |
alist | +0.744 |
Lange | +0.743 |
Cantor | +0.710 |
chamber | +0.700 |
Neg logit contributions | |
aredevil | -0.928 |
vez | -0.883 |
rams | -0.854 |
emies | -0.828 |
irez | -0.800 |
Token | contrast |
Token ID | 6273 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Sigma | +0.611 |
Lange | +0.496 |
alist | +0.494 |
Cantor | +0.472 |
chamber | +0.465 |
Neg logit contributions | |
aredevil | -0.654 |
vez | -0.621 |
rams | -0.601 |
emies | -0.585 |
irez | -0.565 |
Token | sharply |
Token ID | 18939 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
aredevil | +1.860 |
vez | +1.776 |
rams | +1.720 |
emies | +1.666 |
subp | +1.624 |
Neg logit contributions | |
Sigma | -1.725 |
Lange | -1.387 |
alist | -1.386 |
Cantor | -1.330 |
sonian | -1.307 |
Token | Greenberg |
Token ID | 46702 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
Sigma | +0.721 |
Lange | +0.582 |
alist | +0.568 |
Cantor | +0.560 |
Sachs | +0.544 |
Neg logit contributions | |
aredevil | -0.871 |
vez | -0.828 |
rams | -0.799 |
emies | -0.783 |
subp | -0.774 |
Token | told |
Token ID | 1297 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Sigma | +2.532 |
Lange | +2.048 |
alist | +2.031 |
Cantor | +1.996 |
Sachs | +1.956 |
Neg logit contributions | |
aredevil | -2.627 |
vez | -2.447 |
rams | -2.373 |
emies | -2.303 |
irez | -2.244 |
Token | left |
Token ID | 1364 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Sigma | +0.829 |
Lange | +0.671 |
alist | +0.665 |
Cantor | +0.643 |
Sachs | +0.628 |
Neg logit contributions | |
aredevil | -0.892 |
vez | -0.848 |
rams | -0.820 |
emies | -0.795 |
subp | -0.774 |
Token | - |
Token ID | 12 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Sigma | +2.638 |
alist | +2.188 |
Lange | +2.182 |
chamber | +2.112 |
Cantor | +2.103 |
Neg logit contributions | |
aredevil | -2.202 |
vez | -2.091 |
rams | -2.001 |
emies | -1.920 |
subp | -1.878 |
Token | leaning |
Token ID | 25909 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Sigma | +0.958 |
alist | +0.746 |
Lange | +0.743 |
Cantor | +0.702 |
chamber | +0.689 |
Neg logit contributions | |
aredevil | -1.367 |
vez | -1.311 |
rams | -1.272 |
emies | -1.239 |
subp | -1.214 |
Token | Salon |
Token ID | 40121 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Sigma | +3.274 |
Lange | +2.618 |
alist | +2.592 |
Cantor | +2.531 |
chamber | +2.490 |
Neg logit contributions | |
aredevil | -3.652 |
vez | -3.473 |
rams | -3.295 |
emies | -3.238 |
irez | -3.177 |
Token | last |
Token ID | 938 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
Sigma | +4.746 |
alist | +3.772 |
Lange | +3.749 |
Cantor | +3.619 |
chamber | +3.576 |
Neg logit contributions | |
aredevil | -5.883 |
vez | -5.548 |
rams | -5.377 |
emies | -5.166 |
irez | -5.153 |
Token | week |
Token ID | 1285 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Sigma | +2.844 |
Lange | +2.286 |
alist | +2.275 |
Cantor | +2.200 |
chamber | +2.170 |
Neg logit contributions | |
aredevil | -3.092 |
vez | -2.914 |
rams | -2.805 |
emies | -2.736 |
irez | -2.673 |
Token | while |
Token ID | 981 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Sigma | +0.491 |
Lange | +0.396 |
alist | +0.396 |
Cantor | +0.379 |
sonian | +0.372 |
Neg logit contributions | |
aredevil | -0.524 |
vez | -0.499 |
rams | -0.482 |
emies | -0.468 |
subp | -0.455 |
Token | discussing |
Token ID | 11142 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Sigma | +0.753 |
Lange | +0.614 |
alist | +0.610 |
Cantor | +0.591 |
Sachs | +0.578 |
Neg logit contributions | |
aredevil | -0.749 |
vez | -0.708 |
rams | -0.684 |
emies | -0.662 |
subp | -0.643 |
Token | his |
Token ID | 465 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Sigma | +1.040 |
Lange | +0.830 |
alist | +0.829 |
Cantor | +0.795 |
Sachs | +0.776 |
Neg logit contributions | |
aredevil | -1.203 |
vez | -1.147 |
rams | -1.112 |
emies | -1.079 |
subp | -1.050 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Sigma | +0.558 |
Lange | +0.457 |
alist | +0.457 |
Cantor | +0.440 |
sonian | +0.432 |
Neg logit contributions | |
aredevil | -0.517 |
vez | -0.492 |
rams | -0.475 |
emies | -0.459 |
subp | -0.446 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Sigma | +1.023 |
Lange | +0.827 |
alist | +0.827 |
Cantor | +0.793 |
sonian | +0.779 |
Neg logit contributions | |
aredevil | -1.061 |
vez | -1.012 |
rams | -0.978 |
emies | -0.947 |
subp | -0.921 |
Token | In |
Token ID | 554 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Sigma | +1.142 |
Lange | +0.903 |
alist | +0.893 |
Cantor | +0.860 |
Sachs | +0.841 |
Neg logit contributions | |
aredevil | -1.429 |
vez | -1.370 |
rams | -1.327 |
emies | -1.289 |
subp | -1.257 |
Token | a |
Token ID | 257 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Sigma | +1.766 |
Lange | +1.379 |
alist | +1.374 |
Cantor | +1.310 |
chamber | +1.291 |
Neg logit contributions | |
aredevil | -2.294 |
vez | -2.191 |
rams | -2.134 |
emies | -2.066 |
irez | -2.015 |
Token | large |
Token ID | 1588 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Sigma | +1.298 |
alist | +0.994 |
Lange | +0.990 |
Cantor | +0.936 |
sonian | +0.913 |
Neg logit contributions | |
aredevil | -2.032 |
vez | -1.954 |
rams | -1.901 |
emies | -1.850 |
subp | -1.815 |
Token | bowl |
Token ID | 9396 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Sigma | +1.978 |
Lange | +1.320 |
alist | +1.275 |
chamber | +1.199 |
Cantor | +1.167 |
Neg logit contributions | |
aredevil | -5.210 |
vez | -5.034 |
rams | -4.922 |
emies | -4.829 |
irez | -4.722 |
Token | , |
Token ID | 11 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Sigma | +4.530 |
Lange | +3.442 |
alist | +3.441 |
chamber | +3.355 |
Cantor | +3.301 |
Neg logit contributions | |
aredevil | -6.023 |
vez | -5.722 |
rams | -5.586 |
emies | -5.363 |
subp | -5.292 |
Token | combine |
Token ID | 12082 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Sigma | +1.529 |
alist | +1.218 |
Lange | +1.215 |
chamber | +1.174 |
Cantor | +1.167 |
Neg logit contributions | |
aredevil | -1.723 |
vez | -1.632 |
rams | -1.597 |
emies | -1.531 |
subp | -1.484 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Sigma | +3.519 |
alist | +2.610 |
Lange | +2.607 |
chamber | +2.555 |
Cantor | +2.543 |
Neg logit contributions | |
aredevil | -5.358 |
vez | -5.105 |
rams | -4.969 |
irez | -4.805 |
emies | -4.801 |
Token | broccoli |
Token ID | 44653 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
Sigma | +0.792 |
alist | +0.678 |
Lange | +0.677 |
Cantor | +0.659 |
chamber | +0.651 |
Neg logit contributions | |
aredevil | -0.414 |
vez | -0.384 |
rams | -0.365 |
emies | -0.348 |
subp | -0.331 |
Token | pieces |
Token ID | 5207 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
Sigma | +0.101 |
Lange | +0.085 |
alist | +0.085 |
Cantor | +0.083 |
sonian | +0.081 |
Neg logit contributions | |
aredevil | -0.069 |
vez | -0.065 |
rams | -0.062 |
emies | -0.059 |
subp | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Sigma | +0.596 |
Lange | +0.483 |
alist | +0.481 |
Cantor | +0.462 |
chamber | +0.453 |
Neg logit contributions | |
aredevil | -0.615 |
vez | -0.584 |
rams | -0.564 |
emies | -0.548 |
subp | -0.531 |
Token | memory |
Token ID | 4088 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Sigma | +0.329 |
Lange | +0.249 |
alist | +0.249 |
Cantor | +0.236 |
sonian | +0.229 |
Neg logit contributions | |
aredevil | -0.524 |
vez | -0.503 |
rams | -0.489 |
emies | -0.477 |
subp | -0.466 |
Token | ( |
Token ID | 357 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
aredevil | +1.725 |
vez | +1.657 |
rams | +1.606 |
emies | +1.556 |
subp | +1.525 |
Neg logit contributions | |
Sigma | -1.472 |
alist | -1.177 |
Lange | -1.175 |
Cantor | -1.120 |
sonian | -1.116 |
Token | VT |
Token ID | 36392 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Sigma | +1.681 |
alist | +1.342 |
Lange | +1.334 |
Cantor | +1.278 |
sonian | +1.247 |
Neg logit contributions | |
aredevil | -1.985 |
vez | -1.896 |
rams | -1.835 |
emies | -1.796 |
subp | -1.753 |
Token | - |
Token ID | 12 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
aredevil | +1.921 |
vez | +1.800 |
rams | +1.736 |
emies | +1.661 |
subp | +1.612 |
Neg logit contributions | |
Sigma | -2.872 |
alist | -2.446 |
Lange | -2.423 |
Cantor | -2.366 |
sonian | -2.342 |
Token | x |
Token ID | 87 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Sigma | +1.384 |
alist | +1.130 |
Lange | +1.128 |
Cantor | +1.076 |
Sachs | +1.064 |
Neg logit contributions | |
aredevil | -1.324 |
vez | -1.254 |
rams | -1.212 |
emies | -1.185 |
subp | -1.148 |
Token | ), |
Token ID | 828 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Sigma | +5.271 |
Lange | +4.233 |
alist | +4.195 |
Cantor | +4.046 |
chamber | +4.027 |
Neg logit contributions | |
aredevil | -5.270 |
vez | -4.968 |
rams | -4.805 |
emies | -4.708 |
irez | -4.540 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Sigma | +0.871 |
Lange | +0.702 |
alist | +0.697 |
Cantor | +0.671 |
chamber | +0.658 |
Neg logit contributions | |
aredevil | -0.926 |
vez | -0.881 |
rams | -0.854 |
emies | -0.828 |
irez | -0.801 |
Token | using |
Token ID | 1262 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Sigma | +0.691 |
Lange | +0.556 |
alist | +0.553 |
Cantor | +0.532 |
chamber | +0.521 |
Neg logit contributions | |
aredevil | -0.753 |
vez | -0.717 |
rams | -0.695 |
emies | -0.675 |
irez | -0.653 |
Token | par |
Token ID | 1582 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Sigma | +0.193 |
Lange | +0.153 |
alist | +0.153 |
Cantor | +0.146 |
chamber | +0.143 |
Neg logit contributions | |
aredevil | -0.234 |
vez | -0.223 |
rams | -0.217 |
emies | -0.211 |
subp | -0.204 |
Token | av |
Token ID | 615 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
aredevil | +0.673 |
vez | +0.645 |
rams | +0.625 |
emies | +0.606 |
subp | +0.592 |
Neg logit contributions | |
Sigma | -0.546 |
Lange | -0.431 |
alist | -0.430 |
Cantor | -0.412 |
sonian | -0.404 |
Token | by |
Token ID | 416 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Sigma | +0.791 |
alist | +0.647 |
Lange | +0.646 |
Cantor | +0.622 |
chamber | +0.612 |
Neg logit contributions | |
aredevil | -0.727 |
vez | -0.689 |
rams | -0.664 |
emies | -0.640 |
subp | -0.624 |
Token | clicking |
Token ID | 12264 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
aredevil | +1.655 |
vez | +1.599 |
rams | +1.542 |
emies | +1.509 |
subp | +1.474 |
Neg logit contributions | |
Sigma | -1.255 |
alist | -0.994 |
Lange | -0.981 |
sonian | -0.945 |
Cantor | -0.930 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Sigma | +1.778 |
Lange | +1.386 |
alist | +1.365 |
Cantor | +1.328 |
Sachs | +1.295 |
Neg logit contributions | |
aredevil | -2.376 |
vez | -2.264 |
rams | -2.201 |
emies | -2.128 |
subp | -2.095 |
Token | box |
Token ID | 3091 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
aredevil | +0.625 |
vez | +0.600 |
rams | +0.581 |
emies | +0.565 |
subp | +0.551 |
Neg logit contributions | |
Sigma | -0.527 |
alist | -0.421 |
Lange | -0.420 |
Cantor | -0.401 |
sonian | -0.394 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Sigma | +0.630 |
Lange | +0.508 |
alist | +0.507 |
Cantor | +0.487 |
sonian | +0.477 |
Neg logit contributions | |
aredevil | -0.668 |
vez | -0.637 |
rams | -0.616 |
emies | -0.596 |
subp | -0.581 |
Token | Invalid |
Token ID | 17665 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Sigma | +0.981 |
Lange | +0.833 |
alist | +0.831 |
Cantor | +0.807 |
sonian | +0.795 |
Neg logit contributions | |
aredevil | -0.597 |
vez | -0.559 |
rams | -0.535 |
emies | -0.510 |
subp | -0.491 |
Token | email |
Token ID | 3053 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Sigma | +3.106 |
Lange | +2.046 |
alist | +2.042 |
chamber | +1.941 |
Cantor | +1.931 |
Neg logit contributions | |
aredevil | -7.495 |
vez | -7.219 |
rams | -7.061 |
emies | -6.860 |
irez | -6.743 |
Token | address |
Token ID | 2209 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Sigma | +1.412 |
Lange | +1.031 |
alist | +1.029 |
Cantor | +0.965 |
sonian | +0.938 |
Neg logit contributions | |
aredevil | -2.640 |
vez | -2.542 |
rams | -2.479 |
emies | -2.419 |
subp | -2.367 |
Token | . |
Token ID | 13 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
Sigma | +2.068 |
Lange | +1.659 |
alist | +1.650 |
Cantor | +1.593 |
Sachs | +1.556 |
Neg logit contributions | |
aredevil | -2.231 |
vez | -2.119 |
rams | -2.054 |
emies | -1.986 |
subp | -1.945 |
Token | Please |
Token ID | 4222 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
Sigma | +2.383 |
Lange | +1.901 |
alist | +1.858 |
Cantor | +1.828 |
Sachs | +1.785 |
Neg logit contributions | |
aredevil | -2.692 |
vez | -2.547 |
rams | -2.490 |
emies | -2.380 |
subp | -2.350 |
Token | re |
Token ID | 302 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Sigma | +3.087 |
Lange | +2.473 |
alist | +2.459 |
Cantor | +2.391 |
chamber | +2.390 |
Neg logit contributions | |
aredevil | -3.166 |
vez | -2.956 |
rams | -2.848 |
emies | -2.729 |
irez | -2.675 |
Token | to |
Token ID | 284 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Sigma | +0.287 |
Lange | +0.229 |
alist | +0.227 |
Cantor | +0.218 |
chamber | +0.213 |
Neg logit contributions | |
aredevil | -0.337 |
vez | -0.322 |
rams | -0.312 |
emies | -0.302 |
subp | -0.294 |
Token | have |
Token ID | 423 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Sigma | +0.456 |
alist | +0.360 |
Lange | +0.360 |
Cantor | +0.344 |
chamber | +0.336 |
Neg logit contributions | |
aredevil | -0.561 |
vez | -0.537 |
rams | -0.520 |
emies | -0.505 |
subp | -0.492 |
Token | done |
Token ID | 1760 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Sigma | +0.371 |
Lange | +0.289 |
alist | +0.288 |
Cantor | +0.275 |
chamber | +0.267 |
Neg logit contributions | |
aredevil | -0.509 |
vez | -0.487 |
rams | -0.474 |
emies | -0.460 |
subp | -0.449 |
Token | differently |
Token ID | 10338 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
aredevil | +0.629 |
vez | +0.596 |
rams | +0.574 |
emies | +0.553 |
subp | +0.536 |
Neg logit contributions | |
Sigma | -0.758 |
Lange | -0.628 |
alist | -0.628 |
Cantor | -0.606 |
sonian | -0.596 |
Token | ? |
Token ID | 30 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Sigma | +1.430 |
Lange | +1.176 |
alist | +1.167 |
Cantor | +1.130 |
chamber | +1.111 |
Neg logit contributions | |
aredevil | -1.314 |
vez | -1.241 |
rams | -1.202 |
emies | -1.158 |
subp | -1.120 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
aredevil | +3.523 |
vez | +3.306 |
rams | +3.165 |
emies | +3.113 |
subp | +2.916 |
Neg logit contributions | |
Sigma | -4.604 |
alist | -3.913 |
Lange | -3.829 |
sonian | -3.763 |
Cantor | -3.710 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
aredevil | +4.669 |
vez | +4.564 |
rams | +4.378 |
emies | +4.276 |
atti | +4.009 |
Neg logit contributions | |
Sigma | -8.976 |
princ | -8.510 |
Lange | -7.857 |
alist | -7.749 |
sonian | -7.483 |
Token | H |
Token ID | 39 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
aredevil | +5.389 |
vez | +5.096 |
rams | +4.820 |
emies | +4.635 |
irez | +4.423 |
Neg logit contributions | |
Sigma | -7.699 |
Lange | -6.519 |
Cantor | -6.344 |
alist | -6.322 |
chamber | -6.237 |
Token | aj |
Token ID | 1228 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
aredevil | +3.928 |
vez | +3.796 |
rams | +3.734 |
emies | +3.586 |
irez | +3.515 |
Neg logit contributions | |
Sigma | -2.599 |
Lange | -2.031 |
Cantor | -1.871 |
alist | -1.865 |
Sachs | -1.799 |
Token | ime |
Token ID | 524 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
aredevil | +0.645 |
vez | +0.619 |
rams | +0.599 |
emies | +0.585 |
irez | +0.564 |
Neg logit contributions | |
Sigma | -0.556 |
Lange | -0.442 |
alist | -0.437 |
Cantor | -0.423 |
sonian | -0.412 |
Token | Tab |
Token ID | 16904 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
aredevil | +0.751 |
vez | +0.721 |
rams | +0.696 |
emies | +0.676 |
subp | +0.659 |
Neg logit contributions | |
Sigma | -0.674 |
alist | -0.547 |
Lange | -0.540 |
sonian | -0.517 |
Cantor | -0.514 |
Token | E |
Token ID | 36 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aredevil | +2.327 |
vez | +2.233 |
rams | +2.147 |
emies | +2.061 |
irez | +1.993 |
Neg logit contributions | |
Sigma | -2.658 |
Lange | -2.190 |
alist | -2.173 |
Cantor | -2.110 |
chamber | -2.068 |
Token | g |
Token ID | 70 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
aredevil | +3.555 |
vez | +3.438 |
rams | +3.294 |
emies | +3.153 |
irez | +3.050 |
Neg logit contributions | |
Sigma | -4.132 |
Lange | -3.419 |
alist | -3.365 |
Cantor | -3.290 |
chamber | -3.230 |
Token | V |
Token ID | 53 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
aredevil | +2.476 |
vez | +2.370 |
rams | +2.281 |
emies | +2.189 |
irez | +2.115 |
Neg logit contributions | |
Sigma | -2.879 |
Lange | -2.374 |
alist | -2.363 |
Cantor | -2.296 |
chamber | -2.245 |
Token | V |
Token ID | 53 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
aredevil | +2.857 |
vez | +2.743 |
rams | +2.637 |
emies | +2.529 |
irez | +2.443 |
Neg logit contributions | |
Sigma | -3.303 |
Lange | -2.727 |
alist | -2.705 |
Cantor | -2.631 |
chamber | -2.578 |
Token | p |
Token ID | 79 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aredevil | +2.524 |
vez | +2.417 |
rams | +2.325 |
emies | +2.234 |
irez | +2.156 |
Neg logit contributions | |
Sigma | -2.911 |
Lange | -2.403 |
alist | -2.388 |
Cantor | -2.316 |
chamber | -2.269 |
Token | DM |
Token ID | 23127 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
aredevil | +3.544 |
vez | +3.423 |
rams | +3.279 |
emies | +3.138 |
irez | +3.046 |
Neg logit contributions | |
Sigma | -4.157 |
Lange | -3.431 |
alist | -3.400 |
Cantor | -3.326 |
chamber | -3.254 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
aredevil | +6.147 |
vez | +6.036 |
rams | +5.771 |
emies | +5.449 |
irez | +5.327 |
Neg logit contributions | |
Sigma | -7.385 |
Lange | -6.118 |
alist | -6.023 |
Cantor | -5.946 |
chamber | -5.850 |
Token | — |
Token ID | 851 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
aredevil | +4.011 |
vez | +3.852 |
rams | +3.700 |
emies | +3.548 |
subp | +3.439 |
Neg logit contributions | |
Sigma | -4.780 |
alist | -3.979 |
Lange | -3.956 |
Cantor | -3.823 |
sonian | -3.808 |
Token | V |
Token ID | 569 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
aredevil | +0.634 |
vez | +0.605 |
rams | +0.586 |
emies | +0.568 |
subp | +0.553 |
Neg logit contributions | |
Sigma | -0.585 |
Lange | -0.470 |
alist | -0.470 |
Cantor | -0.450 |
sonian | -0.442 |
Token | INE |
Token ID | 8881 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Sigma | +0.756 |
alist | +0.624 |
Lange | +0.623 |
Cantor | +0.598 |
sonian | +0.591 |
Neg logit contributions | |
aredevil | -0.633 |
vez | -0.594 |
rams | -0.574 |
emies | -0.558 |
subp | -0.546 |
Token | : |
Token ID | 25 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
Sigma | +1.959 |
Lange | +1.601 |
alist | +1.581 |
Cantor | +1.531 |
sonian | +1.513 |
Neg logit contributions | |
aredevil | -1.849 |
vez | -1.724 |
rams | -1.677 |
emies | -1.621 |
subp | -1.600 |
Token | O |
Token ID | 46 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
aredevil | +0.489 |
vez | +0.462 |
rams | +0.446 |
emies | +0.432 |
subp | +0.419 |
Neg logit contributions | |
Sigma | -0.556 |
alist | -0.459 |
Lange | -0.458 |
Cantor | -0.440 |
sonian | -0.434 |
Token | JV |
Token ID | 41697 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
aredevil | +3.342 |
vez | +3.215 |
rams | +3.088 |
emies | +2.958 |
irez | +2.865 |
Neg logit contributions | |
Sigma | -3.852 |
Lange | -3.183 |
alist | -3.132 |
Cantor | -3.073 |
chamber | -3.007 |
Token | L |
Token ID | 43 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
aredevil | +4.366 |
vez | +4.242 |
rams | +4.074 |
emies | +3.873 |
irez | +3.763 |
Neg logit contributions | |
Sigma | -5.071 |
Lange | -4.184 |
alist | -4.109 |
Cantor | -4.052 |
chamber | -3.972 |
Token | F |
Token ID | 37 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
aredevil | +3.897 |
vez | +3.768 |
rams | +3.617 |
emies | +3.456 |
irez | +3.339 |
Neg logit contributions | |
Sigma | -4.495 |
Lange | -3.719 |
alist | -3.659 |
Cantor | -3.588 |
chamber | -3.516 |
Token | Re |
Token ID | 3041 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
aredevil | +3.506 |
vez | +3.373 |
rams | +3.248 |
emies | +3.105 |
irez | +3.004 |
Neg logit contributions | |
Sigma | -4.037 |
Lange | -3.334 |
alist | -3.291 |
Cantor | -3.214 |
chamber | -3.154 |
Token | K |
Token ID | 42 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
aredevil | +3.418 |
vez | +3.305 |
rams | +3.168 |
emies | +3.031 |
irez | +2.944 |
Neg logit contributions | |
Sigma | -3.996 |
Lange | -3.305 |
alist | -3.266 |
Cantor | -3.190 |
chamber | -3.132 |
Token | ch |
Token ID | 354 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
aredevil | +6.182 |
vez | +6.086 |
rams | +5.841 |
emies | +5.499 |
irez | +5.361 |
Neg logit contributions | |
Sigma | -7.238 |
Lange | -6.001 |
alist | -5.839 |
Cantor | -5.814 |
chamber | -5.719 |
Token | — |
Token ID | 851 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
aredevil | +3.580 |
vez | +3.438 |
rams | +3.313 |
emies | +3.167 |
irez | +3.061 |
Neg logit contributions | |
Sigma | -4.148 |
alist | -3.431 |
Lange | -3.414 |
Cantor | -3.306 |
sonian | -3.266 |
Token | Dr |
Token ID | 1583 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
aredevil | +0.813 |
vez | +0.777 |
rams | +0.752 |
emies | +0.728 |
subp | +0.709 |
Neg logit contributions | |
Sigma | -0.743 |
alist | -0.599 |
Lange | -0.597 |
Cantor | -0.571 |
sonian | -0.563 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Sigma | +0.783 |
Lange | +0.633 |
alist | +0.631 |
Cantor | +0.607 |
sonian | +0.596 |
Neg logit contributions | |
aredevil | -0.818 |
vez | -0.779 |
rams | -0.753 |
emies | -0.730 |
subp | -0.712 |
Token | Jill |
Token ID | 22772 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Sigma | +1.296 |
Lange | +1.050 |
alist | +1.027 |
Cantor | +1.009 |
Sachs | +0.983 |
Neg logit contributions | |
aredevil | -1.390 |
vez | -1.319 |
rams | -1.278 |
emies | -1.239 |
subp | -1.213 |
Token | u |
Token ID | 84 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
aredevil | +0.390 |
vez | +0.369 |
rams | +0.356 |
emies | +0.344 |
subp | +0.335 |
Neg logit contributions | |
Sigma | -0.443 |
alist | -0.366 |
Lange | -0.365 |
Cantor | -0.351 |
sonian | -0.346 |
Token | I |
Token ID | 40 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
aredevil | +1.275 |
vez | +1.212 |
rams | +1.166 |
emies | +1.124 |
subp | +1.088 |
Neg logit contributions | |
Sigma | -1.509 |
Lange | -1.248 |
alist | -1.246 |
Cantor | -1.204 |
sonian | -1.182 |
Token | ba |
Token ID | 7012 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
aredevil | +3.359 |
vez | +3.233 |
rams | +3.107 |
emies | +2.977 |
irez | +2.880 |
Neg logit contributions | |
Sigma | -3.861 |
Lange | -3.189 |
alist | -3.146 |
Cantor | -3.073 |
chamber | -3.016 |
Token | H |
Token ID | 39 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
aredevil | +2.654 |
vez | +2.551 |
rams | +2.444 |
emies | +2.342 |
irez | +2.269 |
Neg logit contributions | |
Sigma | -3.194 |
Lange | -2.641 |
alist | -2.623 |
Cantor | -2.565 |
chamber | -2.512 |
Token | Ex |
Token ID | 3109 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
aredevil | +4.140 |
vez | +4.010 |
rams | +3.856 |
emies | +3.672 |
irez | +3.558 |
Neg logit contributions | |
Sigma | -4.840 |
Lange | -4.002 |
alist | -3.940 |
Cantor | -3.868 |
chamber | -3.787 |
Token | TT |
Token ID | 15751 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
aredevil | +1.566 |
vez | +1.493 |
rams | +1.438 |
emies | +1.385 |
subp | +1.340 |
Neg logit contributions | |
Sigma | -1.792 |
Lange | -1.476 |
alist | -1.472 |
Cantor | -1.422 |
sonian | -1.396 |
Token | j |
Token ID | 73 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
aredevil | +6.023 |
vez | +5.934 |
rams | +5.686 |
emies | +5.353 |
irez | +5.226 |
Neg logit contributions | |
Sigma | -7.242 |
Lange | -5.979 |
alist | -5.943 |
Cantor | -5.807 |
chamber | -5.732 |
Token | — |
Token ID | 851 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
aredevil | +2.384 |
vez | +2.266 |
rams | +2.177 |
emies | +2.096 |
subp | +2.030 |
Neg logit contributions | |
Sigma | -2.900 |
alist | -2.405 |
Lange | -2.397 |
Cantor | -2.316 |
sonian | -2.289 |
Token | B |
Token ID | 347 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
aredevil | +0.025 |
vez | +0.024 |
rams | +0.023 |
emies | +0.022 |
subp | +0.022 |
Neg logit contributions | |
Sigma | -0.023 |
Lange | -0.018 |
alist | -0.018 |
Cantor | -0.018 |
sonian | -0.017 |
Token | orm |
Token ID | 579 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
aredevil | +0.720 |
vez | +0.678 |
rams | +0.651 |
emies | +0.634 |
subp | +0.618 |
Neg logit contributions | |
Sigma | -0.864 |
alist | -0.718 |
Lange | -0.714 |
Cantor | -0.689 |
chamber | -0.677 |
Token | es |
Token ID | 274 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Sigma | +1.463 |
alist | +1.096 |
Lange | +1.091 |
Cantor | +1.018 |
Sachs | +0.993 |
Neg logit contributions | |
aredevil | -2.571 |
vez | -2.464 |
rams | -2.402 |
emies | -2.347 |
subp | -2.305 |
Token | off |
Token ID | 572 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
aredevil | +1.352 |
vez | +1.289 |
rams | +1.246 |
emies | +1.207 |
subp | +1.174 |
Neg logit contributions | |
Sigma | -1.329 |
Lange | -1.077 |
alist | -1.077 |
Cantor | -1.033 |
sonian | -1.016 |
Token | of |
Token ID | 286 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
aredevil | +0.751 |
vez | +0.711 |
rams | +0.685 |
emies | +0.662 |
subp | +0.641 |
Neg logit contributions | |
Sigma | -0.860 |
Lange | -0.708 |
alist | -0.706 |
Cantor | -0.682 |
chamber | -0.670 |
Token | ? |
Token ID | 30 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
aredevil | +0.154 |
vez | +0.147 |
rams | +0.142 |
emies | +0.137 |
subp | +0.133 |
Neg logit contributions | |
Sigma | -0.159 |
Lange | -0.130 |
alist | -0.129 |
Cantor | -0.125 |
Sachs | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
aredevil | +1.848 |
vez | +1.746 |
rams | +1.681 |
emies | +1.637 |
subp | +1.550 |
Neg logit contributions | |
Sigma | -2.228 |
alist | -1.875 |
Lange | -1.841 |
sonian | -1.778 |
Cantor | -1.771 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
aredevil | +4.254 |
vez | +4.141 |
rams | +3.999 |
emies | +3.893 |
atti | +3.655 |
Neg logit contributions | |
Sigma | -7.604 |
princ | -6.995 |
Lange | -6.552 |
alist | -6.548 |
sonian | -6.290 |
Token | Yeah |
Token ID | 10995 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
aredevil | +4.913 |
vez | +4.685 |
rams | +4.511 |
emies | +4.371 |
atti | +4.166 |
Neg logit contributions | |
Sigma | -6.519 |
Lange | -5.500 |
alist | -5.472 |
Cantor | -5.308 |
chamber | -5.295 |
Token | , |
Token ID | 11 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
aredevil | +5.913 |
vez | +5.638 |
rams | +5.481 |
emies | +5.313 |
subp | +5.087 |
Neg logit contributions | |
Sigma | -7.047 |
alist | -5.979 |
Lange | -5.809 |
sonian | -5.738 |
Cantor | -5.583 |
Token | absolutely |
Token ID | 5543 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
aredevil | +2.925 |
vez | +2.778 |
rams | +2.691 |
emies | +2.590 |
subp | +2.515 |
Neg logit contributions | |
Sigma | -3.450 |
alist | -2.888 |
Lange | -2.859 |
sonian | -2.756 |
Cantor | -2.753 |
Token | . |
Token ID | 13 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
aredevil | +3.749 |
vez | +3.576 |
rams | +3.440 |
emies | +3.334 |
subp | +3.235 |
Neg logit contributions | |
Sigma | -4.102 |
alist | -3.440 |
Lange | -3.362 |
sonian | -3.297 |
Cantor | -3.232 |
Token | Once |
Token ID | 4874 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
aredevil | +2.115 |
vez | +2.014 |
rams | +1.936 |
emies | +1.879 |
subp | +1.803 |
Neg logit contributions | |
Sigma | -2.356 |
alist | -1.969 |
Lange | -1.938 |
Cantor | -1.864 |
sonian | -1.863 |
Token | we |
Token ID | 356 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
Sigma | +0.355 |
Lange | +0.291 |
alist | +0.289 |
Cantor | +0.280 |
Sachs | +0.275 |
Neg logit contributions | |
aredevil | -0.319 |
vez | -0.303 |
rams | -0.292 |
emies | -0.281 |
subp | -0.274 |
Token | have |
Token ID | 423 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Sigma | +0.456 |
alist | +0.360 |
Lange | +0.360 |
Cantor | +0.344 |
chamber | +0.336 |
Neg logit contributions | |
aredevil | -0.561 |
vez | -0.537 |
rams | -0.520 |
emies | -0.505 |
subp | -0.492 |
Token | done |
Token ID | 1760 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Sigma | +0.371 |
Lange | +0.289 |
alist | +0.288 |
Cantor | +0.275 |
chamber | +0.267 |
Neg logit contributions | |
aredevil | -0.509 |
vez | -0.487 |
rams | -0.474 |
emies | -0.460 |
subp | -0.449 |
Token | differently |
Token ID | 10338 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
aredevil | +0.629 |
vez | +0.596 |
rams | +0.574 |
emies | +0.553 |
subp | +0.536 |
Neg logit contributions | |
Sigma | -0.758 |
Lange | -0.628 |
alist | -0.628 |
Cantor | -0.606 |
sonian | -0.596 |
Token | ? |
Token ID | 30 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Sigma | +1.430 |
Lange | +1.176 |
alist | +1.167 |
Cantor | +1.130 |
chamber | +1.111 |
Neg logit contributions | |
aredevil | -1.314 |
vez | -1.241 |
rams | -1.202 |
emies | -1.158 |
subp | -1.120 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
aredevil | +3.523 |
vez | +3.306 |
rams | +3.165 |
emies | +3.113 |
subp | +2.916 |
Neg logit contributions | |
Sigma | -4.604 |
alist | -3.913 |
Lange | -3.829 |
sonian | -3.763 |
Cantor | -3.710 |
Token |
|
Token ID | 198 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
aredevil | +4.669 |
vez | +4.564 |
rams | +4.378 |
emies | +4.276 |
atti | +4.009 |
Neg logit contributions | |
Sigma | -8.976 |
princ | -8.510 |
Lange | -7.857 |
alist | -7.749 |
sonian | -7.483 |
Token | H |
Token ID | 39 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
aredevil | +5.389 |
vez | +5.096 |
rams | +4.820 |
emies | +4.635 |
irez | +4.423 |
Neg logit contributions | |
Sigma | -7.699 |
Lange | -6.519 |
Cantor | -6.344 |
alist | -6.322 |
chamber | -6.237 |
Token | aj |
Token ID | 1228 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
aredevil | +3.928 |
vez | +3.796 |
rams | +3.734 |
emies | +3.586 |
irez | +3.515 |
Neg logit contributions | |
Sigma | -2.599 |
Lange | -2.031 |
Cantor | -1.871 |
alist | -1.865 |
Sachs | -1.799 |
Token | ime |
Token ID | 524 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
aredevil | +0.645 |
vez | +0.619 |
rams | +0.599 |
emies | +0.585 |
irez | +0.564 |
Neg logit contributions | |
Sigma | -0.556 |
Lange | -0.442 |
alist | -0.437 |
Cantor | -0.423 |
sonian | -0.412 |
Token | Tab |
Token ID | 16904 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
aredevil | +0.751 |
vez | +0.721 |
rams | +0.696 |
emies | +0.676 |
subp | +0.659 |
Neg logit contributions | |
Sigma | -0.674 |
alist | -0.547 |
Lange | -0.540 |
sonian | -0.517 |
Cantor | -0.514 |
Token | ata |
Token ID | 1045 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
aredevil | +1.017 |
vez | +0.968 |
rams | +0.931 |
emies | +0.896 |
irez | +0.858 |
Neg logit contributions | |
Sigma | -1.348 |
Lange | -1.127 |
alist | -1.117 |
Cantor | -1.085 |
sonian | -1.073 |
Token | & |
Token ID | 5 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
Sigma | +0.920 |
alist | +0.770 |
Lange | +0.761 |
Cantor | +0.740 |
sonian | +0.737 |
Neg logit contributions | |
aredevil | -0.670 |
vez | -0.630 |
rams | -0.596 |
emies | -0.573 |
subp | -0.567 |
Token | D |
Token ID | 35 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Sigma | +0.145 |
Lange | +0.118 |
alist | +0.118 |
Cantor | +0.114 |
sonian | +0.112 |
Neg logit contributions | |
aredevil | -0.138 |
vez | -0.131 |
rams | -0.127 |
emies | -0.123 |
subp | -0.119 |
Token | in |
Token ID | 287 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Sigma | +0.494 |
Lange | +0.398 |
alist | +0.397 |
Cantor | +0.381 |
chamber | +0.375 |
Neg logit contributions | |
aredevil | -0.532 |
vez | -0.506 |
rams | -0.489 |
emies | -0.475 |
subp | -0.460 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Sigma | +0.931 |
Lange | +0.724 |
alist | +0.712 |
Cantor | +0.690 |
Sachs | +0.677 |
Neg logit contributions | |
aredevil | -1.221 |
vez | -1.158 |
rams | -1.127 |
emies | -1.100 |
irez | -1.073 |
Token | out |
Token ID | 503 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
aredevil | +0.726 |
vez | +0.690 |
rams | +0.666 |
emies | +0.646 |
subp | +0.627 |
Neg logit contributions | |
Sigma | -0.722 |
Lange | -0.587 |
alist | -0.585 |
Cantor | -0.562 |
Sachs | -0.551 |
Token | stri |
Token ID | 33565 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Sigma | +0.055 |
Lange | +0.047 |
alist | +0.047 |
Cantor | +0.045 |
chamber | +0.045 |
Neg logit contributions | |
aredevil | -0.032 |
vez | -0.029 |
rams | -0.027 |
emies | -0.027 |
subp | -0.025 |
Token | ps |
Token ID | 862 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
aredevil | +4.642 |
vez | +4.519 |
rams | +4.264 |
emies | +4.032 |
irez | +3.806 |
Neg logit contributions | |
Sigma | -8.219 |
alist | -7.077 |
Lange | -7.014 |
sonian | -6.968 |
Cantor | -6.841 |
Token | runner |
Token ID | 17490 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
aredevil | +2.159 |
vez | +2.061 |
rams | +2.003 |
emies | +1.940 |
subp | +1.897 |
Neg logit contributions | |
Sigma | -1.841 |
alist | -1.481 |
Lange | -1.470 |
Cantor | -1.404 |
sonian | -1.397 |
Token | - |
Token ID | 12 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
aredevil | +2.594 |
vez | +2.438 |
rams | +2.357 |
emies | +2.268 |
subp | +2.165 |
Neg logit contributions | |
Sigma | -3.650 |
alist | -3.116 |
Lange | -3.102 |
Cantor | -2.989 |
sonian | -2.970 |
Token | up |
Token ID | 929 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
Sigma | +0.346 |
alist | +0.263 |
Lange | +0.259 |
Cantor | +0.246 |
chamber | +0.239 |
Neg logit contributions | |
aredevil | -0.560 |
vez | -0.536 |
rams | -0.521 |
emies | -0.508 |
subp | -0.500 |
Token | Israel |
Token ID | 2692 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Sigma | +1.885 |
Lange | +1.447 |
alist | +1.420 |
Cantor | +1.391 |
chamber | +1.359 |
Neg logit contributions | |
aredevil | -2.478 |
vez | -2.386 |
rams | -2.308 |
emies | -2.245 |
irez | -2.210 |
Token | as |
Token ID | 355 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
Sigma | +0.492 |
Lange | +0.397 |
alist | +0.396 |
Cantor | +0.382 |
Sachs | +0.375 |
Neg logit contributions | |
aredevil | -0.503 |
vez | -0.479 |
rams | -0.464 |
emies | -0.447 |
irez | -0.434 |
Token | successful |
Token ID | 4388 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
Sigma | +2.004 |
Lange | +1.610 |
alist | +1.589 |
Cantor | +1.534 |
Sachs | +1.520 |
Neg logit contributions | |
aredevil | -2.130 |
vez | -2.015 |
rams | -1.957 |
emies | -1.900 |
irez | -1.848 |
Token | GP |
Token ID | 14714 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Sigma | +2.153 |
Lange | +1.746 |
alist | +1.732 |
Cantor | +1.669 |
Sachs | +1.646 |
Neg logit contributions | |
aredevil | -2.068 |
vez | -1.967 |
rams | -1.897 |
emies | -1.843 |
irez | -1.783 |
Token | 2 |
Token ID | 17 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
aredevil | +1.368 |
vez | +1.299 |
rams | +1.252 |
emies | +1.207 |
subp | +1.171 |
Neg logit contributions | |
Sigma | -1.601 |
alist | -1.324 |
Lange | -1.323 |
Cantor | -1.276 |
sonian | -1.258 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
aredevil | +0.280 |
vez | +0.264 |
rams | +0.255 |
emies | +0.246 |
irez | +0.237 |
Neg logit contributions | |
Sigma | -0.333 |
Lange | -0.275 |
alist | -0.275 |
Cantor | -0.264 |
Sachs | -0.260 |
Token | Indy |
Token ID | 26023 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Sigma | +0.698 |
Lange | +0.565 |
alist | +0.563 |
Cantor | +0.542 |
Sachs | +0.532 |
Neg logit contributions | |
aredevil | -0.706 |
vez | -0.672 |
rams | -0.649 |
emies | -0.630 |
subp | -0.609 |
Token | Car |
Token ID | 9914 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
aredevil | +5.770 |
vez | +5.588 |
rams | +5.280 |
emies | +5.147 |
subp | +4.999 |
Neg logit contributions | |
Sigma | -6.625 |
Lange | -5.523 |
alist | -5.508 |
sonian | -5.389 |
Cantor | -5.345 |
Token | teams |
Token ID | 3466 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
aredevil | +2.698 |
vez | +2.579 |
rams | +2.475 |
emies | +2.395 |
subp | +2.345 |
Neg logit contributions | |
Sigma | -3.193 |
alist | -2.656 |
Lange | -2.655 |
Cantor | -2.565 |
sonian | -2.557 |
Token | now |
Token ID | 783 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
aredevil | +0.695 |
vez | +0.664 |
rams | +0.642 |
emies | +0.624 |
subp | +0.607 |
Neg logit contributions | |
Sigma | -0.625 |
alist | -0.502 |
Lange | -0.502 |
Cantor | -0.480 |
sonian | -0.472 |
Token | do |
Token ID | 466 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
aredevil | +1.932 |
vez | +1.841 |
rams | +1.771 |
emies | +1.724 |
subp | +1.687 |
Neg logit contributions | |
Sigma | -1.869 |
alist | -1.517 |
Lange | -1.516 |
Cantor | -1.458 |
sonian | -1.441 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aredevil | +2.592 |
vez | +2.474 |
rams | +2.380 |
emies | +2.313 |
subp | +2.251 |
Neg logit contributions | |
Sigma | -2.702 |
Lange | -2.220 |
alist | -2.208 |
Cantor | -2.124 |
sonian | -2.105 |
Token | up |
Token ID | 510 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
aredevil | +2.175 |
vez | +2.140 |
rams | +2.060 |
emies | +1.988 |
subp | +1.925 |
Neg logit contributions | |
Sigma | -1.956 |
alist | -1.592 |
Lange | -1.584 |
Cantor | -1.506 |
sonian | -1.497 |
Token | for |
Token ID | 329 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
aredevil | +0.996 |
vez | +0.962 |
rams | +0.917 |
emies | +0.880 |
subp | +0.849 |
Neg logit contributions | |
Sigma | -1.185 |
alist | -0.997 |
Lange | -0.993 |
Cantor | -0.955 |
sonian | -0.937 |
Token | our |
Token ID | 674 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
aredevil | +1.521 |
vez | +1.498 |
rams | +1.438 |
emies | +1.374 |
irez | +1.317 |
Neg logit contributions | |
Sigma | -1.407 |
alist | -1.174 |
Lange | -1.153 |
Cantor | -1.089 |
sonian | -1.089 |
Token | Email |
Token ID | 9570 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Sigma | +0.626 |
alist | +0.454 |
Lange | +0.449 |
Cantor | +0.417 |
sonian | +0.403 |
Neg logit contributions | |
aredevil | -1.273 |
vez | -1.233 |
rams | -1.198 |
emies | -1.168 |
subp | -1.143 |
Token | News |
Token ID | 3000 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
aredevil | +0.509 |
vez | +0.492 |
rams | +0.472 |
emies | +0.455 |
subp | +0.441 |
Neg logit contributions | |
Sigma | -0.510 |
alist | -0.421 |
Lange | -0.413 |
Cantor | -0.396 |
sonian | -0.389 |
Token | letters |
Token ID | 15653 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
aredevil | +2.317 |
vez | +2.192 |
rams | +2.116 |
emies | +1.994 |
subp | +1.881 |
Neg logit contributions | |
Sigma | -4.128 |
alist | -3.591 |
Lange | -3.580 |
Cantor | -3.459 |
sonian | -3.441 |
Token | here |
Token ID | 994 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
aredevil | +4.889 |
vez | +4.830 |
rams | +4.639 |
emies | +4.470 |
atti | +4.287 |
Neg logit contributions | |
Sigma | -7.233 |
alist | -6.423 |
Lange | -6.130 |
princ | -5.912 |
Cantor | -5.907 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
aredevil | +1.901 |
vez | +1.823 |
rams | +1.758 |
emies | +1.712 |
subp | +1.647 |
Neg logit contributions | |
Sigma | -1.980 |
alist | -1.630 |
Lange | -1.618 |
Cantor | -1.563 |
sonian | -1.533 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
aredevil | +1.347 |
vez | +1.309 |
rams | +1.229 |
emies | +1.181 |
irez | +1.160 |
Neg logit contributions | |
Sigma | -1.816 |
alist | -1.563 |
Lange | -1.522 |
Cantor | -1.497 |
sonian | -1.485 |
Token | Mike |
Token ID | 16073 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Sigma | +2.939 |
alist | +2.432 |
Lange | +2.353 |
sonian | +2.254 |
Cantor | +2.253 |
Neg logit contributions | |
aredevil | -3.122 |
vez | -2.951 |
rams | -2.851 |
emies | -2.784 |
subp | -2.748 |
Token | Bloomberg |
Token ID | 15689 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
aredevil | +1.005 |
vez | +0.959 |
rams | +0.928 |
emies | +0.901 |
subp | +0.878 |
Neg logit contributions | |
Sigma | -0.913 |
Lange | -0.737 |
alist | -0.732 |
Cantor | -0.705 |
Sachs | -0.688 |
Token | language |
Token ID | 3303 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
aredevil | +0.854 |
vez | +0.812 |
rams | +0.787 |
emies | +0.761 |
irez | +0.739 |
Neg logit contributions | |
Sigma | -0.858 |
Lange | -0.699 |
alist | -0.699 |
Cantor | -0.670 |
chamber | -0.659 |
Token | into |
Token ID | 656 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
aredevil | +2.255 |
vez | +2.150 |
rams | +2.075 |
emies | +2.005 |
subp | +1.958 |
Neg logit contributions | |
Sigma | -2.446 |
Lange | -2.005 |
alist | -2.001 |
Cantor | -1.925 |
sonian | -1.908 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aredevil | +0.114 |
vez | +0.108 |
rams | +0.104 |
emies | +0.101 |
subp | +0.098 |
Neg logit contributions | |
Sigma | -0.115 |
Lange | -0.094 |
alist | -0.094 |
Cantor | -0.090 |
chamber | -0.088 |
Token | series |
Token ID | 2168 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
aredevil | +0.339 |
vez | +0.322 |
rams | +0.311 |
emies | +0.301 |
irez | +0.292 |
Neg logit contributions | |
Sigma | -0.358 |
Lange | -0.293 |
alist | -0.292 |
Cantor | -0.281 |
chamber | -0.276 |
Token | ? |
Token ID | 30 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Sigma | +1.016 |
alist | +0.843 |
Lange | +0.838 |
Cantor | +0.810 |
chamber | +0.801 |
Neg logit contributions | |
aredevil | -0.869 |
vez | -0.817 |
rams | -0.788 |
emies | -0.764 |
irez | -0.739 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
aredevil | +1.802 |
vez | +1.715 |
rams | +1.649 |
emies | +1.596 |
subp | +1.528 |
Neg logit contributions | |
Sigma | -2.158 |
alist | -1.805 |
Lange | -1.783 |
Cantor | -1.714 |
sonian | -1.710 |
Token |
|
Token ID | 198 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
aredevil | +4.357 |
vez | +4.253 |
rams | +4.067 |
emies | +3.960 |
atti | +3.716 |
Neg logit contributions | |
Sigma | -7.597 |
princ | -6.924 |
Lange | -6.554 |
alist | -6.496 |
Cantor | -6.255 |
Token | N |
Token ID | 45 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
aredevil | +5.345 |
vez | +5.112 |
rams | +4.951 |
emies | +4.732 |
atti | +4.498 |
Neg logit contributions | |
Sigma | -6.298 |
Lange | -5.214 |
alist | -5.133 |
Cantor | -5.039 |
chamber | -4.979 |
Token | PH |
Token ID | 11909 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
aredevil | +4.584 |
vez | +4.380 |
rams | +4.161 |
emies | +4.035 |
irez | +3.820 |
Neg logit contributions | |
Sigma | -6.709 |
Lange | -5.687 |
alist | -5.482 |
princ | -5.387 |
Cantor | -5.376 |
Token | : |
Token ID | 25 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
aredevil | +2.593 |
vez | +2.513 |
rams | +2.386 |
emies | +2.340 |
subp | +2.217 |
Neg logit contributions | |
Sigma | -3.267 |
Lange | -2.716 |
alist | -2.708 |
princ | -2.641 |
Cantor | -2.599 |
Token | A |
Token ID | 317 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
aredevil | +3.933 |
vez | +3.746 |
rams | +3.580 |
emies | +3.480 |
subp | +3.315 |
Neg logit contributions | |
Sigma | -5.044 |
alist | -4.326 |
Lange | -4.179 |
sonian | -4.102 |
chamber | -4.030 |
Token | were |
Token ID | 547 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
aredevil | +1.007 |
vez | +0.960 |
rams | +0.928 |
emies | +0.899 |
subp | +0.874 |
Neg logit contributions | |
Sigma | -0.982 |
Lange | -0.795 |
alist | -0.795 |
Cantor | -0.762 |
sonian | -0.750 |
Token | working |
Token ID | 1762 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
aredevil | +1.449 |
vez | +1.378 |
rams | +1.328 |
emies | +1.281 |
subp | +1.243 |
Neg logit contributions | |
Sigma | -1.630 |
Lange | -1.341 |
alist | -1.341 |
Cantor | -1.291 |
Sachs | -1.266 |
Token | off |
Token ID | 572 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
aredevil | +1.352 |
vez | +1.289 |
rams | +1.246 |
emies | +1.207 |
subp | +1.174 |
Neg logit contributions | |
Sigma | -1.329 |
Lange | -1.077 |
alist | -1.077 |
Cantor | -1.033 |
sonian | -1.016 |
Token | of |
Token ID | 286 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
aredevil | +0.751 |
vez | +0.711 |
rams | +0.685 |
emies | +0.662 |
subp | +0.641 |
Neg logit contributions | |
Sigma | -0.860 |
Lange | -0.708 |
alist | -0.706 |
Cantor | -0.682 |
chamber | -0.670 |
Token | ? |
Token ID | 30 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
aredevil | +0.154 |
vez | +0.147 |
rams | +0.142 |
emies | +0.137 |
subp | +0.133 |
Neg logit contributions | |
Sigma | -0.159 |
Lange | -0.130 |
alist | -0.129 |
Cantor | -0.125 |
Sachs | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
aredevil | +1.848 |
vez | +1.746 |
rams | +1.681 |
emies | +1.637 |
subp | +1.550 |
Neg logit contributions | |
Sigma | -2.228 |
alist | -1.875 |
Lange | -1.841 |
sonian | -1.778 |
Cantor | -1.771 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
aredevil | +4.254 |
vez | +4.141 |
rams | +3.999 |
emies | +3.893 |
atti | +3.655 |
Neg logit contributions | |
Sigma | -7.604 |
princ | -6.995 |
Lange | -6.552 |
alist | -6.548 |
sonian | -6.290 |
Token | Yeah |
Token ID | 10995 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
aredevil | +4.913 |
vez | +4.685 |
rams | +4.511 |
emies | +4.371 |
atti | +4.166 |
Neg logit contributions | |
Sigma | -6.519 |
Lange | -5.500 |
alist | -5.472 |
Cantor | -5.308 |
chamber | -5.295 |
Token | , |
Token ID | 11 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
aredevil | +5.913 |
vez | +5.638 |
rams | +5.481 |
emies | +5.313 |
subp | +5.087 |
Neg logit contributions | |
Sigma | -7.047 |
alist | -5.979 |
Lange | -5.809 |
sonian | -5.738 |
Cantor | -5.583 |
Token | absolutely |
Token ID | 5543 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
aredevil | +2.925 |
vez | +2.778 |
rams | +2.691 |
emies | +2.590 |
subp | +2.515 |
Neg logit contributions | |
Sigma | -3.450 |
alist | -2.888 |
Lange | -2.859 |
sonian | -2.756 |
Cantor | -2.753 |
Token | . |
Token ID | 13 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
aredevil | +3.749 |
vez | +3.576 |
rams | +3.440 |
emies | +3.334 |
subp | +3.235 |
Neg logit contributions | |
Sigma | -4.102 |
alist | -3.440 |
Lange | -3.362 |
sonian | -3.297 |
Cantor | -3.232 |
Token | were |
Token ID | 547 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Sigma | +0.015 |
Lange | +0.012 |
alist | +0.012 |
Cantor | +0.011 |
chamber | +0.011 |
Neg logit contributions | |
aredevil | -0.016 |
vez | -0.015 |
rams | -0.015 |
emies | -0.015 |
subp | -0.014 |
Token | ever |
Token ID | 1683 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
aredevil | +1.118 |
vez | +1.068 |
rams | +1.037 |
emies | +1.005 |
irez | +0.977 |
Neg logit contributions | |
Sigma | -0.946 |
Lange | -0.754 |
alist | -0.746 |
Cantor | -0.717 |
chamber | -0.701 |
Token | coming |
Token ID | 2406 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
Sigma | +0.410 |
Lange | +0.326 |
alist | +0.317 |
Cantor | +0.307 |
chamber | +0.301 |
Neg logit contributions | |
aredevil | -0.514 |
vez | -0.491 |
rams | -0.477 |
emies | -0.462 |
irez | -0.453 |
Token | back |
Token ID | 736 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
aredevil | +0.175 |
vez | +0.167 |
rams | +0.162 |
emies | +0.156 |
subp | +0.152 |
Neg logit contributions | |
Sigma | -0.151 |
Lange | -0.121 |
alist | -0.120 |
Cantor | -0.115 |
chamber | -0.113 |
Token | ? |
Token ID | 30 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Sigma | +0.590 |
Lange | +0.477 |
alist | +0.472 |
Cantor | +0.458 |
chamber | +0.449 |
Neg logit contributions | |
aredevil | -0.612 |
vez | -0.580 |
rams | -0.562 |
emies | -0.544 |
irez | -0.529 |
Token |
|
Token ID | 198 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
aredevil | +3.342 |
vez | +3.190 |
rams | +3.066 |
emies | +2.968 |
subp | +2.823 |
Neg logit contributions | |
Sigma | -4.083 |
alist | -3.460 |
Lange | -3.388 |
sonian | -3.278 |
chamber | -3.254 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
aredevil | +4.409 |
vez | +4.331 |
rams | +4.117 |
emies | +4.029 |
atti | +3.779 |
Neg logit contributions | |
Sigma | -7.464 |
princ | -6.702 |
Lange | -6.432 |
alist | -6.412 |
sonian | -6.143 |
Token | Yeah |
Token ID | 10995 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
aredevil | +4.941 |
vez | +4.761 |
rams | +4.562 |
emies | +4.409 |
atti | +4.175 |
Neg logit contributions | |
Sigma | -6.464 |
Lange | -5.412 |
alist | -5.372 |
Cantor | -5.205 |
chamber | -5.161 |
Token | , |
Token ID | 11 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
aredevil | +5.310 |
vez | +5.133 |
rams | +4.957 |
emies | +4.796 |
subp | +4.637 |
Neg logit contributions | |
Sigma | -6.078 |
alist | -5.072 |
Lange | -5.009 |
sonian | -4.859 |
Cantor | -4.772 |
Token | all |
Token ID | 477 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
aredevil | +2.962 |
vez | +2.822 |
rams | +2.720 |
emies | +2.624 |
subp | +2.549 |
Neg logit contributions | |
Sigma | -3.432 |
alist | -2.848 |
Lange | -2.831 |
Cantor | -2.723 |
sonian | -2.706 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
aredevil | +0.214 |
vez | +0.203 |
rams | +0.195 |
emies | +0.190 |
irez | +0.184 |
Neg logit contributions | |
Sigma | -0.203 |
Lange | -0.165 |
alist | -0.161 |
Cantor | -0.158 |
chamber | -0.155 |
Token | U |
Token ID | 52 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
aredevil | +3.205 |
vez | +3.086 |
rams | +2.963 |
emies | +2.835 |
irez | +2.747 |
Neg logit contributions | |
Sigma | -3.806 |
Lange | -3.147 |
alist | -3.119 |
Cantor | -3.042 |
chamber | -2.985 |
Token | g |
Token ID | 70 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
aredevil | +3.455 |
vez | +3.334 |
rams | +3.194 |
emies | +3.059 |
irez | +2.955 |
Neg logit contributions | |
Sigma | -4.067 |
Lange | -3.367 |
alist | -3.316 |
Cantor | -3.254 |
chamber | -3.187 |
Token | I |
Token ID | 40 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
aredevil | +2.256 |
vez | +2.157 |
rams | +2.076 |
emies | +1.993 |
irez | +1.923 |
Neg logit contributions | |
Sigma | -2.634 |
Lange | -2.174 |
alist | -2.164 |
Cantor | -2.101 |
chamber | -2.056 |
Token | x |
Token ID | 87 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
aredevil | +2.804 |
vez | +2.685 |
rams | +2.582 |
emies | +2.482 |
irez | +2.394 |
Neg logit contributions | |
Sigma | -3.219 |
Lange | -2.657 |
alist | -2.634 |
Cantor | -2.560 |
chamber | -2.509 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
aredevil | +0.787 |
vez | +0.747 |
rams | +0.720 |
emies | +0.695 |
subp | +0.674 |
Neg logit contributions | |
Sigma | -0.900 |
alist | -0.742 |
Lange | -0.742 |
Cantor | -0.714 |
sonian | -0.703 |
Token | N |
Token ID | 45 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
aredevil | +3.395 |
vez | +3.290 |
rams | +3.148 |
emies | +3.015 |
irez | +2.921 |
Neg logit contributions | |
Sigma | -3.890 |
Lange | -3.206 |
alist | -3.164 |
Cantor | -3.093 |
chamber | -3.037 |
Token | t |
Token ID | 83 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
aredevil | +5.655 |
vez | +5.551 |
rams | +5.305 |
emies | +5.047 |
irez | +4.881 |
Neg logit contributions | |
Sigma | -6.640 |
Lange | -5.517 |
alist | -5.342 |
Cantor | -5.329 |
chamber | -5.243 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
aredevil | +3.645 |
vez | +3.524 |
rams | +3.373 |
emies | +3.225 |
irez | +3.124 |
Neg logit contributions | |
Sigma | -4.395 |
Lange | -3.632 |
alist | -3.623 |
Cantor | -3.527 |
chamber | -3.464 |
Token | — |
Token ID | 851 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
aredevil | +3.873 |
vez | +3.711 |
rams | +3.555 |
emies | +3.394 |
subp | +3.279 |
Neg logit contributions | |
Sigma | -5.326 |
alist | -4.500 |
Lange | -4.452 |
sonian | -4.332 |
Cantor | -4.308 |
Token | Ze |
Token ID | 9033 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
Sigma | +0.175 |
Lange | +0.140 |
alist | +0.139 |
Cantor | +0.134 |
sonian | +0.131 |
Neg logit contributions | |
aredevil | -0.195 |
vez | -0.186 |
rams | -0.180 |
emies | -0.174 |
subp | -0.170 |
Token | ke |
Token ID | 365 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Sigma | +0.193 |
Lange | +0.150 |
alist | +0.148 |
Cantor | +0.141 |
Sachs | +0.137 |
Neg logit contributions | |
aredevil | -0.272 |
vez | -0.259 |
rams | -0.255 |
emies | -0.248 |
subp | -0.242 |
Token | Canada |
Token ID | 3340 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Sigma | +0.883 |
Lange | +0.706 |
alist | +0.695 |
Cantor | +0.671 |
chamber | +0.658 |
Neg logit contributions | |
aredevil | -1.044 |
vez | -0.990 |
rams | -0.960 |
emies | -0.929 |
irez | -0.906 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
aredevil | +0.403 |
vez | +0.384 |
rams | +0.372 |
emies | +0.360 |
subp | +0.350 |
Neg logit contributions | |
Sigma | -0.382 |
alist | -0.308 |
Lange | -0.308 |
Cantor | -0.296 |
sonian | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Sigma | +0.502 |
Lange | +0.407 |
alist | +0.402 |
Cantor | +0.390 |
Sachs | +0.380 |
Neg logit contributions | |
aredevil | -0.523 |
vez | -0.496 |
rams | -0.481 |
emies | -0.466 |
subp | -0.455 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
aredevil | +0.232 |
vez | +0.221 |
rams | +0.213 |
emies | +0.205 |
subp | +0.199 |
Neg logit contributions | |
Sigma | -0.268 |
Lange | -0.222 |
alist | -0.222 |
Cantor | -0.213 |
sonian | -0.210 |
Token | App |
Token ID | 4677 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Sigma | +0.072 |
alist | +0.058 |
Lange | +0.058 |
Cantor | +0.055 |
sonian | +0.055 |
Neg logit contributions | |
aredevil | -0.075 |
vez | -0.071 |
rams | -0.069 |
emies | -0.067 |
subp | -0.066 |
Token | alach |
Token ID | 33786 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
aredevil | +2.392 |
vez | +2.258 |
rams | +2.173 |
emies | +2.080 |
subp | +2.002 |
Neg logit contributions | |
Sigma | -3.426 |
Lange | -2.864 |
alist | -2.856 |
Cantor | -2.783 |
sonian | -2.743 |
Token | ia |
Token ID | 544 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
aredevil | +7.040 |
vez | +6.659 |
rams | +6.536 |
emies | +6.416 |
irez | +6.171 |
Neg logit contributions | |
Sigma | -5.267 |
Lange | -4.044 |
alist | -4.007 |
Cantor | -3.847 |
chamber | -3.835 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
aredevil | +0.127 |
vez | +0.121 |
rams | +0.117 |
emies | +0.114 |
subp | +0.111 |
Neg logit contributions | |
Sigma | -0.122 |
Lange | -0.099 |
alist | -0.099 |
Cantor | -0.095 |
Sachs | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Sigma | +0.510 |
Lange | +0.410 |
alist | +0.406 |
Cantor | +0.392 |
Sachs | +0.382 |
Neg logit contributions | |
aredevil | -0.561 |
vez | -0.534 |
rams | -0.518 |
emies | -0.503 |
subp | -0.487 |
Token | U |
Token ID | 471 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
aredevil | +0.589 |
vez | +0.561 |
rams | +0.543 |
emies | +0.526 |
subp | +0.511 |
Neg logit contributions | |
Sigma | -0.555 |
Lange | -0.448 |
alist | -0.447 |
Cantor | -0.429 |
sonian | -0.420 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
aredevil | +2.248 |
vez | +2.145 |
rams | +2.069 |
emies | +2.004 |
irez | +1.936 |
Neg logit contributions | |
Sigma | -2.263 |
alist | -1.842 |
Lange | -1.837 |
Cantor | -1.784 |
Sachs | -1.736 |
Token | way |
Token ID | 835 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Sigma | +1.549 |
Lange | +1.314 |
alist | +1.313 |
Cantor | +1.275 |
chamber | +1.267 |
Neg logit contributions | |
aredevil | -0.902 |
vez | -0.850 |
rams | -0.801 |
emies | -0.774 |
irez | -0.741 |
Token | . |
Token ID | 13 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
Sigma | +0.814 |
Lange | +0.657 |
alist | +0.656 |
Cantor | +0.629 |
chamber | +0.616 |
Neg logit contributions | |
aredevil | -0.880 |
vez | -0.837 |
rams | -0.810 |
emies | -0.785 |
irez | -0.766 |
Token |
|
Token ID | 198 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
aredevil | +0.275 |
vez | +0.261 |
rams | +0.252 |
emies | +0.243 |
subp | +0.239 |
Neg logit contributions | |
Sigma | -0.294 |
Lange | -0.240 |
alist | -0.237 |
Cantor | -0.231 |
Sachs | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
aredevil | +1.236 |
vez | +1.180 |
rams | +1.136 |
emies | +1.098 |
subp | +1.050 |
Neg logit contributions | |
Sigma | -1.566 |
Lange | -1.308 |
alist | -1.303 |
Cantor | -1.257 |
sonian | -1.236 |
Token | TV |
Token ID | 6849 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
aredevil | +1.172 |
vez | +1.108 |
rams | +1.064 |
emies | +1.022 |
subp | +0.987 |
Neg logit contributions | |
Sigma | -1.577 |
Lange | -1.319 |
alist | -1.318 |
Cantor | -1.274 |
sonian | -1.254 |
Token | LINE |
Token ID | 24027 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
aredevil | +1.580 |
vez | +1.503 |
rams | +1.440 |
emies | +1.381 |
irez | +1.331 |
Neg logit contributions | |
Sigma | -1.949 |
alist | -1.607 |
Lange | -1.604 |
Cantor | -1.557 |
chamber | -1.538 |
Token | | |
Token ID | 930 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
aredevil | +5.900 |
vez | +5.685 |
emies | +5.434 |
rams | +5.349 |
atti | +5.084 |
Neg logit contributions | |
Sigma | -6.099 |
princ | -5.239 |
alist | -5.053 |
Lange | -4.928 |
Cantor | -4.770 |
Token | Speaking |
Token ID | 21393 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
aredevil | +1.268 |
vez | +1.209 |
rams | +1.169 |
emies | +1.132 |
subp | +1.100 |
Neg logit contributions | |
Sigma | -1.232 |
alist | -1.000 |
Lange | -0.997 |
Cantor | -0.956 |
sonian | -0.942 |
Token | of |
Token ID | 286 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Sigma | +1.356 |
Lange | +1.135 |
alist | +1.133 |
Cantor | +1.094 |
chamber | +1.076 |
Neg logit contributions | |
aredevil | -1.072 |
vez | -1.020 |
rams | -0.975 |
emies | -0.937 |
irez | -0.909 |
Token | people |
Token ID | 661 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
aredevil | +0.683 |
vez | +0.652 |
rams | +0.631 |
emies | +0.612 |
subp | +0.596 |
Neg logit contributions | |
Sigma | -0.610 |
Lange | -0.488 |
alist | -0.488 |
Cantor | -0.467 |
sonian | -0.458 |
Token | with |
Token ID | 351 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Sigma | +0.534 |
Lange | +0.431 |
alist | +0.429 |
Cantor | +0.412 |
Sachs | +0.404 |
Neg logit contributions | |
aredevil | -0.576 |
vez | -0.548 |
rams | -0.534 |
emies | -0.516 |
subp | -0.501 |
Token | world |
Token ID | 995 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
aredevil | +0.174 |
vez | +0.165 |
rams | +0.159 |
emies | +0.154 |
irez | +0.149 |
Neg logit contributions | |
Sigma | -0.193 |
Lange | -0.158 |
alist | -0.158 |
Cantor | -0.153 |
chamber | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
aredevil | +0.166 |
vez | +0.158 |
rams | +0.153 |
emies | +0.148 |
subp | +0.144 |
Neg logit contributions | |
Sigma | -0.163 |
Lange | -0.132 |
alist | -0.132 |
Cantor | -0.127 |
sonian | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
aredevil | +0.516 |
vez | +0.489 |
rams | +0.473 |
emies | +0.457 |
subp | +0.445 |
Neg logit contributions | |
Sigma | -0.546 |
Lange | -0.446 |
alist | -0.443 |
Cantor | -0.429 |
Sachs | -0.419 |
Token |
|
Token ID | 198 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
aredevil | +1.373 |
vez | +1.311 |
rams | +1.263 |
emies | +1.220 |
subp | +1.167 |
Neg logit contributions | |
Sigma | -1.748 |
Lange | -1.460 |
alist | -1.455 |
Cantor | -1.404 |
sonian | -1.383 |
Token | TV |
Token ID | 6849 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
aredevil | +0.878 |
vez | +0.827 |
rams | +0.799 |
emies | +0.771 |
subp | +0.749 |
Neg logit contributions | |
Sigma | -1.098 |
alist | -0.915 |
Lange | -0.914 |
Cantor | -0.879 |
sonian | -0.870 |
Token | LINE |
Token ID | 24027 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
aredevil | +0.998 |
vez | +0.948 |
rams | +0.913 |
emies | +0.880 |
subp | +0.854 |
Neg logit contributions | |
Sigma | -1.138 |
alist | -0.938 |
Lange | -0.937 |
Cantor | -0.903 |
sonian | -0.888 |
Token | | |
Token ID | 930 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
aredevil | +5.965 |
vez | +5.613 |
emies | +5.411 |
rams | +5.364 |
BILITIES | +5.124 |
Neg logit contributions | |
Sigma | -6.043 |
princ | -5.227 |
alist | -5.181 |
Lange | -4.895 |
chamber | -4.756 |
Token | Do |
Token ID | 2141 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
aredevil | +0.266 |
vez | +0.253 |
rams | +0.245 |
emies | +0.237 |
subp | +0.231 |
Neg logit contributions | |
Sigma | -0.262 |
Lange | -0.213 |
alist | -0.211 |
Cantor | -0.204 |
Sachs | -0.200 |
Token | you |
Token ID | 345 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
aredevil | +0.911 |
vez | +0.861 |
rams | +0.826 |
emies | +0.794 |
subp | +0.768 |
Neg logit contributions | |
Sigma | -1.226 |
Lange | -1.026 |
alist | -1.025 |
Cantor | -0.991 |
sonian | -0.975 |
Token | feel |
Token ID | 1254 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Sigma | +0.874 |
alist | +0.701 |
Lange | +0.697 |
Cantor | +0.669 |
chamber | +0.663 |
Neg logit contributions | |
aredevil | -0.968 |
vez | -0.925 |
rams | -0.894 |
emies | -0.864 |
irez | -0.845 |
Token | like |
Token ID | 588 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aredevil | +0.880 |
vez | +0.839 |
rams | +0.811 |
emies | +0.785 |
subp | +0.764 |
Neg logit contributions | |
Sigma | -0.844 |
Lange | -0.683 |
alist | -0.680 |
Cantor | -0.654 |
sonian | -0.639 |
Token | familiar |
Token ID | 5385 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
aredevil | +1.013 |
vez | +0.967 |
rams | +0.937 |
emies | +0.909 |
subp | +0.885 |
Neg logit contributions | |
Sigma | -0.915 |
alist | -0.736 |
Lange | -0.733 |
Cantor | -0.703 |
sonian | -0.690 |
Token | pattern |
Token ID | 3912 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
aredevil | +0.290 |
vez | +0.277 |
rams | +0.268 |
emies | +0.260 |
subp | +0.253 |
Neg logit contributions | |
Sigma | -0.255 |
alist | -0.204 |
Lange | -0.204 |
Cantor | -0.195 |
sonian | -0.191 |
Token | ? |
Token ID | 30 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Sigma | +1.625 |
alist | +1.327 |
Lange | +1.322 |
Cantor | +1.270 |
chamber | +1.250 |
Neg logit contributions | |
aredevil | -1.662 |
vez | -1.576 |
rams | -1.521 |
emies | -1.469 |
irez | -1.425 |
Token |
|
Token ID | 198 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
aredevil | +1.949 |
vez | +1.865 |
rams | +1.789 |
emies | +1.732 |
subp | +1.666 |
Neg logit contributions | |
Sigma | -2.214 |
alist | -1.852 |
Lange | -1.818 |
sonian | -1.748 |
Cantor | -1.747 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
aredevil | +3.937 |
vez | +3.816 |
rams | +3.678 |
emies | +3.590 |
atti | +3.359 |
Neg logit contributions | |
Sigma | -6.664 |
princ | -6.047 |
Lange | -5.729 |
alist | -5.712 |
Cantor | -5.479 |
Token | Yeah |
Token ID | 10995 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
aredevil | +4.738 |
vez | +4.611 |
rams | +4.462 |
emies | +4.253 |
irez | +4.097 |
Neg logit contributions | |
Sigma | -5.164 |
Lange | -4.167 |
alist | -4.162 |
Cantor | -4.005 |
chamber | -3.995 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
aredevil | +5.646 |
vez | +5.451 |
rams | +5.290 |
emies | +5.094 |
subp | +4.918 |
Neg logit contributions | |
Sigma | -6.377 |
alist | -5.359 |
Lange | -5.192 |
sonian | -5.109 |
Cantor | -4.999 |
Token | but |
Token ID | 475 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aredevil | +3.098 |
vez | +2.954 |
rams | +2.852 |
emies | +2.751 |
subp | +2.674 |
Neg logit contributions | |
Sigma | -3.461 |
alist | -2.870 |
Lange | -2.838 |
Cantor | -2.735 |
sonian | -2.725 |
Token | that |
Token ID | 326 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
aredevil | +0.441 |
vez | +0.418 |
rams | +0.403 |
emies | +0.390 |
subp | +0.379 |
Neg logit contributions | |
Sigma | -0.477 |
Lange | -0.391 |
alist | -0.387 |
Cantor | -0.376 |
chamber | -0.367 |
Token | is |
Token ID | 318 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
aredevil | +1.440 |
vez | +1.371 |
rams | +1.325 |
emies | +1.283 |
subp | +1.252 |
Neg logit contributions | |
Sigma | -1.435 |
alist | -1.170 |
Lange | -1.165 |
Cantor | -1.118 |
sonian | -1.105 |
Token | why |
Token ID | 1521 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
Sigma | +1.284 |
Lange | +1.034 |
alist | +1.010 |
Cantor | +0.988 |
chamber | +0.963 |
Neg logit contributions | |
aredevil | -1.428 |
vez | -1.348 |
rams | -1.312 |
emies | -1.278 |
irez | -1.241 |
Token | that |
Token ID | 326 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
aredevil | +0.187 |
vez | +0.177 |
rams | +0.171 |
emies | +0.166 |
subp | +0.161 |
Neg logit contributions | |
Sigma | -0.204 |
Lange | -0.168 |
alist | -0.166 |
Cantor | -0.161 |
Sachs | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
aredevil | +0.153 |
vez | +0.146 |
rams | +0.142 |
emies | +0.138 |
subp | +0.134 |
Neg logit contributions | |
Sigma | -0.137 |
alist | -0.110 |
Lange | -0.109 |
Cantor | -0.105 |
sonian | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
Sigma | +0.212 |
Lange | +0.174 |
alist | +0.171 |
Cantor | +0.167 |
Sachs | +0.163 |
Neg logit contributions | |
aredevil | -0.198 |
vez | -0.188 |
rams | -0.182 |
emies | -0.175 |
subp | -0.172 |
Token |
|
Token ID | 198 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
aredevil | +1.454 |
vez | +1.389 |
rams | +1.336 |
emies | +1.293 |
subp | +1.233 |
Neg logit contributions | |
Sigma | -1.876 |
Lange | -1.569 |
alist | -1.563 |
Cantor | -1.508 |
sonian | -1.484 |
Token | TV |
Token ID | 6849 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
aredevil | +1.036 |
vez | +0.979 |
rams | +0.940 |
emies | +0.905 |
subp | +0.875 |
Neg logit contributions | |
Sigma | -1.374 |
Lange | -1.148 |
alist | -1.148 |
Cantor | -1.108 |
sonian | -1.092 |
Token | LINE |
Token ID | 24027 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
aredevil | +1.319 |
vez | +1.254 |
rams | +1.204 |
emies | +1.156 |
irez | +1.114 |
Neg logit contributions | |
Sigma | -1.597 |
alist | -1.318 |
Lange | -1.314 |
Cantor | -1.274 |
chamber | -1.256 |
Token | | |
Token ID | 930 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
aredevil | +5.860 |
vez | +5.637 |
emies | +5.393 |
rams | +5.319 |
atti | +5.047 |
Neg logit contributions | |
Sigma | -6.018 |
princ | -5.158 |
alist | -5.000 |
Lange | -4.867 |
Cantor | -4.704 |
Token | Can |
Token ID | 1680 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
aredevil | +1.176 |
vez | +1.121 |
rams | +1.084 |
emies | +1.049 |
subp | +1.018 |
Neg logit contributions | |
Sigma | -1.158 |
alist | -0.945 |
Lange | -0.938 |
Cantor | -0.900 |
sonian | -0.889 |
Token | Ann |
Token ID | 5506 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
aredevil | +0.550 |
vez | +0.521 |
rams | +0.500 |
emies | +0.480 |
subp | +0.467 |
Neg logit contributions | |
Sigma | -0.704 |
Lange | -0.588 |
alist | -0.586 |
Cantor | -0.566 |
sonian | -0.556 |
Token | al |
Token ID | 282 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
aredevil | +1.547 |
vez | +1.495 |
rams | +1.455 |
emies | +1.426 |
subp | +1.388 |
Neg logit contributions | |
Sigma | -0.797 |
Lange | -0.575 |
alist | -0.561 |
Cantor | -0.536 |
sonian | -0.522 |
Token | ise |
Token ID | 786 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
aredevil | +0.073 |
vez | +0.069 |
rams | +0.067 |
emies | +0.065 |
subp | +0.062 |
Neg logit contributions | |
Sigma | -0.082 |
Lange | -0.067 |
alist | -0.067 |
Cantor | -0.065 |
sonian | -0.063 |
Token | as |
Token ID | 355 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
Sigma | +0.361 |
Lange | +0.293 |
alist | +0.293 |
Cantor | +0.281 |
sonian | +0.276 |
Neg logit contributions | |
aredevil | -0.368 |
vez | -0.350 |
rams | -0.339 |
emies | -0.328 |
subp | -0.319 |
Token | I |
Token ID | 314 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Sigma | +1.447 |
Lange | +1.166 |
alist | +1.149 |
Cantor | +1.116 |
chamber | +1.092 |
Neg logit contributions | |
aredevil | -1.531 |
vez | -1.453 |
rams | -1.408 |
emies | -1.369 |
irez | -1.322 |
Token | implant |
Token ID | 29016 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
aredevil | +0.878 |
vez | +0.838 |
rams | +0.812 |
emies | +0.787 |
subp | +0.766 |
Neg logit contributions | |
Sigma | -0.790 |
Lange | -0.634 |
alist | -0.634 |
Cantor | -0.606 |
sonian | -0.595 |
Token | it |
Token ID | 340 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Sigma | +0.562 |
Lange | +0.454 |
alist | +0.452 |
Cantor | +0.434 |
chamber | +0.425 |
Neg logit contributions | |
aredevil | -0.594 |
vez | -0.564 |
rams | -0.545 |
emies | -0.531 |
subp | -0.515 |
Token | and |
Token ID | 290 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
aredevil | +1.424 |
vez | +1.367 |
rams | +1.318 |
emies | +1.277 |
subp | +1.242 |
Neg logit contributions | |
Sigma | -1.338 |
alist | -1.081 |
Lange | -1.079 |
Cantor | -1.035 |
sonian | -1.018 |
Token | prove |
Token ID | 5879 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
aredevil | +1.210 |
vez | +1.156 |
rams | +1.118 |
emies | +1.080 |
subp | +1.053 |
Neg logit contributions | |
Sigma | -1.198 |
alist | -0.977 |
Lange | -0.974 |
Cantor | -0.934 |
sonian | -0.923 |
Token | that |
Token ID | 326 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
aredevil | +5.466 |
vez | +5.283 |
rams | +5.126 |
emies | +4.814 |
subp | +4.757 |
Neg logit contributions | |
Sigma | -6.412 |
Lange | -5.374 |
alist | -5.338 |
sonian | -5.131 |
Cantor | -5.121 |
Token | it |
Token ID | 340 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
aredevil | +0.650 |
vez | +0.617 |
rams | +0.594 |
emies | +0.573 |
subp | +0.555 |
Neg logit contributions | |
Sigma | -0.771 |
alist | -0.638 |
Lange | -0.638 |
Cantor | -0.614 |
sonian | -0.605 |
Token | � |
Token ID | 447 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
aredevil | +1.033 |
vez | +0.986 |
rams | +0.951 |
emies | +0.920 |
subp | +0.894 |
Neg logit contributions | |
Sigma | -1.058 |
Lange | -0.862 |
alist | -0.861 |
Cantor | -0.828 |
sonian | -0.813 |
Token | � |
Token ID | 247 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
aredevil | +0.607 |
vez | +0.554 |
rams | +0.527 |
emies | +0.501 |
subp | +0.476 |
Neg logit contributions | |
Sigma | -1.279 |
Lange | -1.109 |
alist | -1.104 |
Cantor | -1.071 |
sonian | -1.060 |
Token | s |
Token ID | 82 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
aredevil | +0.755 |
vez | +0.720 |
rams | +0.698 |
emies | +0.678 |
subp | +0.661 |
Neg logit contributions | |
Sigma | -0.631 |
alist | -0.502 |
Lange | -0.501 |
Cantor | -0.478 |
sonian | -0.468 |
Token | topia |
Token ID | 46575 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
aredevil | +1.244 |
vez | +1.185 |
rams | +1.145 |
emies | +1.110 |
subp | +1.080 |
Neg logit contributions | |
Sigma | -1.212 |
Lange | -0.983 |
alist | -0.982 |
Cantor | -0.940 |
sonian | -0.927 |
Token | ( |
Token ID | 357 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
Sigma | +0.927 |
Lange | +0.744 |
alist | +0.739 |
Cantor | +0.712 |
chamber | +0.698 |
Neg logit contributions | |
aredevil | -0.990 |
vez | -0.942 |
rams | -0.911 |
emies | -0.882 |
irez | -0.857 |
Token | � |
Token ID | 30266 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
aredevil | +0.146 |
vez | +0.139 |
rams | +0.134 |
emies | +0.130 |
subp | +0.126 |
Neg logit contributions | |
Sigma | -0.142 |
Lange | -0.115 |
alist | -0.115 |
Cantor | -0.110 |
sonian | -0.108 |
Token | � |
Token ID | 109 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
aredevil | +1.769 |
vez | +1.674 |
rams | +1.610 |
emies | +1.551 |
subp | +1.502 |
Neg logit contributions | |
Sigma | -2.220 |
Lange | -1.846 |
alist | -1.845 |
Cantor | -1.780 |
sonian | -1.753 |
Token | 方 |
Token ID | 43095 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
aredevil | +1.631 |
vez | +1.561 |
rams | +1.511 |
emies | +1.466 |
subp | +1.426 |
Neg logit contributions | |
Sigma | -1.424 |
alist | -1.141 |
Lange | -1.137 |
Cantor | -1.088 |
sonian | -1.068 |
Token | � |
Token ID | 23877 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
aredevil | +2.236 |
vez | +2.135 |
rams | +2.064 |
emies | +1.999 |
subp | +1.942 |
Neg logit contributions | |
Sigma | -2.188 |
alist | -1.778 |
Lange | -1.774 |
Cantor | -1.702 |
sonian | -1.676 |
Token | � |
Token ID | 229 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
aredevil | +4.259 |
vez | +4.159 |
rams | +3.975 |
emies | +3.798 |
irez | +3.545 |
Neg logit contributions | |
Sigma | -7.743 |
alist | -6.599 |
Lange | -6.552 |
sonian | -6.363 |
Cantor | -6.355 |
Token | � |
Token ID | 162 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
aredevil | +2.370 |
vez | +2.267 |
rams | +2.190 |
emies | +2.121 |
subp | +2.066 |
Neg logit contributions | |
Sigma | -2.258 |
alist | -1.835 |
Lange | -1.827 |
Cantor | -1.752 |
sonian | -1.725 |
Token | � |
Token ID | 252 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
aredevil | +1.155 |
vez | +1.089 |
rams | +1.042 |
emies | +1.000 |
subp | +0.963 |
Neg logit contributions | |
Sigma | -1.726 |
alist | -1.455 |
Lange | -1.455 |
Cantor | -1.408 |
sonian | -1.389 |
Token | � |
Token ID | 250 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
aredevil | +1.132 |
vez | +1.052 |
rams | +0.998 |
emies | +0.947 |
subp | +0.902 |
Neg logit contributions | |
Sigma | -2.316 |
alist | -1.992 |
Lange | -1.987 |
Cantor | -1.936 |
sonian | -1.915 |
Token | � |
Token ID | 40367 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
aredevil | +1.081 |
vez | +1.030 |
rams | +0.996 |
emies | +0.964 |
subp | +0.937 |
Neg logit contributions | |
Sigma | -1.067 |
Lange | -0.866 |
alist | -0.865 |
Cantor | -0.830 |
sonian | -0.815 |
Token | failures |
Token ID | 15536 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Sigma | +0.315 |
alist | +0.253 |
Lange | +0.253 |
Cantor | +0.242 |
sonian | +0.238 |
Neg logit contributions | |
aredevil | -0.351 |
vez | -0.334 |
rams | -0.324 |
emies | -0.314 |
subp | -0.307 |
Token | over |
Token ID | 625 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
Sigma | +2.152 |
Lange | +1.717 |
alist | +1.712 |
Cantor | +1.636 |
chamber | +1.607 |
Neg logit contributions | |
aredevil | -2.565 |
vez | -2.434 |
rams | -2.369 |
emies | -2.293 |
irez | -2.238 |
Token | the |
Token ID | 262 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
Sigma | +0.140 |
Lange | +0.111 |
alist | +0.111 |
Cantor | +0.106 |
sonian | +0.104 |
Neg logit contributions | |
aredevil | -0.169 |
vez | -0.162 |
rams | -0.157 |
emies | -0.152 |
subp | -0.149 |
Token | last |
Token ID | 938 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
aredevil | +0.157 |
vez | +0.151 |
rams | +0.146 |
emies | +0.142 |
subp | +0.139 |
Neg logit contributions | |
Sigma | -0.122 |
alist | -0.096 |
Lange | -0.096 |
Cantor | -0.091 |
sonian | -0.090 |
Token | ten |
Token ID | 3478 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Sigma | +0.811 |
Lange | +0.670 |
alist | +0.670 |
Cantor | +0.646 |
sonian | +0.633 |
Neg logit contributions | |
aredevil | -0.691 |
vez | -0.655 |
rams | -0.631 |
emies | -0.609 |
subp | -0.589 |
Token | years |
Token ID | 812 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aredevil | +0.791 |
vez | +0.745 |
rams | +0.715 |
emies | +0.687 |
subp | +0.662 |
Neg logit contributions | |
Sigma | -1.143 |
Lange | -0.964 |
alist | -0.963 |
Cantor | -0.931 |
sonian | -0.919 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
Sigma | +3.540 |
alist | +2.834 |
Lange | +2.822 |
Cantor | +2.715 |
chamber | +2.673 |
Neg logit contributions | |
aredevil | -4.152 |
vez | -3.944 |
rams | -3.806 |
emies | -3.689 |
irez | -3.604 |
Token | Mr |
Token ID | 1770 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
aredevil | +0.052 |
vez | +0.049 |
rams | +0.048 |
emies | +0.046 |
subp | +0.045 |
Neg logit contributions | |
Sigma | -0.048 |
alist | -0.039 |
Lange | -0.038 |
Cantor | -0.037 |
sonian | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
Sigma | +0.923 |
Lange | +0.740 |
alist | +0.739 |
Cantor | +0.708 |
sonian | +0.694 |
Neg logit contributions | |
aredevil | -1.034 |
vez | -0.987 |
rams | -0.956 |
emies | -0.927 |
subp | -0.902 |
Token | Brady |
Token ID | 15260 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
Sigma | +0.265 |
alist | +0.211 |
Lange | +0.211 |
Cantor | +0.202 |
sonian | +0.198 |
Neg logit contributions | |
aredevil | -0.307 |
vez | -0.294 |
rams | -0.285 |
emies | -0.276 |
subp | -0.269 |
Token | lists |
Token ID | 8341 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
aredevil | +2.059 |
vez | +1.968 |
rams | +1.896 |
emies | +1.831 |
subp | +1.789 |
Neg logit contributions | |
Sigma | -2.269 |
alist | -1.859 |
Lange | -1.855 |
Cantor | -1.782 |
sonian | -1.752 |
Token | all |
Token ID | 477 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Sigma | +0.029 |
Lange | +0.023 |
alist | +0.023 |
Cantor | +0.022 |
sonian | +0.022 |
Neg logit contributions | |
aredevil | -0.031 |
vez | -0.030 |
rams | -0.029 |
emies | -0.028 |
subp | -0.027 |
Token | be |
Token ID | 307 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
aredevil | +0.563 |
vez | +0.537 |
rams | +0.518 |
emies | +0.503 |
subp | +0.490 |
Neg logit contributions | |
Sigma | -0.539 |
Lange | -0.436 |
alist | -0.435 |
Cantor | -0.418 |
sonian | -0.410 |
Token | if |
Token ID | 611 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
aredevil | +1.767 |
vez | +1.692 |
rams | +1.630 |
emies | +1.583 |
subp | +1.536 |
Neg logit contributions | |
Sigma | -1.795 |
Lange | -1.463 |
alist | -1.460 |
Cantor | -1.401 |
sonian | -1.381 |
Token | right |
Token ID | 826 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
aredevil | +1.110 |
vez | +1.064 |
rams | +1.029 |
emies | +0.998 |
subp | +0.971 |
Neg logit contributions | |
Sigma | -0.995 |
alist | -0.798 |
Lange | -0.797 |
Cantor | -0.760 |
sonian | -0.749 |
Token | - |
Token ID | 12 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Sigma | +3.272 |
alist | +2.744 |
Lange | +2.696 |
Cantor | +2.647 |
Sachs | +2.607 |
Neg logit contributions | |
aredevil | -2.791 |
vez | -2.579 |
rams | -2.497 |
emies | -2.393 |
subp | -2.360 |
Token | wing |
Token ID | 5469 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Sigma | +0.861 |
alist | +0.640 |
Lange | +0.634 |
Cantor | +0.597 |
sonian | +0.580 |
Neg logit contributions | |
aredevil | -1.561 |
vez | -1.500 |
rams | -1.460 |
emies | -1.424 |
subp | -1.399 |
Token | ers |
Token ID | 364 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Sigma | +3.052 |
alist | +2.420 |
Lange | +2.410 |
Cantor | +2.359 |
chamber | +2.273 |
Neg logit contributions | |
aredevil | -3.830 |
vez | -3.615 |
rams | -3.489 |
emies | -3.375 |
subp | -3.335 |
Token | had |
Token ID | 550 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Sigma | +1.160 |
Lange | +0.942 |
alist | +0.941 |
Cantor | +0.909 |
Sachs | +0.890 |
Neg logit contributions | |
aredevil | -1.170 |
vez | -1.105 |
rams | -1.075 |
emies | -1.039 |
subp | -1.011 |
Token | refused |
Token ID | 6520 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
aredevil | +0.723 |
vez | +0.690 |
rams | +0.666 |
emies | +0.644 |
subp | +0.626 |
Neg logit contributions | |
Sigma | -0.744 |
alist | -0.606 |
Lange | -0.606 |
Cantor | -0.582 |
sonian | -0.573 |
Token | to |
Token ID | 284 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
aredevil | +0.906 |
vez | +0.874 |
rams | +0.843 |
emies | +0.818 |
subp | +0.794 |
Neg logit contributions | |
Sigma | -0.830 |
alist | -0.666 |
Lange | -0.663 |
Cantor | -0.629 |
sonian | -0.627 |
Token | support |
Token ID | 1104 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Sigma | +1.139 |
alist | +0.920 |
Lange | +0.920 |
Cantor | +0.883 |
sonian | +0.865 |
Neg logit contributions | |
aredevil | -1.188 |
vez | -1.132 |
rams | -1.095 |
emies | -1.060 |
subp | -1.031 |
Token | from |
Token ID | 422 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aredevil | +3.060 |
vez | +2.971 |
rams | +2.855 |
emies | +2.758 |
subp | +2.703 |
Neg logit contributions | |
Sigma | -2.904 |
alist | -2.382 |
Lange | -2.331 |
sonian | -2.251 |
Cantor | -2.244 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Sigma | +0.335 |
Lange | +0.267 |
alist | +0.266 |
Cantor | +0.255 |
chamber | +0.249 |
Neg logit contributions | |
aredevil | -0.394 |
vez | -0.375 |
rams | -0.364 |
emies | -0.353 |
subp | -0.344 |
Token | Shank |
Token ID | 41595 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Sigma | +1.486 |
Lange | +1.192 |
alist | +1.174 |
Cantor | +1.137 |
chamber | +1.108 |
Neg logit contributions | |
aredevil | -1.703 |
vez | -1.606 |
rams | -1.564 |
emies | -1.521 |
subp | -1.479 |
Token | ar |
Token ID | 283 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Sigma | +1.407 |
alist | +1.117 |
Lange | +1.114 |
Cantor | +1.059 |
Sachs | +1.034 |
Neg logit contributions | |
aredevil | -1.745 |
vez | -1.652 |
rams | -1.591 |
emies | -1.577 |
subp | -1.531 |
Token | Bh |
Token ID | 16581 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Sigma | +1.061 |
Lange | +0.847 |
alist | +0.839 |
Cantor | +0.806 |
Sachs | +0.786 |
Neg logit contributions | |
aredevil | -1.243 |
vez | -1.181 |
rams | -1.146 |
emies | -1.115 |
subp | -1.087 |
Token | ai |
Token ID | 1872 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Sigma | +1.370 |
alist | +1.152 |
Lange | +1.143 |
Cantor | +1.109 |
Sachs | +1.086 |
Neg logit contributions | |
aredevil | -1.020 |
vez | -0.959 |
rams | -0.911 |
emies | -0.887 |
subp | -0.869 |
Token | Veg |
Token ID | 8427 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
Sigma | +3.221 |
Lange | +2.622 |
alist | +2.570 |
Cantor | +2.476 |
Sachs | +2.433 |
Neg logit contributions | |
aredevil | -3.516 |
vez | -3.215 |
rams | -3.149 |
emies | -3.074 |
subp | -2.985 |
Token | ad |
Token ID | 324 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
aredevil | +0.128 |
vez | +0.122 |
rams | +0.118 |
emies | +0.114 |
subp | +0.111 |
Neg logit contributions | |
Sigma | -0.122 |
Lange | -0.098 |
alist | -0.098 |
Cantor | -0.094 |
sonian | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Sigma | +1.350 |
Lange | +1.103 |
alist | +1.101 |
Cantor | +1.057 |
Sachs | +1.038 |
Neg logit contributions | |
aredevil | -1.311 |
vez | -1.241 |
rams | -1.201 |
emies | -1.161 |
subp | -1.140 |
Token | Union |
Token ID | 4479 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Sigma | +0.542 |
Lange | +0.443 |
alist | +0.441 |
Cantor | +0.427 |
Sachs | +0.417 |
Neg logit contributions | |
aredevil | -0.514 |
vez | -0.487 |
rams | -0.471 |
emies | -0.456 |
subp | -0.444 |
Token | Minister |
Token ID | 4139 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Sigma | +1.444 |
Lange | +1.166 |
alist | +1.159 |
Cantor | +1.108 |
chamber | +1.104 |
Neg logit contributions | |
aredevil | -1.601 |
vez | -1.511 |
rams | -1.471 |
emies | -1.426 |
subp | -1.389 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Sigma | +0.833 |
Lange | +0.661 |
alist | +0.660 |
Cantor | +0.627 |
chamber | +0.616 |
Neg logit contributions | |
aredevil | -1.015 |
vez | -0.969 |
rams | -0.939 |
emies | -0.917 |
irez | -0.886 |
Token | shrink |
Token ID | 22085 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
aredevil | +0.380 |
vez | +0.363 |
rams | +0.352 |
emies | +0.341 |
subp | +0.331 |
Neg logit contributions | |
Sigma | -0.336 |
Lange | -0.269 |
alist | -0.269 |
Cantor | -0.257 |
sonian | -0.252 |
Token | age |
Token ID | 496 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
aredevil | +1.686 |
vez | +1.607 |
rams | +1.554 |
emies | +1.504 |
subp | +1.463 |
Neg logit contributions | |
Sigma | -1.659 |
Lange | -1.346 |
alist | -1.345 |
Cantor | -1.291 |
sonian | -1.269 |
Token | |
Token ID | 22020 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
aredevil | +0.141 |
vez | +0.134 |
rams | +0.130 |
emies | +0.126 |
subp | +0.122 |
Neg logit contributions | |
Sigma | -0.146 |
alist | -0.119 |
Lange | -0.119 |
Cantor | -0.114 |
sonian | -0.112 |
Token | – |
Token ID | 1906 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
aredevil | +0.133 |
vez | +0.127 |
rams | +0.122 |
emies | +0.119 |
subp | +0.115 |
Neg logit contributions | |
Sigma | -0.134 |
alist | -0.110 |
Lange | -0.109 |
Cantor | -0.105 |
chamber | -0.103 |
Token | frequently |
Token ID | 6777 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Sigma | +0.888 |
Lange | +0.715 |
alist | +0.714 |
Cantor | +0.682 |
Sachs | +0.670 |
Neg logit contributions | |
aredevil | -0.977 |
vez | -0.932 |
rams | -0.903 |
emies | -0.879 |
subp | -0.848 |
Token | attributed |
Token ID | 14183 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Sigma | +3.358 |
Lange | +2.714 |
alist | +2.697 |
Cantor | +2.574 |
chamber | +2.547 |
Neg logit contributions | |
aredevil | -3.707 |
vez | -3.533 |
rams | -3.430 |
emies | -3.362 |
irez | -3.228 |
Token | by |
Token ID | 416 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Sigma | +2.498 |
alist | +1.993 |
Lange | +1.986 |
Cantor | +1.896 |
Sachs | +1.856 |
Neg logit contributions | |
aredevil | -2.959 |
vez | -2.826 |
rams | -2.739 |
emies | -2.653 |
subp | -2.588 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Sigma | +1.065 |
Lange | +0.859 |
alist | +0.854 |
Cantor | +0.821 |
Sachs | +0.806 |
Neg logit contributions | |
aredevil | -1.182 |
vez | -1.122 |
rams | -1.089 |
emies | -1.057 |
irez | -1.023 |
Token | Iranian |
Token ID | 10704 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
Sigma | +0.994 |
Lange | +0.806 |
alist | +0.805 |
Cantor | +0.770 |
chamber | +0.765 |
Neg logit contributions | |
aredevil | -1.060 |
vez | -0.999 |
rams | -0.967 |
emies | -0.940 |
irez | -0.905 |
Token | water |
Token ID | 1660 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Sigma | +0.288 |
Lange | +0.231 |
alist | +0.231 |
chamber | +0.221 |
Cantor | +0.220 |
Neg logit contributions | |
aredevil | -0.316 |
vez | -0.298 |
rams | -0.289 |
emies | -0.281 |
subp | -0.272 |
Token | or |
Token ID | 393 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
aredevil | +0.788 |
vez | +0.752 |
rams | +0.727 |
emies | +0.705 |
subp | +0.686 |
Neg logit contributions | |
Sigma | -0.726 |
alist | -0.585 |
Lange | -0.584 |
Cantor | -0.559 |
sonian | -0.549 |
Token | propulsion |
Token ID | 38873 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Sigma | +0.131 |
Lange | +0.104 |
alist | +0.104 |
Cantor | +0.099 |
chamber | +0.097 |
Neg logit contributions | |
aredevil | -0.157 |
vez | -0.150 |
rams | -0.145 |
emies | -0.141 |
subp | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aredevil | +1.832 |
vez | +1.752 |
rams | +1.695 |
emies | +1.634 |
subp | +1.604 |
Neg logit contributions | |
Sigma | -1.820 |
Lange | -1.480 |
alist | -1.470 |
Cantor | -1.416 |
sonian | -1.400 |
Token | The |
Token ID | 383 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
aredevil | +0.359 |
vez | +0.343 |
rams | +0.332 |
emies | +0.322 |
subp | +0.313 |
Neg logit contributions | |
Sigma | -0.339 |
alist | -0.274 |
Lange | -0.274 |
Cantor | -0.262 |
sonian | -0.259 |
Token | sax |
Token ID | 46909 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Sigma | +0.311 |
alist | +0.250 |
Lange | +0.249 |
Cantor | +0.240 |
chamber | +0.234 |
Neg logit contributions | |
aredevil | -0.345 |
vez | -0.329 |
rams | -0.318 |
emies | -0.309 |
subp | -0.300 |
Token | ophon |
Token ID | 48982 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Sigma | +4.077 |
alist | +3.436 |
Lange | +3.321 |
Cantor | +3.215 |
chamber | +3.177 |
Neg logit contributions | |
aredevil | -3.962 |
vez | -3.753 |
rams | -3.612 |
emies | -3.529 |
subp | -3.412 |
Token | ist |
Token ID | 396 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Sigma | +2.535 |
alist | +1.889 |
Lange | +1.745 |
Cantor | +1.645 |
chamber | +1.571 |
Neg logit contributions | |
aredevil | -5.944 |
vez | -5.713 |
rams | -5.584 |
emies | -5.444 |
subp | -5.375 |
Token | 's |
Token ID | 338 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Sigma | +1.957 |
alist | +1.576 |
Lange | +1.567 |
Cantor | +1.505 |
sonian | +1.476 |
Neg logit contributions | |
aredevil | -2.231 |
vez | -2.120 |
rams | -2.062 |
emies | -1.996 |
irez | -1.934 |
Token | disagreement |
Token ID | 25800 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
aredevil | +0.497 |
vez | +0.475 |
rams | +0.462 |
emies | +0.448 |
subp | +0.438 |
Neg logit contributions | |
Sigma | -0.401 |
Lange | -0.317 |
alist | -0.317 |
Cantor | -0.302 |
sonian | -0.296 |
Token | with |
Token ID | 351 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
aredevil | +0.235 |
vez | +0.225 |
rams | +0.217 |
emies | +0.211 |
subp | +0.205 |
Neg logit contributions | |
Sigma | -0.208 |
alist | -0.167 |
Lange | -0.167 |
Cantor | -0.160 |
sonian | -0.156 |
Token | � |
Token ID | 564 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
Sigma | +0.723 |
Lange | +0.576 |
alist | +0.574 |
Cantor | +0.550 |
chamber | +0.537 |
Neg logit contributions | |
aredevil | -0.855 |
vez | -0.815 |
rams | -0.790 |
emies | -0.769 |
subp | -0.746 |
Token | Jim |
Token ID | 5395 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
Sigma | +0.955 |
Lange | +0.781 |
alist | +0.765 |
Cantor | +0.742 |
chamber | +0.730 |
Neg logit contributions | |
aredevil | -1.093 |
vez | -1.034 |
rams | -1.006 |
emies | -0.975 |
irez | -0.950 |
Token | Rutherford |
Token ID | 49767 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Sigma | +2.292 |
Lange | +1.981 |
Cantor | +1.835 |
alist | +1.798 |
chamber | +1.783 |
Neg logit contributions | |
aredevil | -2.477 |
vez | -2.342 |
rams | -2.269 |
emies | -2.194 |
irez | -2.182 |
Token | approached |
Token ID | 10448 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Sigma | +1.492 |
Lange | +1.215 |
alist | +1.202 |
Cantor | +1.163 |
chamber | +1.145 |
Neg logit contributions | |
aredevil | -1.547 |
vez | -1.447 |
rams | -1.413 |
emies | -1.359 |
irez | -1.319 |
Token | Fle |
Token ID | 12005 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
Sigma | +1.139 |
Lange | +0.912 |
alist | +0.893 |
Cantor | +0.873 |
chamber | +0.842 |
Neg logit contributions | |
aredevil | -1.407 |
vez | -1.338 |
rams | -1.307 |
emies | -1.270 |
irez | -1.234 |
Token | ury |
Token ID | 1601 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
aredevil | +0.264 |
vez | +0.254 |
rams | +0.249 |
emies | +0.244 |
subp | +0.241 |
Neg logit contributions | |
Sigma | -0.073 |
alist | -0.042 |
Lange | -0.041 |
Cantor | -0.036 |
sonian | -0.034 |
Token | leading |
Token ID | 3756 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Sigma | +1.305 |
Lange | +1.044 |
alist | +1.035 |
Cantor | +0.995 |
chamber | +0.973 |
Neg logit contributions | |
aredevil | -1.532 |
vez | -1.453 |
rams | -1.413 |
emies | -1.370 |
irez | -1.330 |
Token | into |
Token ID | 656 |
Feature activation | +8.79e-04 |
Pos logit contributions | |
Sigma | +1.161 |
Lange | +0.907 |
alist | +0.899 |
Cantor | +0.867 |
chamber | +0.846 |
Neg logit contributions | |
aredevil | -1.538 |
vez | -1.473 |
rams | -1.430 |
emies | -1.388 |
irez | -1.355 |
Token | the |
Token ID | 262 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
Sigma | +0.003 |
alist | +0.002 |
Lange | +0.002 |
Cantor | +0.002 |
sonian | +0.002 |
Neg logit contributions | |
aredevil | -0.003 |
vez | -0.003 |
rams | -0.003 |
emies | -0.003 |
subp | -0.003 |
Token | March |
Token ID | 2805 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
Sigma | +0.241 |
alist | +0.195 |
Lange | +0.195 |
Cantor | +0.187 |
sonian | +0.183 |
Neg logit contributions | |
aredevil | -0.250 |
vez | -0.238 |
rams | -0.231 |
emies | -0.223 |
subp | -0.217 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Sigma | +0.226 |
Lange | +0.182 |
alist | +0.181 |
Cantor | +0.174 |
sonian | +0.170 |
Neg logit contributions | |
aredevil | -0.249 |
vez | -0.238 |
rams | -0.230 |
emies | -0.223 |
subp | -0.216 |
Token | NHL |
Token ID | 9481 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Sigma | +1.089 |
Lange | +0.895 |
alist | +0.888 |
Cantor | +0.860 |
sonian | +0.847 |
Neg logit contributions | |
aredevil | -0.998 |
vez | -0.952 |
rams | -0.916 |
emies | -0.887 |
irez | -0.855 |
Token | !), |
Token ID | 26290 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
aredevil | +1.668 |
vez | +1.589 |
rams | +1.534 |
emies | +1.484 |
subp | +1.440 |
Neg logit contributions | |
Sigma | -1.765 |
Lange | -1.443 |
alist | -1.443 |
Cantor | -1.387 |
sonian | -1.364 |
Token | Ko |
Token ID | 17634 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
aredevil | +1.967 |
vez | +1.882 |
rams | +1.831 |
emies | +1.776 |
subp | +1.735 |
Neg logit contributions | |
Sigma | -1.856 |
alist | -1.516 |
Lange | -1.497 |
Cantor | -1.439 |
sonian | -1.437 |
Token | ji |
Token ID | 7285 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Sigma | +0.846 |
alist | +0.682 |
Lange | +0.679 |
Cantor | +0.650 |
sonian | +0.640 |
Neg logit contributions | |
aredevil | -0.926 |
vez | -0.881 |
rams | -0.853 |
emies | -0.826 |
subp | -0.807 |
Token | took |
Token ID | 1718 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
Sigma | +1.932 |
Lange | +1.550 |
alist | +1.526 |
Cantor | +1.472 |
Sachs | +1.439 |
Neg logit contributions | |
aredevil | -2.264 |
vez | -2.153 |
rams | -2.082 |
emies | -2.020 |
subp | -1.963 |
Token | advantage |
Token ID | 4621 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Sigma | +0.262 |
Lange | +0.209 |
alist | +0.209 |
Cantor | +0.200 |
sonian | +0.196 |
Neg logit contributions | |
aredevil | -0.306 |
vez | -0.293 |
rams | -0.284 |
emies | -0.275 |
subp | -0.268 |
Token | of |
Token ID | 286 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
aredevil | +1.047 |
vez | +0.988 |
rams | +0.949 |
emies | +0.914 |
subp | +0.887 |
Neg logit contributions | |
Sigma | -1.476 |
Lange | -1.236 |
alist | -1.236 |
Cantor | -1.195 |
sonian | -1.181 |
Token | the |
Token ID | 262 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Sigma | +0.462 |
alist | +0.367 |
Lange | +0.367 |
Cantor | +0.350 |
sonian | +0.344 |
Neg logit contributions | |
aredevil | -0.552 |
vez | -0.528 |
rams | -0.512 |
emies | -0.497 |
subp | -0.484 |
Token | N |
Token ID | 399 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Sigma | +0.775 |
Lange | +0.624 |
alist | +0.622 |
Cantor | +0.597 |
chamber | +0.585 |
Neg logit contributions | |
aredevil | -0.834 |
vez | -0.794 |
rams | -0.767 |
emies | -0.744 |
subp | -0.722 |
Token | 64 |
Token ID | 2414 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
aredevil | +0.464 |
vez | +0.439 |
rams | +0.421 |
emies | +0.406 |
subp | +0.393 |
Neg logit contributions | |
Sigma | -0.590 |
alist | -0.492 |
Lange | -0.491 |
Cantor | -0.474 |
sonian | -0.467 |
Token | � |
Token ID | 447 |
Feature activation | -4.47e-03 |
Pos logit contributions | |
Sigma | +1.811 |
alist | +1.433 |
Lange | +1.424 |
Cantor | +1.361 |
chamber | +1.350 |
Neg logit contributions | |
aredevil | -2.156 |
vez | -2.035 |
rams | -1.968 |
emies | -1.915 |
irez | -1.864 |
Token | � |
Token ID | 247 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
aredevil | +0.009 |
vez | +0.008 |
rams | +0.008 |
emies | +0.008 |
subp | +0.007 |
Neg logit contributions | |
Sigma | -0.020 |
Lange | -0.017 |
alist | -0.017 |
Cantor | -0.017 |
sonian | -0.016 |
Token | best |
Token ID | 1266 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
aredevil | +0.873 |
vez | +0.833 |
rams | +0.808 |
emies | +0.780 |
subp | +0.761 |
Neg logit contributions | |
Sigma | -0.838 |
alist | -0.681 |
Lange | -0.680 |
Cantor | -0.652 |
sonian | -0.642 |
Token | attributes |
Token ID | 12608 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
aredevil | +1.888 |
vez | +1.793 |
rams | +1.736 |
emies | +1.674 |
subp | +1.629 |
Neg logit contributions | |
Sigma | -2.066 |
alist | -1.699 |
Lange | -1.698 |
Cantor | -1.633 |
sonian | -1.607 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aredevil | +0.978 |
vez | +0.921 |
rams | +0.888 |
emies | +0.854 |
subp | +0.826 |
Neg logit contributions | |
Sigma | -1.316 |
alist | -1.104 |
Lange | -1.104 |
Cantor | -1.066 |
sonian | -1.054 |
Token | clutch |
Token ID | 22756 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
aredevil | +0.362 |
vez | +0.345 |
rams | +0.334 |
emies | +0.324 |
subp | +0.315 |
Neg logit contributions | |
Sigma | -0.335 |
Lange | -0.270 |
alist | -0.270 |
Cantor | -0.259 |
sonian | -0.254 |
Token | - |
Token ID | 12 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
Sigma | +4.002 |
Lange | +3.147 |
alist | +3.113 |
chamber | +3.054 |
Sachs | +3.041 |
Neg logit contributions | |
aredevil | -4.428 |
vez | -4.255 |
rams | -4.040 |
emies | -3.896 |
irez | -3.836 |
Token | driven |
Token ID | 15808 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Sigma | +0.251 |
alist | +0.204 |
Lange | +0.203 |
Cantor | +0.195 |
sonian | +0.191 |
Neg logit contributions | |
aredevil | -0.259 |
vez | -0.247 |
rams | -0.238 |
emies | -0.231 |
subp | -0.225 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Sigma | +0.596 |
Lange | +0.481 |
alist | +0.480 |
Cantor | +0.460 |
Sachs | +0.454 |
Neg logit contributions | |
aredevil | -0.611 |
vez | -0.582 |
rams | -0.560 |
emies | -0.545 |
subp | -0.528 |
Token | on |
Token ID | 319 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aredevil | +0.043 |
vez | +0.041 |
rams | +0.040 |
emies | +0.039 |
subp | +0.038 |
Neg logit contributions | |
Sigma | -0.037 |
alist | -0.030 |
Lange | -0.030 |
Cantor | -0.028 |
sonian | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
aredevil | +0.354 |
vez | +0.334 |
rams | +0.320 |
emies | +0.308 |
subp | +0.297 |
Neg logit contributions | |
Sigma | -0.495 |
Lange | -0.416 |
alist | -0.416 |
Cantor | -0.402 |
sonian | -0.396 |
Token | demand |
Token ID | 28550 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
aredevil | +0.696 |
vez | +0.660 |
rams | +0.635 |
emies | +0.612 |
subp | +0.591 |
Neg logit contributions | |
Sigma | -0.871 |
Lange | -0.724 |
alist | -0.723 |
Cantor | -0.699 |
sonian | -0.687 |
Token | all |
Token ID | 477 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
aredevil | +1.126 |
vez | +1.074 |
rams | +1.039 |
emies | +1.008 |
subp | +0.980 |
Neg logit contributions | |
Sigma | -1.045 |
Lange | -0.841 |
alist | -0.841 |
Cantor | -0.805 |
sonian | -0.789 |
Token | the |
Token ID | 262 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
aredevil | +1.475 |
vez | +1.410 |
rams | +1.365 |
emies | +1.324 |
subp | +1.290 |
Neg logit contributions | |
Sigma | -1.294 |
Lange | -1.034 |
alist | -1.034 |
Cantor | -0.989 |
sonian | -0.970 |
Token | And |
Token ID | 843 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
aredevil | +1.337 |
vez | +1.279 |
rams | +1.238 |
emies | +1.201 |
subp | +1.173 |
Neg logit contributions | |
Sigma | -1.180 |
alist | -0.951 |
Lange | -0.944 |
Cantor | -0.905 |
sonian | -0.891 |
Token | omin |
Token ID | 6351 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Sigma | +0.488 |
alist | +0.370 |
Lange | +0.368 |
Cantor | +0.341 |
chamber | +0.334 |
Neg logit contributions | |
aredevil | -0.817 |
vez | -0.786 |
rams | -0.761 |
emies | -0.746 |
subp | -0.732 |
Token | ous |
Token ID | 516 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Sigma | +1.310 |
alist | +1.065 |
Lange | +1.065 |
Cantor | +1.012 |
chamber | +1.004 |
Neg logit contributions | |
aredevil | -1.342 |
vez | -1.274 |
rams | -1.232 |
emies | -1.186 |
subp | -1.168 |
Token | rex |
Token ID | 21510 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
Sigma | +0.831 |
Lange | +0.673 |
alist | +0.669 |
Cantor | +0.644 |
chamber | +0.632 |
Neg logit contributions | |
aredevil | -0.854 |
vez | -0.812 |
rams | -0.787 |
emies | -0.763 |
subp | -0.741 |
Token | s |
Token ID | 82 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Sigma | +1.722 |
Lange | +1.390 |
alist | +1.390 |
Cantor | +1.326 |
chamber | +1.320 |
Neg logit contributions | |
aredevil | -1.827 |
vez | -1.731 |
rams | -1.667 |
emies | -1.618 |
subp | -1.580 |
Token | path |
Token ID | 3108 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Sigma | +0.168 |
Lange | +0.135 |
alist | +0.135 |
Cantor | +0.129 |
chamber | +0.127 |
Neg logit contributions | |
aredevil | -0.184 |
vez | -0.175 |
rams | -0.169 |
emies | -0.164 |
subp | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aredevil | +0.392 |
vez | +0.374 |
rams | +0.361 |
emies | +0.349 |
subp | +0.340 |
Neg logit contributions | |
Sigma | -0.383 |
alist | -0.311 |
Lange | -0.310 |
Cantor | -0.298 |
sonian | -0.292 |
Token | Seriously |
Token ID | 27777 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
Sigma | +0.366 |
Lange | +0.297 |
alist | +0.294 |
Cantor | +0.285 |
Sachs | +0.280 |
Neg logit contributions | |
aredevil | -0.352 |
vez | -0.334 |
rams | -0.324 |
emies | -0.313 |
subp | -0.304 |
Token | , |
Token ID | 11 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Sigma | +0.265 |
Lange | +0.214 |
alist | +0.212 |
Cantor | +0.205 |
Sachs | +0.201 |
Neg logit contributions | |
aredevil | -0.274 |
vez | -0.261 |
rams | -0.253 |
emies | -0.245 |
subp | -0.238 |
Token | the |
Token ID | 262 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
aredevil | +1.061 |
vez | +1.012 |
rams | +0.978 |
emies | +0.946 |
subp | +0.921 |
Neg logit contributions | |
Sigma | -1.046 |
alist | -0.851 |
Lange | -0.849 |
Cantor | -0.815 |
sonian | -0.802 |
Token | Soccer |
Token ID | 15872 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
aredevil | +1.391 |
vez | +1.318 |
rams | +1.262 |
emies | +1.217 |
subp | +1.184 |
Neg logit contributions | |
Sigma | -1.794 |
alist | -1.506 |
Lange | -1.497 |
Cantor | -1.448 |
sonian | -1.447 |
Token | until |
Token ID | 1566 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
aredevil | +0.155 |
vez | +0.148 |
rams | +0.143 |
emies | +0.138 |
subp | +0.135 |
Neg logit contributions | |
Sigma | -0.147 |
alist | -0.119 |
Lange | -0.119 |
Cantor | -0.114 |
sonian | -0.112 |
Token | 35 |
Token ID | 3439 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Sigma | +1.328 |
Lange | +1.049 |
alist | +1.038 |
Cantor | +1.006 |
Sachs | +0.982 |
Neg logit contributions | |
aredevil | -1.612 |
vez | -1.532 |
rams | -1.490 |
emies | -1.446 |
irez | -1.406 |
Token | , |
Token ID | 11 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
aredevil | +1.190 |
vez | +1.122 |
rams | +1.081 |
emies | +1.038 |
subp | +1.002 |
Neg logit contributions | |
Sigma | -1.656 |
Lange | -1.393 |
alist | -1.393 |
Cantor | -1.346 |
sonian | -1.330 |
Token | an |
Token ID | 281 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
aredevil | +1.019 |
vez | +0.974 |
rams | +0.942 |
emies | +0.912 |
subp | +0.887 |
Neg logit contributions | |
Sigma | -0.953 |
alist | -0.769 |
Lange | -0.768 |
Cantor | -0.736 |
sonian | -0.724 |
Token | age |
Token ID | 2479 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Sigma | +0.567 |
Lange | +0.455 |
alist | +0.455 |
Cantor | +0.436 |
sonian | +0.428 |
Neg logit contributions | |
aredevil | -0.620 |
vez | -0.592 |
rams | -0.572 |
emies | -0.555 |
subp | -0.540 |
Token | that |
Token ID | 326 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Sigma | +0.471 |
Lange | +0.377 |
alist | +0.376 |
Cantor | +0.359 |
chamber | +0.352 |
Neg logit contributions | |
aredevil | -0.537 |
vez | -0.512 |
rams | -0.497 |
emies | -0.482 |
subp | -0.470 |
Token | usually |
Token ID | 3221 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Sigma | +1.150 |
Lange | +0.932 |
alist | +0.927 |
Cantor | +0.892 |
Sachs | +0.875 |
Neg logit contributions | |
aredevil | -1.193 |
vez | -1.136 |
rams | -1.099 |
emies | -1.066 |
subp | -1.034 |
Token | signals |
Token ID | 10425 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Sigma | +0.902 |
Lange | +0.744 |
alist | +0.742 |
Cantor | +0.713 |
chamber | +0.704 |
Neg logit contributions | |
aredevil | -0.822 |
vez | -0.779 |
rams | -0.752 |
emies | -0.729 |
subp | -0.703 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
aredevil | +1.717 |
vez | +1.643 |
rams | +1.587 |
emies | +1.542 |
subp | +1.514 |
Neg logit contributions | |
Sigma | -1.550 |
alist | -1.251 |
Lange | -1.241 |
Cantor | -1.190 |
sonian | -1.179 |
Token | end |
Token ID | 886 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
aredevil | +0.735 |
vez | +0.701 |
rams | +0.678 |
emies | +0.656 |
subp | +0.638 |
Neg logit contributions | |
Sigma | -0.719 |
alist | -0.583 |
Lange | -0.583 |
Cantor | -0.559 |
sonian | -0.549 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Sigma | +0.287 |
Lange | +0.231 |
alist | +0.231 |
Cantor | +0.221 |
chamber | +0.217 |
Neg logit contributions | |
aredevil | -0.305 |
vez | -0.290 |
rams | -0.281 |
emies | -0.272 |
subp | -0.264 |
Token | Add |
Token ID | 3060 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
aredevil | +0.912 |
vez | +0.871 |
rams | +0.841 |
emies | +0.815 |
subp | +0.789 |
Neg logit contributions | |
Sigma | -0.954 |
alist | -0.785 |
Lange | -0.779 |
Cantor | -0.748 |
sonian | -0.740 |
Token | into |
Token ID | 656 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Sigma | +0.516 |
alist | +0.413 |
Lange | +0.413 |
Cantor | +0.394 |
Sachs | +0.387 |
Neg logit contributions | |
aredevil | -0.579 |
vez | -0.552 |
rams | -0.533 |
emies | -0.518 |
subp | -0.503 |
Token | that |
Token ID | 326 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
Sigma | +0.568 |
Lange | +0.454 |
alist | +0.453 |
Cantor | +0.435 |
Sachs | +0.425 |
Neg logit contributions | |
aredevil | -0.641 |
vez | -0.610 |
rams | -0.592 |
emies | -0.573 |
irez | -0.556 |
Token | some |
Token ID | 617 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Sigma | +0.215 |
Lange | +0.171 |
alist | +0.171 |
Cantor | +0.164 |
sonian | +0.161 |
Neg logit contributions | |
aredevil | -0.246 |
vez | -0.235 |
rams | -0.228 |
emies | -0.221 |
subp | -0.215 |
Token | of |
Token ID | 286 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
aredevil | +1.118 |
vez | +1.065 |
rams | +1.028 |
emies | +0.994 |
subp | +0.966 |
Neg logit contributions | |
Sigma | -1.178 |
alist | -0.963 |
Lange | -0.963 |
Cantor | -0.925 |
sonian | -0.911 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
aredevil | +0.895 |
vez | +0.859 |
rams | +0.830 |
emies | +0.808 |
subp | +0.787 |
Neg logit contributions | |
Sigma | -0.767 |
alist | -0.614 |
Lange | -0.610 |
Cantor | -0.585 |
sonian | -0.575 |
Token | most |
Token ID | 749 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
Sigma | +0.074 |
Lange | +0.060 |
alist | +0.060 |
Cantor | +0.057 |
sonian | +0.056 |
Neg logit contributions | |
aredevil | -0.077 |
vez | -0.073 |
rams | -0.071 |
emies | -0.068 |
subp | -0.066 |
Token | l |
Token ID | 300 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
aredevil | +0.223 |
vez | +0.212 |
rams | +0.204 |
emies | +0.198 |
subp | +0.191 |
Neg logit contributions | |
Sigma | -0.242 |
Lange | -0.199 |
alist | -0.198 |
Cantor | -0.191 |
chamber | -0.187 |
Token | us |
Token ID | 385 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
aredevil | +0.836 |
vez | +0.779 |
rams | +0.739 |
emies | +0.703 |
subp | +0.668 |
Neg logit contributions | |
Sigma | -1.572 |
Lange | -1.346 |
alist | -1.342 |
Cantor | -1.306 |
sonian | -1.291 |
Token | cious |
Token ID | 4680 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Sigma | +0.195 |
alist | +0.168 |
Lange | +0.167 |
Cantor | +0.162 |
chamber | +0.161 |
Neg logit contributions | |
aredevil | -0.100 |
vez | -0.091 |
rams | -0.086 |
emies | -0.082 |
subp | -0.079 |
Token | as |
Token ID | 355 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
aredevil | +0.666 |
vez | +0.634 |
rams | +0.612 |
emies | +0.593 |
subp | +0.576 |
Neg logit contributions | |
Sigma | -0.699 |
alist | -0.574 |
Lange | -0.572 |
Cantor | -0.548 |
sonian | -0.542 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Sigma | +0.295 |
Lange | +0.235 |
alist | +0.233 |
Cantor | +0.225 |
chamber | +0.219 |
Neg logit contributions | |
aredevil | -0.353 |
vez | -0.337 |
rams | -0.327 |
emies | -0.316 |
irez | -0.308 |
Token | Senate |
Token ID | 3845 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
aredevil | +0.532 |
vez | +0.507 |
rams | +0.491 |
emies | +0.475 |
subp | +0.463 |
Neg logit contributions | |
Sigma | -0.499 |
Lange | -0.402 |
alist | -0.402 |
Cantor | -0.385 |
sonian | -0.378 |
Token | confirms |
Token ID | 19623 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
aredevil | +1.254 |
vez | +1.194 |
rams | +1.156 |
emies | +1.117 |
subp | +1.084 |
Neg logit contributions | |
Sigma | -1.240 |
Lange | -1.010 |
alist | -1.002 |
Cantor | -0.967 |
chamber | -0.952 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
aredevil | +2.425 |
vez | +2.318 |
rams | +2.228 |
emies | +2.177 |
subp | +2.115 |
Neg logit contributions | |
Sigma | -2.313 |
alist | -1.879 |
Lange | -1.856 |
sonian | -1.783 |
Cantor | -1.779 |
Token | successor |
Token ID | 17270 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
aredevil | +0.589 |
vez | +0.563 |
rams | +0.547 |
emies | +0.530 |
irez | +0.515 |
Neg logit contributions | |
Sigma | -0.511 |
Lange | -0.409 |
alist | -0.406 |
Cantor | -0.390 |
chamber | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
aredevil | +1.801 |
vez | +1.714 |
rams | +1.649 |
emies | +1.607 |
subp | +1.571 |
Neg logit contributions | |
Sigma | -1.728 |
alist | -1.403 |
Lange | -1.401 |
Cantor | -1.338 |
sonian | -1.327 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Sigma | +0.950 |
Lange | +0.783 |
alist | +0.774 |
Cantor | +0.755 |
Sachs | +0.737 |
Neg logit contributions | |
aredevil | -0.871 |
vez | -0.825 |
rams | -0.797 |
emies | -0.765 |
subp | -0.751 |
Token |
|
Token ID | 198 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Sigma | +1.047 |
alist | +0.860 |
Lange | +0.860 |
Cantor | +0.829 |
sonian | +0.815 |
Neg logit contributions | |
aredevil | -0.934 |
vez | -0.885 |
rams | -0.853 |
emies | -0.823 |
subp | -0.801 |
Token | H |
Token ID | 39 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Sigma | +1.087 |
alist | +0.873 |
Lange | +0.869 |
Cantor | +0.831 |
sonian | +0.816 |
Neg logit contributions | |
aredevil | -1.295 |
vez | -1.226 |
rams | -1.190 |
emies | -1.149 |
subp | -1.142 |
Token | ag |
Token ID | 363 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
aredevil | +0.417 |
vez | +0.393 |
rams | +0.376 |
emies | +0.361 |
subp | +0.351 |
Neg logit contributions | |
Sigma | -0.597 |
alist | -0.504 |
Lange | -0.502 |
Cantor | -0.486 |
sonian | -0.479 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
aredevil | +0.206 |
vez | +0.196 |
rams | +0.189 |
emies | +0.182 |
subp | +0.176 |
Neg logit contributions | |
Sigma | -0.245 |
Lange | -0.203 |
alist | -0.203 |
Cantor | -0.195 |
sonian | -0.193 |
Token | Similarly |
Token ID | 28039 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
Sigma | +0.046 |
alist | +0.038 |
Lange | +0.037 |
Cantor | +0.036 |
sonian | +0.035 |
Neg logit contributions | |
aredevil | -0.049 |
vez | -0.047 |
rams | -0.046 |
emies | -0.044 |
subp | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
aredevil | +1.536 |
vez | +1.463 |
rams | +1.409 |
emies | +1.371 |
subp | +1.330 |
Neg logit contributions | |
Sigma | -1.566 |
Lange | -1.283 |
alist | -1.280 |
Cantor | -1.225 |
sonian | -1.217 |
Token | Australia |
Token ID | 4505 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
aredevil | +0.561 |
vez | +0.535 |
rams | +0.519 |
emies | +0.503 |
subp | +0.489 |
Neg logit contributions | |
Sigma | -0.500 |
Lange | -0.400 |
alist | -0.400 |
Cantor | -0.383 |
sonian | -0.375 |
Token | could |
Token ID | 714 |
Feature activation | +4.83e-03 |
Pos logit contributions | |
aredevil | +1.143 |
vez | +1.091 |
rams | +1.059 |
emies | +1.024 |
subp | +0.998 |
Neg logit contributions | |
Sigma | -1.010 |
alist | -0.808 |
Lange | -0.808 |
Cantor | -0.773 |
sonian | -0.758 |
Token | also |
Token ID | 635 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Sigma | +0.015 |
alist | +0.012 |
Lange | +0.012 |
Cantor | +0.012 |
chamber | +0.012 |
Neg logit contributions | |
aredevil | -0.016 |
vez | -0.015 |
rams | -0.015 |
emies | -0.014 |
subp | -0.014 |
Token | still |
Token ID | 991 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
aredevil | +0.822 |
vez | +0.784 |
rams | +0.758 |
emies | +0.735 |
subp | +0.716 |
Neg logit contributions | |
Sigma | -0.808 |
Lange | -0.657 |
alist | -0.655 |
Cantor | -0.629 |
sonian | -0.621 |
Token | lose |
Token ID | 4425 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
aredevil | +0.155 |
vez | +0.148 |
rams | +0.143 |
emies | +0.138 |
subp | +0.134 |
Neg logit contributions | |
Sigma | -0.153 |
alist | -0.124 |
Lange | -0.124 |
Cantor | -0.119 |
sonian | -0.116 |
Token | out |
Token ID | 503 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
aredevil | +0.504 |
vez | +0.481 |
rams | +0.466 |
emies | +0.451 |
subp | +0.440 |
Neg logit contributions | |
Sigma | -0.463 |
alist | -0.373 |
Lange | -0.372 |
Cantor | -0.356 |
sonian | -0.350 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
aredevil | +0.208 |
vez | +0.198 |
rams | +0.191 |
emies | +0.185 |
subp | +0.180 |
Neg logit contributions | |
Sigma | -0.194 |
alist | -0.156 |
Lange | -0.156 |
Cantor | -0.150 |
chamber | -0.147 |
Token | The |
Token ID | 383 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
aredevil | +0.962 |
vez | +0.918 |
rams | +0.887 |
emies | +0.860 |
subp | +0.837 |
Neg logit contributions | |
Sigma | -0.904 |
alist | -0.730 |
Lange | -0.729 |
Cantor | -0.698 |
sonian | -0.687 |
Token | whom |
Token ID | 4150 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Sigma | +0.231 |
alist | +0.184 |
Lange | +0.184 |
Cantor | +0.176 |
Sachs | +0.172 |
Neg logit contributions | |
aredevil | -0.269 |
vez | -0.257 |
rams | -0.249 |
emies | -0.241 |
subp | -0.234 |
Token | have |
Token ID | 423 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Sigma | +0.569 |
Lange | +0.457 |
alist | +0.453 |
Cantor | +0.438 |
chamber | +0.429 |
Neg logit contributions | |
aredevil | -0.622 |
vez | -0.591 |
rams | -0.576 |
emies | -0.555 |
subp | -0.539 |
Token | moved |
Token ID | 3888 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Sigma | +0.708 |
Lange | +0.575 |
alist | +0.570 |
Cantor | +0.552 |
chamber | +0.541 |
Neg logit contributions | |
aredevil | -0.704 |
vez | -0.663 |
rams | -0.644 |
emies | -0.621 |
irez | -0.603 |
Token | with |
Token ID | 351 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
aredevil | +2.415 |
vez | +2.322 |
rams | +2.246 |
emies | +2.179 |
subp | +2.137 |
Neg logit contributions | |
Sigma | -2.302 |
alist | -1.870 |
Lange | -1.867 |
sonian | -1.784 |
Cantor | -1.782 |
Token | local |
Token ID | 1957 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
aredevil | +2.042 |
vez | +1.953 |
rams | +1.890 |
emies | +1.831 |
subp | +1.783 |
Neg logit contributions | |
Sigma | -1.855 |
Lange | -1.490 |
alist | -1.489 |
Cantor | -1.425 |
sonian | -1.402 |
Token | forces |
Token ID | 3386 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
aredevil | +0.849 |
vez | +0.807 |
rams | +0.781 |
emies | +0.754 |
subp | +0.731 |
Neg logit contributions | |
Sigma | -0.882 |
Lange | -0.719 |
alist | -0.718 |
Cantor | -0.690 |
chamber | -0.677 |
Token | within |
Token ID | 1626 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
aredevil | +0.758 |
vez | +0.723 |
rams | +0.699 |
emies | +0.677 |
subp | +0.659 |
Neg logit contributions | |
Sigma | -0.720 |
Lange | -0.582 |
alist | -0.582 |
Cantor | -0.557 |
sonian | -0.548 |
Token | 20 |
Token ID | 1160 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
aredevil | +2.299 |
vez | +2.216 |
rams | +2.133 |
emies | +2.064 |
subp | +2.016 |
Neg logit contributions | |
Sigma | -2.270 |
alist | -1.844 |
Lange | -1.844 |
sonian | -1.761 |
Cantor | -1.761 |
Token | miles |
Token ID | 4608 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
aredevil | +1.452 |
vez | +1.369 |
rams | +1.308 |
emies | +1.253 |
subp | +1.209 |
Neg logit contributions | |
Sigma | -2.255 |
Lange | -1.910 |
alist | -1.909 |
Cantor | -1.847 |
sonian | -1.825 |
Token | of |
Token ID | 286 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
aredevil | +1.777 |
vez | +1.693 |
rams | +1.634 |
emies | +1.574 |
subp | +1.527 |
Neg logit contributions | |
Sigma | -2.065 |
Lange | -1.707 |
alist | -1.704 |
Cantor | -1.640 |
sonian | -1.619 |
Token | the |
Token ID | 262 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
aredevil | +1.169 |
vez | +1.126 |
rams | +1.092 |
emies | +1.061 |
subp | +1.033 |
Neg logit contributions | |
Sigma | -0.920 |
alist | -0.724 |
Lange | -0.723 |
Cantor | -0.688 |
sonian | -0.683 |
Token | m |
Token ID | 285 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Sigma | +0.509 |
Lange | +0.422 |
alist | +0.422 |
Cantor | +0.404 |
chamber | +0.398 |
Neg logit contributions | |
aredevil | -0.443 |
vez | -0.419 |
rams | -0.406 |
emies | -0.391 |
subp | -0.378 |
Token | over |
Token ID | 2502 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
aredevil | +0.465 |
vez | +0.442 |
rams | +0.426 |
emies | +0.410 |
subp | +0.399 |
Neg logit contributions | |
Sigma | -0.524 |
alist | -0.433 |
Lange | -0.432 |
Cantor | -0.415 |
sonian | -0.409 |
Token | named |
Token ID | 3706 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
Sigma | +1.695 |
alist | +1.362 |
Lange | +1.348 |
Cantor | +1.295 |
chamber | +1.272 |
Neg logit contributions | |
aredevil | -1.922 |
vez | -1.833 |
rams | -1.773 |
emies | -1.708 |
subp | -1.659 |
Token | Dim |
Token ID | 14048 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Sigma | +2.394 |
Lange | +1.946 |
alist | +1.897 |
Cantor | +1.860 |
Sachs | +1.808 |
Neg logit contributions | |
aredevil | -2.566 |
vez | -2.419 |
rams | -2.364 |
emies | -2.279 |
subp | -2.233 |
Token | itri |
Token ID | 49510 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
Sigma | +0.646 |
Lange | +0.535 |
alist | +0.533 |
Cantor | +0.513 |
sonian | +0.505 |
Neg logit contributions | |
aredevil | -0.563 |
vez | -0.533 |
rams | -0.515 |
emies | -0.498 |
subp | -0.484 |
Token | to |
Token ID | 284 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
aredevil | +2.556 |
vez | +2.452 |
rams | +2.371 |
emies | +2.305 |
subp | +2.218 |
Neg logit contributions | |
Sigma | -2.410 |
alist | -1.957 |
Lange | -1.936 |
Cantor | -1.863 |
sonian | -1.862 |
Token | a |
Token ID | 257 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
aredevil | +1.887 |
vez | +1.805 |
rams | +1.754 |
emies | +1.698 |
subp | +1.661 |
Neg logit contributions | |
Sigma | -1.644 |
alist | -1.316 |
Lange | -1.311 |
Cantor | -1.258 |
sonian | -1.248 |
Token | r |
Token ID | 374 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
aredevil | +1.209 |
vez | +1.154 |
rams | +1.115 |
emies | +1.081 |
subp | +1.054 |
Neg logit contributions | |
Sigma | -1.141 |
alist | -0.923 |
Lange | -0.920 |
Cantor | -0.883 |
sonian | -0.871 |
Token | omp |
Token ID | 3361 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
aredevil | +0.580 |
vez | +0.546 |
rams | +0.524 |
emies | +0.504 |
subp | +0.487 |
Neg logit contributions | |
Sigma | -0.821 |
alist | -0.692 |
Lange | -0.690 |
Cantor | -0.667 |
sonian | -0.658 |
Token | through |
Token ID | 832 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
Sigma | +1.043 |
alist | +0.851 |
Lange | +0.826 |
Cantor | +0.789 |
chamber | +0.788 |
Neg logit contributions | |
aredevil | -1.300 |
vez | -1.250 |
rams | -1.200 |
emies | -1.167 |
subp | -1.134 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
aredevil | +0.192 |
vez | +0.183 |
rams | +0.178 |
emies | +0.172 |
subp | +0.168 |
Neg logit contributions | |
Sigma | -0.165 |
Lange | -0.131 |
alist | -0.131 |
Cantor | -0.125 |
sonian | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
aredevil | +0.041 |
vez | +0.039 |
rams | +0.038 |
emies | +0.037 |
subp | +0.036 |
Neg logit contributions | |
Sigma | -0.040 |
Lange | -0.032 |
alist | -0.032 |
Cantor | -0.031 |
chamber | -0.030 |
Token | employment |
Token ID | 7184 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Sigma | +0.302 |
Lange | +0.244 |
alist | +0.244 |
Cantor | +0.234 |
sonian | +0.229 |
Neg logit contributions | |
aredevil | -0.321 |
vez | -0.306 |
rams | -0.296 |
emies | -0.287 |
subp | -0.279 |
Token | paperwork |
Token ID | 23143 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
aredevil | +1.322 |
vez | +1.258 |
rams | +1.213 |
emies | +1.172 |
subp | +1.139 |
Neg logit contributions | |
Sigma | -1.435 |
alist | -1.176 |
Lange | -1.176 |
Cantor | -1.130 |
sonian | -1.114 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
aredevil | +1.510 |
vez | +1.439 |
rams | +1.391 |
emies | +1.346 |
subp | +1.310 |
Neg logit contributions | |
Sigma | -1.502 |
Lange | -1.220 |
alist | -1.220 |
Cantor | -1.170 |
sonian | -1.152 |
Token | or |
Token ID | 393 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Sigma | +0.498 |
Lange | +0.398 |
alist | +0.398 |
Cantor | +0.382 |
chamber | +0.376 |
Neg logit contributions | |
aredevil | -0.567 |
vez | -0.540 |
rams | -0.524 |
emies | -0.508 |
irez | -0.495 |
Token | evidence |
Token ID | 2370 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
aredevil | +0.720 |
vez | +0.689 |
rams | +0.666 |
emies | +0.646 |
subp | +0.630 |
Neg logit contributions | |
Sigma | -0.653 |
alist | -0.524 |
Lange | -0.524 |
Cantor | -0.501 |
sonian | -0.493 |
Token | of |
Token ID | 286 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
aredevil | +3.725 |
vez | +3.532 |
rams | +3.417 |
emies | +3.271 |
subp | +3.223 |
Neg logit contributions | |
Sigma | -4.734 |
alist | -3.956 |
Lange | -3.942 |
Cantor | -3.803 |
sonian | -3.789 |
Token | appointments |
Token ID | 23976 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
aredevil | +2.487 |
vez | +2.397 |
rams | +2.307 |
emies | +2.250 |
subp | +2.208 |
Neg logit contributions | |
Sigma | -2.244 |
alist | -1.808 |
Lange | -1.799 |
sonian | -1.714 |
Cantor | -1.714 |
Token | for |
Token ID | 329 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Sigma | +0.045 |
Lange | +0.036 |
alist | +0.036 |
Cantor | +0.035 |
chamber | +0.034 |
Neg logit contributions | |
aredevil | -0.050 |
vez | -0.047 |
rams | -0.046 |
emies | -0.044 |
subp | -0.043 |
Token | those |
Token ID | 883 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
Sigma | +0.073 |
Lange | +0.058 |
alist | +0.058 |
Cantor | +0.055 |
chamber | +0.054 |
Neg logit contributions | |
aredevil | -0.083 |
vez | -0.079 |
rams | -0.077 |
emies | -0.074 |
subp | -0.072 |
Token | who |
Token ID | 508 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
Sigma | +0.227 |
Lange | +0.183 |
alist | +0.183 |
Cantor | +0.177 |
chamber | +0.175 |
Neg logit contributions | |
aredevil | -0.230 |
vez | -0.218 |
rams | -0.211 |
emies | -0.203 |
irez | -0.198 |
Token | co |
Token ID | 1073 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
aredevil | +0.081 |
vez | +0.077 |
rams | +0.075 |
emies | +0.072 |
subp | +0.070 |
Neg logit contributions | |
Sigma | -0.083 |
Lange | -0.068 |
alist | -0.068 |
Cantor | -0.065 |
sonian | -0.063 |
Token | / |
Token ID | 14 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Sigma | +0.716 |
alist | +0.588 |
Lange | +0.588 |
Cantor | +0.565 |
sonian | +0.556 |
Neg logit contributions | |
aredevil | -0.661 |
vez | -0.625 |
rams | -0.604 |
emies | -0.584 |
subp | -0.569 |
Token | P |
Token ID | 47 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
aredevil | +0.587 |
vez | +0.556 |
rams | +0.536 |
emies | +0.519 |
subp | +0.504 |
Neg logit contributions | |
Sigma | -0.665 |
alist | -0.548 |
Lange | -0.547 |
Cantor | -0.526 |
sonian | -0.519 |
Token | 9 |
Token ID | 24 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
aredevil | +2.442 |
vez | +2.332 |
rams | +2.244 |
emies | +2.159 |
irez | +2.083 |
Neg logit contributions | |
Sigma | -2.842 |
Lange | -2.349 |
alist | -2.336 |
Cantor | -2.264 |
sonian | -2.218 |
Token | gc |
Token ID | 36484 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
aredevil | +0.125 |
vez | +0.118 |
rams | +0.114 |
emies | +0.110 |
subp | +0.107 |
Neg logit contributions | |
Sigma | -0.142 |
alist | -0.117 |
Lange | -0.117 |
Cantor | -0.112 |
sonian | -0.111 |
Token | N |
Token ID | 45 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
aredevil | +1.015 |
vez | +0.962 |
rams | +0.927 |
emies | +0.895 |
subp | +0.868 |
Neg logit contributions | |
Sigma | -1.192 |
alist | -0.985 |
Lange | -0.985 |
Cantor | -0.948 |
sonian | -0.934 |
Token | PA |
Token ID | 4537 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
aredevil | +4.148 |
vez | +4.016 |
rams | +3.856 |
emies | +3.690 |
irez | +3.560 |
Neg logit contributions | |
Sigma | -4.797 |
Lange | -3.967 |
alist | -3.884 |
Cantor | -3.832 |
chamber | -3.755 |
Token | um |
Token ID | 388 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
aredevil | +3.165 |
vez | +3.052 |
rams | +2.929 |
emies | +2.807 |
irez | +2.716 |
Neg logit contributions | |
Sigma | -3.646 |
Lange | -3.012 |
alist | -2.967 |
Cantor | -2.907 |
chamber | -2.845 |
Token | H |
Token ID | 39 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
aredevil | +1.912 |
vez | +1.824 |
rams | +1.754 |
emies | +1.688 |
subp | +1.633 |
Neg logit contributions | |
Sigma | -2.227 |
Lange | -1.838 |
alist | -1.834 |
Cantor | -1.773 |
sonian | -1.740 |
Token | — |
Token ID | 851 |
Feature activation | -8.05e-04 |
Pos logit contributions | |
aredevil | +3.657 |
vez | +3.477 |
rams | +3.368 |
emies | +3.216 |
subp | +3.116 |
Neg logit contributions | |
Sigma | -4.395 |
alist | -3.645 |
Lange | -3.637 |
Cantor | -3.512 |
sonian | -3.473 |
Token | ACLU |
Token ID | 24381 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
aredevil | +0.003 |
vez | +0.003 |
rams | +0.002 |
emies | +0.002 |
subp | +0.002 |
Neg logit contributions | |
Sigma | -0.003 |
Lange | -0.002 |
alist | -0.002 |
Cantor | -0.002 |
Sachs | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
aredevil | +1.440 |
vez | +1.369 |
rams | +1.312 |
emies | +1.264 |
subp | +1.227 |
Neg logit contributions | |
Sigma | -1.826 |
alist | -1.524 |
Lange | -1.519 |
Cantor | -1.466 |
sonian | -1.448 |
Token | to |
Token ID | 284 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
aredevil | +2.101 |
vez | +2.007 |
rams | +1.938 |
emies | +1.882 |
subp | +1.833 |
Neg logit contributions | |
Sigma | -2.019 |
alist | -1.642 |
Lange | -1.629 |
Cantor | -1.562 |
sonian | -1.549 |
Token | do |
Token ID | 466 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
aredevil | +0.803 |
vez | +0.769 |
rams | +0.746 |
emies | +0.724 |
subp | +0.706 |
Neg logit contributions | |
Sigma | -0.650 |
Lange | -0.514 |
alist | -0.514 |
Cantor | -0.490 |
sonian | -0.480 |
Token | ? |
Token ID | 30 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
aredevil | +1.555 |
vez | +1.479 |
rams | +1.419 |
emies | +1.370 |
subp | +1.330 |
Neg logit contributions | |
Sigma | -1.881 |
alist | -1.561 |
Lange | -1.556 |
Cantor | -1.499 |
sonian | -1.483 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
aredevil | +2.399 |
vez | +2.275 |
rams | +2.187 |
emies | +2.117 |
subp | +2.015 |
Neg logit contributions | |
Sigma | -3.017 |
alist | -2.545 |
Lange | -2.502 |
sonian | -2.428 |
Cantor | -2.402 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
aredevil | +3.767 |
vez | +3.657 |
rams | +3.497 |
emies | +3.419 |
atti | +3.205 |
Neg logit contributions | |
Sigma | -6.088 |
princ | -5.366 |
Lange | -5.228 |
alist | -5.212 |
sonian | -4.993 |
Token | I |
Token ID | 40 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
aredevil | +4.020 |
vez | +3.841 |
rams | +3.676 |
emies | +3.546 |
irez | +3.360 |
Neg logit contributions | |
Sigma | -5.545 |
Lange | -4.659 |
alist | -4.628 |
Cantor | -4.489 |
sonian | -4.442 |
Token | was |
Token ID | 373 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
aredevil | +2.417 |
vez | +2.311 |
rams | +2.224 |
emies | +2.157 |
subp | +2.088 |
Neg logit contributions | |
Sigma | -2.451 |
alist | -1.993 |
Lange | -1.992 |
Cantor | -1.913 |
sonian | -1.879 |
Token | definitely |
Token ID | 4753 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
aredevil | +2.110 |
vez | +2.008 |
rams | +1.935 |
emies | +1.872 |
subp | +1.818 |
Neg logit contributions | |
Sigma | -2.274 |
alist | -1.864 |
Lange | -1.863 |
Cantor | -1.791 |
sonian | -1.763 |
Token | satisfied |
Token ID | 11378 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
aredevil | +2.369 |
vez | +2.266 |
rams | +2.187 |
emies | +2.125 |
subp | +2.071 |
Neg logit contributions | |
Sigma | -2.127 |
alist | -1.708 |
Lange | -1.705 |
Cantor | -1.630 |
sonian | -1.606 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
aredevil | +1.562 |
vez | +1.493 |
rams | +1.443 |
emies | +1.399 |
subp | +1.361 |
Neg logit contributions | |
Sigma | -1.442 |
alist | -1.161 |
Lange | -1.160 |
Cantor | -1.111 |
sonian | -1.093 |
Token | the |
Token ID | 262 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Sigma | +0.961 |
Lange | +0.761 |
alist | +0.760 |
Cantor | +0.726 |
chamber | +0.711 |
Neg logit contributions | |
aredevil | -1.147 |
vez | -1.092 |
rams | -1.062 |
emies | -1.031 |
subp | -0.999 |
Token | final |
Token ID | 2457 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
aredevil | +0.833 |
vez | +0.797 |
rams | +0.771 |
emies | +0.747 |
subp | +0.729 |
Neg logit contributions | |
Sigma | -0.766 |
alist | -0.616 |
Lange | -0.615 |
Cantor | -0.589 |
sonian | -0.582 |
Token | agreement |
Token ID | 4381 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
Sigma | +0.067 |
Lange | +0.054 |
alist | +0.054 |
Cantor | +0.051 |
chamber | +0.050 |
Neg logit contributions | |
aredevil | -0.076 |
vez | -0.073 |
rams | -0.070 |
emies | -0.068 |
subp | -0.066 |
Token | between |
Token ID | 1022 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Sigma | +0.168 |
alist | +0.137 |
Lange | +0.136 |
Cantor | +0.130 |
chamber | +0.128 |
Neg logit contributions | |
aredevil | -0.181 |
vez | -0.172 |
rams | -0.167 |
emies | -0.162 |
subp | -0.157 |
Token | the |
Token ID | 262 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
aredevil | +0.487 |
vez | +0.467 |
rams | +0.453 |
emies | +0.441 |
subp | +0.430 |
Neg logit contributions | |
Sigma | -0.354 |
Lange | -0.275 |
alist | -0.275 |
Cantor | -0.261 |
sonian | -0.256 |
Token | two |
Token ID | 734 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
aredevil | +1.268 |
vez | +1.209 |
rams | +1.169 |
emies | +1.132 |
subp | +1.101 |
Neg logit contributions | |
Sigma | -1.253 |
Lange | -1.017 |
alist | -1.017 |
Cantor | -0.976 |
sonian | -0.959 |
Token | countries |
Token ID | 2678 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
aredevil | +3.279 |
vez | +3.091 |
rams | +2.975 |
emies | +2.876 |
subp | +2.779 |
Neg logit contributions | |
Sigma | -4.789 |
Lange | -4.060 |
alist | -4.045 |
Cantor | -3.935 |
sonian | -3.855 |
Token | has |
Token ID | 468 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
aredevil | +0.754 |
vez | +0.715 |
rams | +0.694 |
emies | +0.673 |
subp | +0.654 |
Neg logit contributions | |
Sigma | -0.716 |
alist | -0.579 |
Lange | -0.579 |
Cantor | -0.554 |
chamber | -0.545 |
Token | been |
Token ID | 587 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
aredevil | +0.069 |
vez | +0.065 |
rams | +0.064 |
emies | +0.062 |
subp | +0.060 |
Neg logit contributions | |
Sigma | -0.069 |
alist | -0.056 |
Lange | -0.056 |
Cantor | -0.054 |
chamber | -0.053 |
Token | signed |
Token ID | 4488 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
aredevil | +1.445 |
vez | +1.369 |
rams | +1.316 |
emies | +1.268 |
subp | +1.228 |
Neg logit contributions | |
Sigma | -1.801 |
Lange | -1.496 |
alist | -1.496 |
Cantor | -1.443 |
sonian | -1.422 |
Token | , |
Token ID | 11 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Sigma | +0.611 |
alist | +0.493 |
Lange | +0.493 |
Cantor | +0.473 |
sonian | +0.462 |
Neg logit contributions | |
aredevil | -0.648 |
vez | -0.617 |
rams | -0.598 |
emies | -0.579 |
subp | -0.565 |
Token | Donald |
Token ID | 3759 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
aredevil | +0.541 |
vez | +0.517 |
rams | +0.501 |
emies | +0.486 |
subp | +0.473 |
Neg logit contributions | |
Sigma | -0.474 |
Lange | -0.378 |
alist | -0.377 |
Cantor | -0.363 |
chamber | -0.353 |
Token | Trump |
Token ID | 1301 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
aredevil | +1.548 |
vez | +1.475 |
rams | +1.429 |
emies | +1.381 |
subp | +1.339 |
Neg logit contributions | |
Sigma | -1.627 |
alist | -1.334 |
Lange | -1.325 |
Cantor | -1.269 |
chamber | -1.254 |
Token | Donald |
Token ID | 3759 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
aredevil | +1.931 |
vez | +1.844 |
rams | +1.775 |
emies | +1.722 |
subp | +1.672 |
Neg logit contributions | |
Sigma | -2.080 |
Lange | -1.704 |
alist | -1.700 |
Cantor | -1.638 |
sonian | -1.618 |
Token | John |
Token ID | 1757 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
aredevil | +1.715 |
vez | +1.631 |
rams | +1.586 |
emies | +1.533 |
irez | +1.479 |
Neg logit contributions | |
Sigma | -1.920 |
alist | -1.593 |
Lange | -1.575 |
Cantor | -1.518 |
sonian | -1.502 |
Token | Trump |
Token ID | 1301 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
aredevil | +2.569 |
vez | +2.457 |
rams | +2.386 |
emies | +2.317 |
subp | +2.218 |
Neg logit contributions | |
Sigma | -2.798 |
alist | -2.313 |
Lange | -2.301 |
Cantor | -2.210 |
sonian | -2.195 |
Token | House |
Token ID | 18102 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
aredevil | +2.451 |
vez | +2.337 |
rams | +2.263 |
emies | +2.190 |
subp | +2.119 |
Neg logit contributions | |
Sigma | -2.508 |
alist | -2.043 |
Lange | -2.042 |
Cantor | -1.962 |
sonian | -1.931 |
Token | committee |
Token ID | 5583 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
aredevil | +5.571 |
vez | +5.477 |
rams | +5.194 |
emies | +5.193 |
atti | +4.996 |
Neg logit contributions | |
Sigma | -5.781 |
alist | -4.760 |
Lange | -4.659 |
sonian | -4.566 |
Cantor | -4.469 |
Token | believes |
Token ID | 5804 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
aredevil | +1.744 |
vez | +1.641 |
rams | +1.566 |
emies | +1.495 |
irez | +1.450 |
Neg logit contributions | |
Sigma | -2.455 |
Lange | -2.053 |
alist | -2.039 |
Cantor | -1.991 |
chamber | -1.958 |
Token | it |
Token ID | 340 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
aredevil | +3.003 |
vez | +2.832 |
rams | +2.759 |
emies | +2.653 |
subp | +2.609 |
Neg logit contributions | |
Sigma | -3.303 |
alist | -2.751 |
Lange | -2.742 |
sonian | -2.594 |
Sachs | -2.572 |
Token | has |
Token ID | 468 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
aredevil | +1.925 |
vez | +1.850 |
rams | +1.783 |
emies | +1.730 |
irez | +1.692 |
Neg logit contributions | |
Sigma | -1.648 |
Lange | -1.295 |
alist | -1.286 |
Cantor | -1.251 |
chamber | -1.225 |
Token | evidence |
Token ID | 2370 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Sigma | +0.399 |
alist | +0.335 |
Lange | +0.334 |
Cantor | +0.322 |
sonian | +0.319 |
Neg logit contributions | |
aredevil | -0.306 |
vez | -0.289 |
rams | -0.278 |
emies | -0.267 |
subp | -0.259 |