Token | " |
Token ID | 366 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
kids | +0.003 |
idea | +0.003 |
sun | +0.002 |
do | +0.002 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.007 |
Charl | -0.007 |
astically | -0.006 |
Har | -0.006 |
ky | -0.006 |
Token | M |
Token ID | 44 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
otte | +0.006 |
Charl | +0.006 |
la | +0.005 |
Smith | +0.005 |
astically | +0.005 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.003 |
do | -0.003 |
sun | -0.003 |
wind | -0.003 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
idea | +0.022 |
kids | +0.021 |
wind | +0.019 |
do | +0.019 |
sun | +0.019 |
Neg logit contributions | |
otte | -0.030 |
Charl | -0.029 |
Har | -0.029 |
May | -0.028 |
astically | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
kids | +0.056 |
idea | +0.055 |
do | +0.050 |
sun | +0.047 |
wind | +0.047 |
Neg logit contributions | |
Charl | -0.090 |
otte | -0.090 |
Har | -0.087 |
Jessica | -0.084 |
astically | -0.084 |
Token | o |
Token ID | 267 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Charl | +0.029 |
otte | +0.029 |
Har | +0.028 |
May | +0.027 |
ky | +0.027 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.017 |
do | -0.015 |
sun | -0.014 |
wind | -0.014 |
Token | ink |
Token ID | 676 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
idea | +0.041 |
kids | +0.041 |
friends | +0.035 |
sun | +0.035 |
wind | +0.035 |
Neg logit contributions | |
Charl | -0.033 |
otte | -0.032 |
ky | -0.031 |
Har | -0.030 |
astically | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
idea | +0.079 |
kids | +0.077 |
do | +0.068 |
sun | +0.066 |
wind | +0.065 |
Neg logit contributions | |
Charl | -0.129 |
otte | -0.127 |
Har | -0.122 |
May | -0.118 |
astically | -0.118 |
Token | b |
Token ID | 275 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
otte | +0.034 |
Charl | +0.034 |
Har | +0.033 |
astically | +0.032 |
ically | +0.032 |
Neg logit contributions | |
kids | -0.017 |
idea | -0.016 |
do | -0.015 |
sun | -0.014 |
wind | -0.014 |
Token | aa |
Token ID | 7252 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
kids | +0.019 |
idea | +0.018 |
sun | +0.016 |
do | +0.016 |
wind | +0.016 |
Neg logit contributions | |
Charl | -0.032 |
otte | -0.031 |
May | -0.030 |
Jessica | -0.030 |
Har | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
kids | +0.058 |
idea | +0.057 |
do | +0.051 |
wind | +0.047 |
sun | +0.047 |
Neg logit contributions | |
otte | -0.094 |
Charl | -0.093 |
Har | -0.090 |
Jessica | -0.089 |
astically | -0.089 |
Token | cl |
Token ID | 537 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
otte | +0.040 |
Charl | +0.039 |
Har | +0.038 |
Jessica | +0.037 |
astically | +0.037 |
Neg logit contributions | |
kids | -0.019 |
idea | -0.017 |
do | -0.017 |
sun | -0.016 |
wind | -0.015 |
Token | is |
Token ID | 318 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
kids | +0.023 |
idea | +0.023 |
do | +0.019 |
sun | +0.018 |
wind | +0.017 |
Neg logit contributions | |
otte | -0.052 |
Charl | -0.052 |
Har | -0.050 |
ky | -0.049 |
astically | -0.049 |
Token | Ch |
Token ID | 609 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ically | +0.019 |
otte | +0.019 |
Charl | +0.019 |
astically | +0.019 |
Har | +0.018 |
Neg logit contributions | |
kids | -0.010 |
idea | -0.009 |
do | -0.008 |
sun | -0.008 |
friends | -0.008 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.014 |
do | +0.013 |
sun | +0.012 |
wind | +0.012 |
Neg logit contributions | |
Charl | -0.024 |
otte | -0.024 |
Har | -0.023 |
ky | -0.023 |
May | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
idea | +0.084 |
kids | +0.082 |
do | +0.073 |
sun | +0.071 |
wind | +0.069 |
Neg logit contributions | |
Charl | -0.103 |
otte | -0.102 |
Har | -0.097 |
ky | -0.096 |
May | -0.096 |
Token | Ch |
Token ID | 1925 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
kids | +0.048 |
idea | +0.046 |
do | +0.043 |
sun | +0.042 |
wind | +0.041 |
Neg logit contributions | |
otte | -0.045 |
Charl | -0.045 |
astically | -0.044 |
Har | -0.043 |
ically | -0.042 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
idea | +0.013 |
kids | +0.013 |
do | +0.011 |
sun | +0.010 |
wind | +0.010 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.027 |
Har | -0.026 |
ky | -0.025 |
May | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
idea | +0.084 |
kids | +0.084 |
do | +0.074 |
sun | +0.072 |
wind | +0.070 |
Neg logit contributions | |
Charl | -0.105 |
otte | -0.104 |
Har | -0.099 |
May | -0.097 |
astically | -0.097 |
Token | Will |
Token ID | 2561 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
idea | +0.030 |
kids | +0.029 |
do | +0.025 |
sun | +0.024 |
friends | +0.024 |
Neg logit contributions | |
Charl | -0.036 |
otte | -0.035 |
May | -0.034 |
Har | -0.033 |
ky | -0.033 |
Token | you |
Token ID | 345 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
kids | +0.017 |
idea | +0.016 |
do | +0.014 |
sun | +0.013 |
friends | +0.013 |
Neg logit contributions | |
Charl | -0.032 |
otte | -0.031 |
Har | -0.030 |
astically | -0.030 |
May | -0.030 |
Token | be |
Token ID | 307 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
idea | +0.010 |
kids | +0.010 |
do | +0.008 |
sun | +0.008 |
wind | +0.007 |
Neg logit contributions | |
Charl | -0.026 |
otte | -0.026 |
Har | -0.025 |
May | -0.024 |
ky | -0.024 |
Token | my |
Token ID | 616 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
idea | +0.017 |
kids | +0.016 |
do | +0.015 |
sun | +0.014 |
expect | +0.014 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.022 |
Har | -0.022 |
May | -0.022 |
ky | -0.021 |
Token | that |
Token ID | 326 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
kids | +0.018 |
idea | +0.017 |
do | +0.016 |
sun | +0.015 |
of | +0.015 |
Neg logit contributions | |
Charl | -0.048 |
otte | -0.048 |
Har | -0.045 |
den | -0.045 |
Simon | -0.044 |
Token | said |
Token ID | 531 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.016 |
do | +0.013 |
sun | +0.013 |
wind | +0.012 |
Neg logit contributions | |
otte | -0.030 |
Charl | -0.030 |
Har | -0.028 |
ky | -0.028 |
Smith | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
idea | +0.004 |
kids | +0.004 |
do | +0.003 |
sun | +0.003 |
wind | +0.003 |
Neg logit contributions | |
Charl | -0.007 |
otte | -0.007 |
Har | -0.006 |
ky | -0.006 |
May | -0.006 |
Token | Sh |
Token ID | 2484 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.022 |
Har | +0.021 |
Alexa | +0.020 |
May | +0.020 |
Neg logit contributions | |
kids | -0.023 |
idea | -0.022 |
do | -0.021 |
sun | -0.020 |
wind | -0.020 |
Token | r |
Token ID | 81 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
kids | +0.012 |
idea | +0.012 |
do | +0.010 |
sun | +0.010 |
wind | +0.010 |
Neg logit contributions | |
Charl | -0.012 |
otte | -0.012 |
Har | -0.011 |
May | -0.011 |
astically | -0.011 |
Token | ink |
Token ID | 676 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
kids | +0.018 |
idea | +0.017 |
do | +0.016 |
sun | +0.016 |
friends | +0.015 |
Neg logit contributions | |
Charl | -0.020 |
otte | -0.020 |
Har | -0.019 |
May | -0.019 |
Jessica | -0.019 |
Token | Mud |
Token ID | 32878 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
kids | +0.083 |
idea | +0.083 |
do | +0.074 |
sun | +0.073 |
wind | +0.071 |
Neg logit contributions | |
Charl | -0.109 |
otte | -0.108 |
Har | -0.103 |
May | -0.100 |
Jessica | -0.099 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
kids | +0.006 |
idea | +0.006 |
do | +0.005 |
sun | +0.005 |
wind | +0.005 |
Neg logit contributions | |
Charl | -0.009 |
otte | -0.009 |
Har | -0.008 |
Jessica | -0.008 |
May | -0.008 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
idea | +0.004 |
expect | +0.003 |
kids | +0.003 |
promise | +0.003 |
belong | +0.003 |
Neg logit contributions | |
Smith | -0.005 |
astically | -0.004 |
ically | -0.004 |
ky | -0.004 |
any | -0.004 |
Token | did |
Token ID | 750 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
do | +0.001 |
friends | +0.001 |
sun | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.002 |
May | -0.002 |
Jessica | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
kids | +0.039 |
idea | +0.038 |
sun | +0.036 |
wind | +0.036 |
add | +0.035 |
Neg logit contributions | |
otte | -0.026 |
astically | -0.026 |
ically | -0.025 |
May | -0.025 |
neatly | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
Charl | +0.017 |
otte | +0.017 |
May | +0.016 |
Smith | +0.016 |
la | +0.016 |
Neg logit contributions | |
idea | -0.020 |
kids | -0.018 |
oops | -0.017 |
urge | -0.017 |
choices | -0.017 |
Token | my |
Token ID | 616 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
May | +0.017 |
Charl | +0.016 |
Maya | +0.016 |
otte | +0.016 |
la | +0.016 |
Neg logit contributions | |
idea | -0.018 |
oops | -0.016 |
choices | -0.016 |
promises | -0.015 |
urge | -0.014 |
Token | name |
Token ID | 1438 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
idea | +0.017 |
kids | +0.016 |
do | +0.013 |
sun | +0.012 |
wind | +0.012 |
Neg logit contributions | |
Charl | -0.049 |
otte | -0.049 |
Har | -0.047 |
May | -0.047 |
ky | -0.047 |
Token | is |
Token ID | 318 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
kids | +0.023 |
idea | +0.023 |
do | +0.019 |
sun | +0.018 |
wind | +0.017 |
Neg logit contributions | |
otte | -0.052 |
Charl | -0.052 |
Har | -0.050 |
ky | -0.049 |
astically | -0.049 |
Token | Ch |
Token ID | 609 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ically | +0.019 |
otte | +0.019 |
Charl | +0.019 |
astically | +0.019 |
Har | +0.018 |
Neg logit contributions | |
kids | -0.010 |
idea | -0.009 |
do | -0.008 |
sun | -0.008 |
friends | -0.008 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.014 |
do | +0.013 |
sun | +0.012 |
wind | +0.012 |
Neg logit contributions | |
Charl | -0.024 |
otte | -0.024 |
Har | -0.023 |
ky | -0.023 |
May | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
idea | +0.084 |
kids | +0.082 |
do | +0.073 |
sun | +0.071 |
wind | +0.069 |
Neg logit contributions | |
Charl | -0.103 |
otte | -0.102 |
Har | -0.097 |
ky | -0.096 |
May | -0.096 |
Token | Ch |
Token ID | 1925 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
kids | +0.048 |
idea | +0.046 |
do | +0.043 |
sun | +0.042 |
wind | +0.041 |
Neg logit contributions | |
otte | -0.045 |
Charl | -0.045 |
astically | -0.044 |
Har | -0.043 |
ically | -0.042 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
idea | +0.013 |
kids | +0.013 |
do | +0.011 |
sun | +0.010 |
wind | +0.010 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.027 |
Har | -0.026 |
ky | -0.025 |
May | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
idea | +0.084 |
kids | +0.084 |
do | +0.074 |
sun | +0.072 |
wind | +0.070 |
Neg logit contributions | |
Charl | -0.105 |
otte | -0.104 |
Har | -0.099 |
May | -0.097 |
astically | -0.097 |
Token | Will |
Token ID | 2561 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
idea | +0.030 |
kids | +0.029 |
do | +0.025 |
sun | +0.024 |
friends | +0.024 |
Neg logit contributions | |
Charl | -0.036 |
otte | -0.035 |
May | -0.034 |
Har | -0.033 |
ky | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.014 |
do | +0.013 |
friends | +0.012 |
sun | +0.012 |
Neg logit contributions | |
Charl | -0.029 |
otte | -0.029 |
Har | -0.029 |
ky | -0.028 |
Jessica | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
kids | +0.013 |
idea | +0.012 |
sun | +0.011 |
do | +0.010 |
wind | +0.010 |
Neg logit contributions | |
otte | -0.030 |
Charl | -0.030 |
Har | -0.029 |
den | -0.028 |
ky | -0.028 |
Token | Good |
Token ID | 10248 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
do | +0.003 |
sun | +0.003 |
wind | +0.003 |
Neg logit contributions | |
otte | -0.004 |
Charl | -0.004 |
Har | -0.004 |
Smith | -0.003 |
la | -0.003 |
Token | idea |
Token ID | 2126 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
kids | +0.006 |
idea | +0.005 |
do | +0.005 |
expect | +0.004 |
sun | +0.004 |
Neg logit contributions | |
otte | -0.012 |
Charl | -0.012 |
ky | -0.012 |
Smith | -0.012 |
astically | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Charl | +0.016 |
otte | +0.016 |
Har | +0.015 |
ky | +0.015 |
May | +0.015 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.014 |
do | -0.012 |
sun | -0.012 |
wind | -0.012 |
Token | Cow |
Token ID | 10417 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Charl | +0.013 |
otte | +0.013 |
Smith | +0.012 |
May | +0.012 |
Har | +0.012 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.012 |
expect | -0.012 |
oops | -0.012 |
do | -0.011 |
Token | ." |
Token ID | 526 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
kids | +0.072 |
idea | +0.071 |
do | +0.062 |
friends | +0.060 |
sun | +0.059 |
Neg logit contributions | |
Charl | -0.118 |
otte | -0.116 |
Har | -0.114 |
May | -0.111 |
Jessica | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Charl | +0.027 |
otte | +0.026 |
Har | +0.026 |
Smith | +0.025 |
May | +0.025 |
Neg logit contributions | |
idea | -0.022 |
kids | -0.021 |
expect | -0.019 |
do | -0.019 |
wind | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Charl | +0.004 |
otte | +0.004 |
Har | +0.004 |
May | +0.004 |
Smith | +0.004 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
wind | -0.003 |
urge | -0.003 |
do | -0.003 |
Token | But |
Token ID | 1537 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
otte | +0.007 |
Charl | +0.007 |
den | +0.007 |
Alexa | +0.007 |
Smith | +0.006 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.008 |
do | -0.007 |
sun | -0.007 |
friends | -0.007 |
Token | then |
Token ID | 788 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Charl | +0.015 |
otte | +0.014 |
Har | +0.014 |
Jessica | +0.014 |
den | +0.014 |
Neg logit contributions | |
kids | -0.011 |
idea | -0.011 |
sun | -0.010 |
do | -0.010 |
friends | -0.009 |
Token | chickens |
Token ID | 25972 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Charl | +0.012 |
Smith | +0.012 |
Har | +0.012 |
ky | +0.011 |
otte | +0.011 |
Neg logit contributions | |
idea | -0.007 |
oops | -0.007 |
expect | -0.006 |
n | -0.005 |
add | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
sun | +0.005 |
wind | +0.005 |
Neg logit contributions | |
Charl | -0.008 |
otte | -0.008 |
Har | -0.007 |
May | -0.007 |
ky | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
idea | +0.013 |
kids | +0.012 |
expect | +0.012 |
promises | +0.011 |
choices | +0.011 |
Neg logit contributions | |
ically | -0.014 |
otte | -0.013 |
astically | -0.013 |
onna | -0.013 |
May | -0.013 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
idea | +0.008 |
kids | +0.007 |
do | +0.006 |
sun | +0.006 |
wind | +0.006 |
Neg logit contributions | |
Charl | -0.012 |
otte | -0.012 |
Har | -0.011 |
ky | -0.011 |
May | -0.011 |
Token | O |
Token ID | 440 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
idea | +0.014 |
kids | +0.013 |
do | +0.012 |
urge | +0.011 |
sun | +0.011 |
Neg logit contributions | |
otte | -0.019 |
Charl | -0.019 |
Har | -0.019 |
la | -0.018 |
May | -0.018 |
Token | ink |
Token ID | 676 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
otte | +0.006 |
Charl | +0.006 |
Har | +0.006 |
ky | +0.005 |
la | +0.005 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.013 |
relief | -0.012 |
sun | -0.012 |
wind | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
kids | +0.080 |
idea | +0.078 |
do | +0.070 |
sun | +0.069 |
wind | +0.068 |
Neg logit contributions | |
Charl | -0.109 |
otte | -0.108 |
Har | -0.101 |
May | -0.100 |
Jessica | -0.099 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.002 |
May | -0.002 |
astically | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
kids | +0.013 |
idea | +0.013 |
do | +0.012 |
sun | +0.011 |
friends | +0.011 |
Neg logit contributions | |
Charl | -0.013 |
otte | -0.013 |
Har | -0.012 |
May | -0.012 |
ky | -0.012 |
Token | bite |
Token ID | 13197 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
idea | +0.011 |
kids | +0.011 |
sun | +0.009 |
wind | +0.008 |
do | +0.008 |
Neg logit contributions | |
Charl | -0.022 |
otte | -0.022 |
Har | -0.022 |
astically | -0.021 |
May | -0.021 |
Token | him |
Token ID | 683 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
kids | +0.013 |
idea | +0.013 |
do | +0.011 |
sun | +0.011 |
friends | +0.010 |
Neg logit contributions | |
Charl | -0.025 |
otte | -0.025 |
Har | -0.024 |
May | -0.024 |
astically | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
otte | +0.012 |
Charl | +0.012 |
ically | +0.012 |
Har | +0.011 |
astically | +0.011 |
Neg logit contributions | |
kids | -0.006 |
idea | -0.005 |
friends | -0.005 |
sun | -0.005 |
do | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
otte | +0.046 |
Charl | +0.045 |
ically | +0.045 |
ky | +0.044 |
astically | +0.044 |
Neg logit contributions | |
kids | -0.022 |
idea | -0.020 |
do | -0.018 |
friends | -0.017 |
sun | -0.017 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
kids | +0.008 |
idea | +0.007 |
sun | +0.007 |
do | +0.006 |
wind | +0.006 |
Neg logit contributions | |
otte | -0.030 |
astically | -0.029 |
la | -0.029 |
ky | -0.029 |
den | -0.029 |
Token | called |
Token ID | 1444 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
do | +0.003 |
friends | +0.003 |
sun | +0.003 |
Neg logit contributions | |
otte | -0.006 |
Charl | -0.006 |
Har | -0.006 |
astically | -0.006 |
Jessica | -0.006 |
Token | Spr |
Token ID | 5522 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
otte | +0.011 |
Charl | +0.011 |
ky | +0.011 |
astically | +0.011 |
ically | +0.011 |
Neg logit contributions | |
kids | -0.007 |
idea | -0.006 |
do | -0.006 |
sun | -0.006 |
friends | -0.005 |
Token | ink |
Token ID | 676 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
kids | +0.015 |
idea | +0.015 |
do | +0.014 |
sun | +0.014 |
friends | +0.014 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.015 |
Har | -0.014 |
May | -0.014 |
Smith | -0.014 |
Token | les |
Token ID | 829 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
kids | +0.075 |
idea | +0.068 |
friends | +0.067 |
sun | +0.064 |
animals | +0.063 |
Neg logit contributions | |
Charl | -0.117 |
otte | -0.116 |
Har | -0.108 |
Alexa | -0.107 |
Jessica | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
kids | +0.009 |
friends | +0.008 |
idea | +0.008 |
of | +0.007 |
do | +0.007 |
Neg logit contributions | |
Charl | -0.021 |
otte | -0.021 |
Jessica | -0.020 |
Har | -0.020 |
May | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Charl | +0.006 |
otte | +0.006 |
May | +0.006 |
Smith | +0.006 |
Har | +0.005 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
expect | -0.004 |
do | -0.004 |
wind | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
kids | +0.008 |
oops | +0.008 |
choices | +0.007 |
idea | +0.007 |
expect | +0.007 |
Neg logit contributions | |
y | -0.008 |
Charl | -0.008 |
Smith | -0.008 |
otte | -0.008 |
any | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Charl | +0.005 |
otte | +0.005 |
Jessica | +0.005 |
ky | +0.005 |
Har | +0.005 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.002 |
do | -0.002 |
sun | -0.002 |
friends | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
kids | +0.018 |
idea | +0.018 |
do | +0.016 |
sun | +0.015 |
friends | +0.015 |
Neg logit contributions | |
Charl | -0.030 |
otte | -0.029 |
Har | -0.028 |
May | -0.028 |
ky | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
idea | +0.012 |
kids | +0.011 |
expect | +0.010 |
do | +0.010 |
urge | +0.010 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.014 |
May | -0.014 |
Har | -0.014 |
Alexa | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.015 |
do | +0.012 |
sun | +0.012 |
friends | +0.011 |
Neg logit contributions | |
Charl | -0.031 |
otte | -0.031 |
Har | -0.030 |
ky | -0.030 |
astically | -0.029 |
Token | " |
Token ID | 1 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
kids | +0.014 |
idea | +0.014 |
do | +0.013 |
sun | +0.012 |
wind | +0.012 |
Neg logit contributions | |
otte | -0.016 |
Charl | -0.016 |
Smith | -0.016 |
la | -0.015 |
work | -0.015 |
Token | Ch |
Token ID | 1925 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
kids | +0.015 |
sun | +0.013 |
idea | +0.013 |
wind | +0.013 |
do | +0.013 |
Neg logit contributions | |
otte | -0.017 |
Charl | -0.016 |
astically | -0.015 |
la | -0.015 |
ky | -0.015 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
idea | +0.032 |
kids | +0.031 |
do | +0.027 |
sun | +0.027 |
wind | +0.026 |
Neg logit contributions | |
Charl | -0.045 |
otte | -0.045 |
Har | -0.043 |
ky | -0.043 |
astically | -0.043 |
Token | cho |
Token ID | 1727 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
idea | +0.076 |
kids | +0.075 |
do | +0.066 |
sun | +0.064 |
wind | +0.063 |
Neg logit contributions | |
Charl | -0.107 |
otte | -0.106 |
Har | -0.101 |
May | -0.100 |
ky | -0.099 |
Token | o |
Token ID | 78 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
kids | +0.052 |
idea | +0.051 |
do | +0.047 |
friends | +0.043 |
of | +0.043 |
Neg logit contributions | |
Charl | -0.060 |
otte | -0.060 |
Har | -0.059 |
May | -0.057 |
Avery | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
kids | +0.029 |
idea | +0.028 |
do | +0.027 |
friends | +0.023 |
wind | +0.023 |
Neg logit contributions | |
Charl | -0.053 |
otte | -0.051 |
Har | -0.050 |
Jessica | -0.049 |
May | -0.048 |
Token | this |
Token ID | 428 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Charl | +0.009 |
otte | +0.009 |
ky | +0.009 |
May | +0.008 |
Har | +0.008 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.006 |
friends | -0.005 |
choices | -0.005 |
expect | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
sun | +0.005 |
friends | +0.005 |
Neg logit contributions | |
Charl | -0.009 |
otte | -0.008 |
ky | -0.008 |
Har | -0.008 |
astically | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
kids | +0.009 |
idea | +0.009 |
sun | +0.008 |
do | +0.007 |
friends | +0.007 |
Neg logit contributions | |
otte | -0.023 |
Charl | -0.023 |
Har | -0.023 |
astically | -0.022 |
Gr | -0.022 |
Token | made |
Token ID | 925 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Charl | +0.028 |
otte | +0.028 |
Har | +0.027 |
astically | +0.026 |
May | +0.026 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.015 |
do | -0.014 |
sun | -0.013 |
wind | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
idea | +0.009 |
kids | +0.009 |
do | +0.007 |
sun | +0.007 |
friends | +0.007 |
Neg logit contributions | |
Charl | -0.019 |
otte | -0.019 |
Har | -0.018 |
ky | -0.018 |
May | -0.018 |
Token | white |
Token ID | 2330 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
otte | +0.021 |
Charl | +0.021 |
astically | +0.020 |
Har | +0.019 |
ically | +0.019 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.012 |
sun | -0.011 |
friends | -0.011 |
do | -0.011 |
Token | tw |
Token ID | 665 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
kids | +0.003 |
idea | +0.002 |
sun | +0.002 |
friends | +0.002 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.005 |
Charl | -0.005 |
Har | -0.005 |
Jessica | -0.005 |
May | -0.005 |
Token | ink |
Token ID | 676 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Charl | +0.021 |
otte | +0.021 |
Har | +0.020 |
May | +0.020 |
Smith | +0.020 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.017 |
do | -0.015 |
sun | -0.015 |
wind | -0.015 |
Token | ly |
Token ID | 306 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
idea | +0.076 |
kids | +0.073 |
sun | +0.067 |
do | +0.066 |
wind | +0.066 |
Neg logit contributions | |
Charl | -0.111 |
otte | -0.110 |
Har | -0.105 |
Smith | -0.103 |
Jessica | -0.102 |
Token | dust |
Token ID | 8977 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
otte | +0.034 |
Charl | +0.034 |
Har | +0.032 |
Jessica | +0.032 |
Jason | +0.031 |
Neg logit contributions | |
sun | -0.016 |
kids | -0.016 |
idea | -0.014 |
things | -0.014 |
wind | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
idea | +0.011 |
kids | +0.010 |
sun | +0.010 |
do | +0.009 |
of | +0.009 |
Neg logit contributions | |
Charl | -0.028 |
otte | -0.028 |
Har | -0.027 |
Jessica | -0.026 |
May | -0.026 |
Token | Every |
Token ID | 3887 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
otte | +0.046 |
Charl | +0.046 |
astically | +0.043 |
Har | +0.043 |
ky | +0.043 |
Neg logit contributions | |
idea | -0.025 |
kids | -0.025 |
do | -0.021 |
sun | -0.021 |
wind | -0.020 |
Token | night |
Token ID | 1755 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
idea | +0.000 |
kids | +0.000 |
do | +0.000 |
sun | +0.000 |
wind | +0.000 |
Neg logit contributions | |
otte | -0.000 |
Charl | -0.000 |
Har | -0.000 |
May | -0.000 |
ky | -0.000 |
Token | word |
Token ID | 1573 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
otte | +0.023 |
Charl | +0.023 |
Har | +0.022 |
astically | +0.021 |
den | +0.021 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.012 |
sun | -0.011 |
do | -0.011 |
wind | -0.011 |
Token | : |
Token ID | 25 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
Charl | +0.021 |
otte | +0.021 |
Har | +0.020 |
ky | +0.019 |
Simon | +0.019 |
Neg logit contributions | |
idea | -0.009 |
kids | -0.009 |
do | -0.008 |
of | -0.008 |
sun | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
otte | +0.034 |
Charl | +0.033 |
Har | +0.031 |
abby | +0.031 |
athan | +0.031 |
Neg logit contributions | |
kids | -0.015 |
sun | -0.013 |
do | -0.013 |
animals | -0.013 |
birds | -0.013 |
Token | Sh |
Token ID | 2484 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
Charl | +0.032 |
otte | +0.032 |
Alexa | +0.029 |
athan | +0.029 |
Avery | +0.029 |
Neg logit contributions | |
kids | -0.028 |
idea | -0.026 |
do | -0.026 |
sun | -0.025 |
wind | -0.024 |
Token | r |
Token ID | 81 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
kids | +0.003 |
idea | +0.003 |
do | +0.003 |
sun | +0.003 |
wind | +0.003 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.003 |
May | -0.003 |
Simon | -0.003 |
Token | ink |
Token ID | 676 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
kids | +0.010 |
idea | +0.010 |
do | +0.009 |
sun | +0.009 |
friends | +0.009 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
Har | -0.011 |
May | -0.010 |
den | -0.010 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
idea | +0.080 |
kids | +0.080 |
do | +0.071 |
sun | +0.070 |
wind | +0.069 |
Neg logit contributions | |
Charl | -0.105 |
otte | -0.104 |
Har | -0.099 |
May | -0.095 |
Jessica | -0.095 |
Token | Tom |
Token ID | 4186 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
idea | +0.007 |
kids | +0.006 |
promises | +0.006 |
relief | +0.006 |
urge | +0.006 |
Neg logit contributions | |
Smith | -0.010 |
la | -0.010 |
astically | -0.010 |
otte | -0.010 |
ically | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Charl | +0.025 |
otte | +0.025 |
Har | +0.025 |
side | +0.024 |
Avery | +0.024 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.008 |
do | -0.007 |
friends | -0.007 |
did | -0.006 |
Token | Jen |
Token ID | 13364 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
idea | +0.039 |
promises | +0.036 |
kids | +0.035 |
choices | +0.034 |
sun | +0.033 |
Neg logit contributions | |
den | -0.052 |
la | -0.050 |
Paula | -0.050 |
any | -0.049 |
otte | -0.049 |
Token | were |
Token ID | 547 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
idea | +0.009 |
kids | +0.009 |
do | +0.009 |
urge | +0.007 |
friends | +0.007 |
Neg logit contributions | |
Charl | -0.021 |
otte | -0.021 |
Har | -0.020 |
May | -0.020 |
Jessica | -0.020 |
Token | sky |
Token ID | 6766 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
otte | +0.058 |
Charl | +0.054 |
Har | +0.052 |
rett | +0.050 |
astically | +0.050 |
Neg logit contributions | |
sun | -0.025 |
idea | -0.024 |
wind | -0.023 |
kids | -0.023 |
air | -0.022 |
Token | like |
Token ID | 588 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
idea | +0.013 |
kids | +0.013 |
sun | +0.012 |
do | +0.011 |
of | +0.011 |
Neg logit contributions | |
Charl | -0.035 |
Har | -0.034 |
otte | -0.034 |
Jessica | -0.031 |
Ba | -0.031 |
Token | jewels |
Token ID | 42701 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
otte | +0.023 |
Charl | +0.023 |
Har | +0.022 |
ically | +0.022 |
any | +0.021 |
Neg logit contributions | |
kids | -0.011 |
sun | -0.010 |
animals | -0.009 |
friends | -0.009 |
people | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
kids | +0.025 |
idea | +0.023 |
do | +0.022 |
sun | +0.022 |
of | +0.021 |
Neg logit contributions | |
Charl | -0.060 |
otte | -0.058 |
Har | -0.057 |
Jessica | -0.054 |
Ba | -0.053 |
Token | tw |
Token ID | 665 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
otte | +0.013 |
Charl | +0.013 |
Har | +0.012 |
ically | +0.012 |
May | +0.012 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.007 |
sun | -0.007 |
do | -0.007 |
friends | -0.006 |
Token | ink |
Token ID | 676 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Charl | +0.039 |
otte | +0.038 |
Smith | +0.036 |
Har | +0.036 |
May | +0.035 |
Neg logit contributions | |
idea | -0.032 |
kids | -0.031 |
do | -0.028 |
sun | -0.028 |
friends | -0.028 |
Token | ling |
Token ID | 1359 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
kids | +0.064 |
idea | +0.064 |
sun | +0.056 |
friends | +0.054 |
do | +0.054 |
Neg logit contributions | |
Charl | -0.126 |
otte | -0.125 |
Har | -0.121 |
Smith | -0.116 |
Jessica | -0.115 |
Token | away |
Token ID | 1497 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
otte | +0.047 |
Charl | +0.046 |
Har | +0.045 |
Jessica | +0.042 |
Ba | +0.042 |
Neg logit contributions | |
kids | -0.021 |
sun | -0.020 |
idea | -0.019 |
animals | -0.019 |
things | -0.018 |
Token | ." |
Token ID | 526 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.002 |
Har | +0.002 |
Em | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
kids | -0.001 |
idea | -0.001 |
sun | -0.001 |
friends | -0.001 |
things | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
Charl | +0.011 |
otte | +0.011 |
Har | +0.010 |
May | +0.010 |
ky | +0.010 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.008 |
do | -0.007 |
sun | -0.007 |
wind | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
ky | -0.002 |
Har | -0.002 |
astically | -0.002 |
Token | full |
Token ID | 1336 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Charl | +0.007 |
otte | +0.007 |
Har | +0.007 |
May | +0.007 |
astically | +0.007 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
sun | -0.004 |
wind | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
Charl | +0.015 |
otte | +0.015 |
Smith | +0.015 |
ky | +0.014 |
Har | +0.014 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.002 |
expect | -0.002 |
urge | -0.002 |
Token | bright |
Token ID | 6016 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
Charl | +0.032 |
otte | +0.031 |
ky | +0.030 |
Har | +0.030 |
May | +0.030 |
Neg logit contributions | |
idea | -0.017 |
kids | -0.016 |
do | -0.013 |
expect | -0.013 |
oops | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
do | +0.001 |
expect | +0.001 |
urge | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
ky | -0.003 |
otte | -0.003 |
Smith | -0.003 |
Har | -0.003 |
Token | tw |
Token ID | 665 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
Charl | +0.027 |
otte | +0.026 |
ky | +0.025 |
May | +0.025 |
Har | +0.025 |
Neg logit contributions | |
idea | -0.015 |
kids | -0.015 |
do | -0.012 |
friends | -0.012 |
expect | -0.011 |
Token | ink |
Token ID | 676 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Charl | +0.017 |
otte | +0.017 |
ky | +0.016 |
Har | +0.015 |
la | +0.015 |
Neg logit contributions | |
idea | -0.025 |
kids | -0.025 |
do | -0.023 |
sun | -0.022 |
wind | -0.022 |
Token | ling |
Token ID | 1359 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
kids | +0.078 |
idea | +0.077 |
sun | +0.070 |
wind | +0.068 |
do | +0.068 |
Neg logit contributions | |
Charl | -0.105 |
otte | -0.105 |
Har | -0.099 |
May | -0.097 |
astically | -0.096 |
Token | lights |
Token ID | 7588 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
otte | +0.016 |
Charl | +0.016 |
Har | +0.015 |
May | +0.015 |
Jessica | +0.015 |
Neg logit contributions | |
kids | -0.006 |
idea | -0.006 |
sun | -0.005 |
wind | -0.005 |
friends | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
otte | +0.006 |
Charl | +0.006 |
Har | +0.005 |
May | +0.005 |
Jessica | +0.005 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
sun | -0.003 |
do | -0.003 |
wind | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
Charl | +0.005 |
otte | +0.005 |
Har | +0.005 |
ky | +0.005 |
May | +0.005 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.002 |
sun | -0.002 |
wind | -0.002 |
Token | crept |
Token ID | 47092 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
kids | +0.002 |
idea | +0.002 |
do | +0.002 |
friends | +0.002 |
sun | +0.002 |
Neg logit contributions | |
Charl | -0.005 |
otte | -0.005 |
Har | -0.004 |
Smith | -0.004 |
side | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
Charl | +0.024 |
otte | +0.024 |
Har | +0.023 |
May | +0.023 |
ky | +0.022 |
Neg logit contributions | |
idea | -0.015 |
kids | -0.015 |
do | -0.012 |
sun | -0.012 |
friends | -0.012 |
Token | O |
Token ID | 46 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Charl | +0.031 |
otte | +0.030 |
Har | +0.030 |
May | +0.029 |
ky | +0.028 |
Neg logit contributions | |
idea | -0.035 |
kids | -0.033 |
friends | -0.030 |
do | -0.030 |
sun | -0.029 |
Token | ink |
Token ID | 676 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
idea | +0.011 |
kids | +0.011 |
sun | +0.010 |
wind | +0.010 |
friends | +0.010 |
Neg logit contributions | |
otte | -0.007 |
Charl | -0.007 |
ky | -0.006 |
Har | -0.006 |
ically | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
idea | +0.061 |
kids | +0.061 |
do | +0.052 |
sun | +0.050 |
wind | +0.049 |
Neg logit contributions | |
Charl | -0.111 |
otte | -0.110 |
Har | -0.105 |
May | -0.103 |
astically | -0.103 |
Token | o |
Token ID | 267 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
May | +0.032 |
otte | +0.031 |
Maya | +0.031 |
Charl | +0.031 |
Smith | +0.030 |
Neg logit contributions | |
idea | -0.037 |
acquaintance | -0.028 |
choices | -0.027 |
ag | -0.027 |
friends | -0.027 |
Token | ink |
Token ID | 676 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
idea | +0.029 |
kids | +0.028 |
expect | +0.025 |
wind | +0.025 |
noise | +0.025 |
Neg logit contributions | |
Charl | -0.021 |
otte | -0.020 |
flake | -0.020 |
ky | -0.020 |
fly | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
idea | +0.075 |
kids | +0.074 |
do | +0.065 |
sun | +0.064 |
wind | +0.062 |
Neg logit contributions | |
Charl | -0.105 |
otte | -0.104 |
Har | -0.099 |
May | -0.097 |
ky | -0.097 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Charl | +0.039 |
otte | +0.039 |
May | +0.039 |
Smith | +0.037 |
Maya | +0.037 |
Neg logit contributions | |
idea | -0.032 |
kids | -0.025 |
friends | -0.024 |
choices | -0.024 |
expect | -0.023 |
Token | ! |
Token ID | 0 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
idea | +0.018 |
kids | +0.018 |
do | +0.015 |
sun | +0.015 |
friends | +0.015 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.027 |
Har | -0.025 |
May | -0.025 |
astically | -0.025 |
Token | Can |
Token ID | 1680 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
idea | +0.019 |
kids | +0.018 |
do | +0.016 |
sun | +0.015 |
wind | +0.015 |
Neg logit contributions | |
Charl | -0.031 |
otte | -0.031 |
Har | -0.030 |
May | -0.029 |
ky | -0.029 |
Token | you |
Token ID | 345 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
idea | +0.013 |
kids | +0.011 |
sun | +0.010 |
expect | +0.010 |
urge | +0.010 |
Neg logit contributions | |
otte | -0.012 |
Charl | -0.011 |
May | -0.011 |
Smith | -0.011 |
astically | -0.011 |
Token | sky |
Token ID | 6766 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
otte | +0.005 |
Charl | +0.005 |
Har | +0.005 |
May | +0.004 |
den | +0.004 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.003 |
sun | -0.003 |
wind | -0.002 |
do | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
kids | +0.011 |
idea | +0.011 |
do | +0.011 |
sun | +0.010 |
of | +0.010 |
Neg logit contributions | |
Charl | -0.026 |
otte | -0.025 |
Har | -0.025 |
May | -0.023 |
Gr | -0.023 |
Token | shining |
Token ID | 22751 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Charl | +0.008 |
otte | +0.008 |
Har | +0.007 |
ky | +0.007 |
May | +0.007 |
Neg logit contributions | |
kids | -0.004 |
idea | -0.004 |
do | -0.004 |
sun | -0.004 |
wind | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Charl | +0.006 |
otte | +0.006 |
Har | +0.006 |
Jessica | +0.006 |
May | +0.006 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.003 |
sun | -0.003 |
wind | -0.002 |
things | -0.002 |
Token | tw |
Token ID | 665 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Charl | +0.022 |
otte | +0.022 |
Har | +0.021 |
ically | +0.020 |
astically | +0.020 |
Neg logit contributions | |
kids | -0.012 |
idea | -0.011 |
sun | -0.011 |
do | -0.011 |
wind | -0.010 |
Token | ink |
Token ID | 676 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Charl | +0.028 |
otte | +0.028 |
Har | +0.026 |
Smith | +0.026 |
May | +0.026 |
Neg logit contributions | |
idea | -0.029 |
kids | -0.028 |
do | -0.026 |
sun | -0.025 |
friends | -0.024 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
kids | +0.073 |
idea | +0.072 |
sun | +0.064 |
do | +0.063 |
wind | +0.063 |
Neg logit contributions | |
Charl | -0.115 |
otte | -0.113 |
Har | -0.108 |
Smith | -0.104 |
Jessica | -0.103 |
Token | ." |
Token ID | 526 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
otte | +0.013 |
Charl | +0.013 |
Har | +0.012 |
Jessica | +0.011 |
May | +0.011 |
Neg logit contributions | |
kids | -0.006 |
idea | -0.006 |
sun | -0.006 |
wind | -0.005 |
people | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Charl | +0.014 |
otte | +0.013 |
la | +0.013 |
Har | +0.012 |
fly | +0.012 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.008 |
sun | -0.007 |
do | -0.006 |
friends | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
kids | +0.008 |
idea | +0.007 |
do | +0.006 |
sun | +0.005 |
friends | +0.005 |
Neg logit contributions | |
otte | -0.024 |
Charl | -0.024 |
ky | -0.024 |
la | -0.023 |
ically | -0.023 |
Token | The |
Token ID | 464 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
sun | +0.001 |
do | +0.001 |
of | +0.001 |
Neg logit contributions | |
otte | -0.001 |
Charl | -0.001 |
fly | -0.001 |
la | -0.001 |
ky | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
kids | +0.008 |
idea | +0.008 |
wind | +0.007 |
choices | +0.007 |
oops | +0.007 |
Neg logit contributions | |
Charl | -0.010 |
otte | -0.010 |
Har | -0.009 |
May | -0.009 |
Jessica | -0.009 |
Token | One |
Token ID | 3198 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Charl | +0.010 |
otte | +0.010 |
Har | +0.009 |
May | +0.009 |
ky | +0.009 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
do | -0.014 |
sun | -0.014 |
wind | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
kids | +0.011 |
idea | +0.011 |
oops | +0.010 |
choices | +0.010 |
promises | +0.010 |
Neg logit contributions | |
otte | -0.016 |
Charl | -0.016 |
ky | -0.015 |
Smith | -0.015 |
den | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Charl | +0.022 |
otte | +0.022 |
Har | +0.021 |
May | +0.021 |
ky | +0.021 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
do | -0.014 |
sun | -0.014 |
friends | -0.014 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
otte | +0.017 |
Charl | +0.017 |
Har | +0.016 |
May | +0.016 |
ky | +0.016 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
do | -0.014 |
sun | -0.013 |
wind | -0.013 |
Token | inky |
Token ID | 29246 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Charl | +0.034 |
otte | +0.033 |
Jessica | +0.032 |
ky | +0.032 |
Alexa | +0.031 |
Neg logit contributions | |
kids | -0.037 |
idea | -0.037 |
do | -0.033 |
friends | -0.033 |
sun | -0.032 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
kids | +0.065 |
idea | +0.060 |
friends | +0.053 |
do | +0.052 |
sun | +0.049 |
Neg logit contributions | |
Charl | -0.125 |
otte | -0.122 |
Har | -0.118 |
May | -0.117 |
ky | -0.114 |
Token | some |
Token ID | 617 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
kids | +0.017 |
idea | +0.017 |
do | +0.015 |
sun | +0.015 |
friends | +0.014 |
Neg logit contributions | |
otte | -0.022 |
Charl | -0.022 |
Har | -0.021 |
May | -0.021 |
ky | -0.021 |
Token | kids |
Token ID | 3988 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
idea | +0.019 |
kids | +0.017 |
do | +0.014 |
oops | +0.012 |
sun | +0.012 |
Neg logit contributions | |
otte | -0.060 |
Charl | -0.060 |
Har | -0.058 |
May | -0.058 |
ky | -0.057 |
Token | playing |
Token ID | 2712 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
kids | +0.013 |
idea | +0.012 |
do | +0.011 |
friends | +0.010 |
sun | +0.010 |
Neg logit contributions | |
Charl | -0.022 |
otte | -0.021 |
Har | -0.020 |
May | -0.020 |
ically | -0.020 |
Token | outside |
Token ID | 2354 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
do | +0.002 |
friends | +0.002 |
sun | +0.002 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.003 |
la | -0.003 |
May | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
kids | +0.009 |
idea | +0.009 |
sun | +0.009 |
of | +0.008 |
friends | +0.007 |
Neg logit contributions | |
Charl | -0.042 |
otte | -0.041 |
den | -0.040 |
Thomas | -0.039 |
May | -0.039 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
idea | +0.008 |
kids | +0.008 |
do | +0.007 |
sun | +0.007 |
wind | +0.007 |
Neg logit contributions | |
Charl | -0.014 |
otte | -0.014 |
Har | -0.013 |
ky | -0.013 |
May | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
otte | +0.008 |
Charl | +0.008 |
ically | +0.008 |
astically | +0.008 |
Har | +0.008 |
Neg logit contributions | |
kids | -0.005 |
idea | -0.004 |
friends | -0.004 |
sun | -0.004 |
do | -0.004 |
Token | stars |
Token ID | 5788 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
kids | +0.002 |
idea | +0.002 |
sun | +0.002 |
wind | +0.002 |
do | +0.002 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.003 |
den | -0.002 |
astically | -0.002 |
Token | tw |
Token ID | 665 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Charl | +0.009 |
otte | +0.009 |
Har | +0.009 |
May | +0.008 |
Jessica | +0.008 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.005 |
sun | -0.005 |
friends | -0.004 |
Token | ink |
Token ID | 676 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Charl | +0.025 |
otte | +0.024 |
Smith | +0.023 |
Har | +0.023 |
May | +0.023 |
Neg logit contributions | |
idea | -0.022 |
kids | -0.021 |
do | -0.019 |
sun | -0.019 |
friends | -0.019 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
idea | +0.076 |
kids | +0.075 |
sun | +0.067 |
do | +0.066 |
wind | +0.065 |
Neg logit contributions | |
Charl | -0.106 |
otte | -0.106 |
Har | -0.100 |
May | -0.098 |
Jessica | -0.097 |
Token | in |
Token ID | 287 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
otte | +0.007 |
Charl | +0.007 |
Har | +0.007 |
Jessica | +0.007 |
May | +0.007 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
sun | -0.003 |
wind | -0.003 |
animals | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
otte | +0.031 |
Charl | +0.030 |
ically | +0.029 |
den | +0.029 |
astically | +0.029 |
Neg logit contributions | |
kids | -0.010 |
idea | -0.010 |
sun | -0.008 |
wind | -0.008 |
do | -0.008 |
Token | night |
Token ID | 1755 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
otte | +0.041 |
Charl | +0.038 |
ge | +0.038 |
rett | +0.038 |
den | +0.038 |
Neg logit contributions | |
sun | -0.013 |
wind | -0.012 |
kids | -0.012 |
idea | -0.011 |
air | -0.011 |
Token | sky |
Token ID | 6766 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
otte | +0.030 |
Charl | +0.030 |
Har | +0.028 |
May | +0.028 |
den | +0.027 |
Neg logit contributions | |
kids | -0.016 |
idea | -0.016 |
sun | -0.015 |
wind | -0.014 |
do | -0.014 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.016 |
do | +0.013 |
sun | +0.013 |
wind | +0.012 |
Neg logit contributions | |
Charl | -0.036 |
otte | -0.036 |
Har | -0.034 |
May | -0.034 |
ky | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
kids | +0.005 |
idea | +0.005 |
sun | +0.001 |
do | +0.001 |
of | +0.000 |
Neg logit contributions | |
otte | -0.077 |
Charl | -0.076 |
Har | -0.074 |
May | -0.073 |
astically | -0.072 |
Token | fun |
Token ID | 1257 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
oops | +0.027 |
There | +0.024 |
kids | +0.024 |
expect | +0.023 |
tum | +0.023 |
Neg logit contributions | |
Charl | -0.048 |
Har | -0.046 |
otte | -0.045 |
neatly | -0.044 |
May | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.016 |
wind | +0.015 |
oops | +0.015 |
expect | +0.015 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.015 |
ky | -0.015 |
astically | -0.015 |
ically | -0.014 |
Token | Bl |
Token ID | 1086 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Charl | +0.017 |
otte | +0.017 |
ky | +0.017 |
Har | +0.017 |
astically | +0.016 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.014 |
do | -0.012 |
expect | -0.012 |
sun | -0.011 |
Token | inky |
Token ID | 29246 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Charl | +0.037 |
otte | +0.036 |
Jessica | +0.035 |
den | +0.034 |
ky | +0.034 |
Neg logit contributions | |
idea | -0.042 |
kids | -0.042 |
do | -0.037 |
friends | -0.037 |
sun | -0.036 |
Token | wanted |
Token ID | 2227 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
kids | +0.064 |
idea | +0.056 |
friends | +0.055 |
do | +0.050 |
children | +0.046 |
Neg logit contributions | |
Charl | -0.130 |
otte | -0.126 |
Har | -0.124 |
May | -0.121 |
side | -0.119 |
Token | to |
Token ID | 284 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
kids | +0.029 |
friends | +0.024 |
sun | +0.023 |
do | +0.023 |
animals | +0.023 |
Neg logit contributions | |
Charl | -0.044 |
otte | -0.043 |
ically | -0.041 |
May | -0.040 |
Har | -0.040 |
Token | join |
Token ID | 4654 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
idea | +0.024 |
kids | +0.023 |
do | +0.021 |
sun | +0.018 |
friends | +0.017 |
Neg logit contributions | |
Charl | -0.071 |
otte | -0.070 |
Har | -0.067 |
ky | -0.067 |
May | -0.067 |
Token | them |
Token ID | 606 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
friends | +0.001 |
do | +0.001 |
people | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
ically | -0.003 |
astically | -0.003 |
Har | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
kids | +0.029 |
idea | +0.028 |
friends | +0.025 |
do | +0.025 |
sun | +0.023 |
Neg logit contributions | |
Charl | -0.055 |
otte | -0.054 |
Har | -0.053 |
Jessica | -0.051 |
May | -0.051 |
Token | not |
Token ID | 407 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.003 |
ky | +0.003 |
Har | +0.003 |
May | +0.003 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
do | -0.002 |
sun | -0.001 |
friends | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.003 |
Har | +0.003 |
May | +0.003 |
ky | +0.003 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
do | -0.001 |
sun | -0.001 |
wind | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
kids | +0.008 |
idea | +0.008 |
do | +0.007 |
sun | +0.007 |
wind | +0.006 |
Neg logit contributions | |
otte | -0.015 |
Charl | -0.015 |
Har | -0.014 |
ky | -0.014 |
May | -0.014 |
Token | A |
Token ID | 32 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Charl | +0.013 |
otte | +0.013 |
Har | +0.012 |
ky | +0.012 |
May | +0.012 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.013 |
do | -0.011 |
sun | -0.011 |
wind | -0.011 |
Token | ch |
Token ID | 354 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
otte | +0.012 |
Charl | +0.011 |
ky | +0.011 |
la | +0.011 |
astically | +0.011 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.007 |
do | -0.007 |
sun | -0.007 |
wind | -0.007 |
Token | oo |
Token ID | 2238 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
idea | +0.023 |
kids | +0.023 |
do | +0.020 |
sun | +0.019 |
wind | +0.019 |
Neg logit contributions | |
Charl | -0.033 |
otte | -0.033 |
Har | -0.031 |
May | -0.031 |
ky | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
idea | +0.078 |
kids | +0.077 |
do | +0.068 |
sun | +0.066 |
friends | +0.065 |
Neg logit contributions | |
Charl | -0.098 |
otte | -0.097 |
Har | -0.092 |
May | -0.091 |
ky | -0.091 |
Token | she |
Token ID | 673 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Charl | +0.030 |
otte | +0.030 |
Har | +0.029 |
ky | +0.028 |
May | +0.028 |
Neg logit contributions | |
idea | -0.023 |
kids | -0.023 |
do | -0.020 |
sun | -0.020 |
wind | -0.019 |
Token | sne |
Token ID | 10505 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Charl | +0.024 |
otte | +0.024 |
Har | +0.023 |
May | +0.023 |
ky | +0.023 |
Neg logit contributions | |
idea | -0.010 |
kids | -0.009 |
do | -0.008 |
sun | -0.007 |
wind | -0.007 |
Token | ez |
Token ID | 8471 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
kids | +0.045 |
idea | +0.045 |
sun | +0.040 |
do | +0.040 |
wind | +0.039 |
Neg logit contributions | |
Charl | -0.035 |
otte | -0.034 |
ky | -0.032 |
Har | -0.032 |
May | -0.031 |
Token | ed |
Token ID | 276 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
kids | +0.016 |
idea | +0.014 |
friends | +0.014 |
do | +0.014 |
wind | +0.013 |
Neg logit contributions | |
otte | -0.015 |
Charl | -0.015 |
Har | -0.015 |
astically | -0.014 |
Jessica | -0.014 |
Token | star |
Token ID | 3491 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
idea | +0.009 |
kids | +0.009 |
sun | +0.008 |
do | +0.008 |
wind | +0.007 |
Neg logit contributions | |
otte | -0.016 |
Charl | -0.016 |
Har | -0.016 |
astically | -0.015 |
ically | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
do | +0.003 |
sun | +0.002 |
friends | +0.002 |
Neg logit contributions | |
Charl | -0.005 |
otte | -0.005 |
Har | -0.005 |
Jessica | -0.004 |
May | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Charl | +0.010 |
otte | +0.010 |
Har | +0.010 |
ky | +0.010 |
May | +0.010 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
sun | -0.004 |
wind | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
do | +0.003 |
sun | +0.003 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.005 |
Charl | -0.005 |
Har | -0.005 |
May | -0.004 |
astically | -0.004 |
Token | tw |
Token ID | 665 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
idea | +0.008 |
kids | +0.008 |
sun | +0.008 |
wind | +0.007 |
do | +0.007 |
Neg logit contributions | |
otte | -0.017 |
Charl | -0.017 |
Har | -0.016 |
den | -0.016 |
May | -0.016 |
Token | ink |
Token ID | 676 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Charl | +0.016 |
otte | +0.016 |
Har | +0.015 |
ky | +0.015 |
May | +0.015 |
Neg logit contributions | |
idea | -0.023 |
kids | -0.023 |
do | -0.021 |
sun | -0.020 |
wind | -0.020 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
idea | +0.078 |
kids | +0.077 |
sun | +0.069 |
do | +0.068 |
wind | +0.068 |
Neg logit contributions | |
otte | -0.100 |
Charl | -0.100 |
Har | -0.094 |
Smith | -0.093 |
May | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
otte | +0.002 |
Charl | +0.002 |
Jessica | +0.002 |
Har | +0.002 |
May | +0.002 |
Neg logit contributions | |
sun | -0.001 |
idea | -0.001 |
of | -0.001 |
kids | -0.000 |
wind | -0.000 |
Token | shimmer |
Token ID | 34493 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
sun | +0.001 |
kids | +0.001 |
friends | +0.001 |
wind | +0.001 |
do | +0.001 |
Neg logit contributions | |
otte | -0.002 |
Charl | -0.002 |
Har | -0.002 |
den | -0.002 |
astically | -0.002 |
Token | ing |
Token ID | 278 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
idea | +0.042 |
kids | +0.042 |
do | +0.038 |
sun | +0.038 |
wind | +0.037 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.027 |
Har | -0.025 |
May | -0.024 |
ky | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
otte | +0.015 |
Charl | +0.015 |
Har | +0.015 |
Jessica | +0.014 |
May | +0.014 |
Neg logit contributions | |
idea | -0.007 |
sun | -0.007 |
kids | -0.006 |
wind | -0.006 |
things | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Charl | +0.012 |
otte | +0.012 |
Har | +0.012 |
astically | +0.012 |
ky | +0.012 |
Neg logit contributions | |
idea | -0.006 |
kids | -0.006 |
do | -0.006 |
noise | -0.005 |
friends | -0.005 |
Token | A |
Token ID | 32 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
kids | +0.002 |
idea | +0.002 |
do | +0.002 |
sun | +0.002 |
wind | +0.002 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.002 |
May | -0.002 |
astically | -0.002 |
Token | good |
Token ID | 922 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
idea | +0.011 |
kids | +0.011 |
do | +0.010 |
sun | +0.009 |
wind | +0.009 |
Neg logit contributions | |
otte | -0.021 |
Charl | -0.021 |
Har | -0.020 |
May | -0.020 |
ky | -0.020 |
Token | wind |
Token ID | 2344 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
oops | +0.003 |
do | +0.003 |
sun | +0.003 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.015 |
Smith | -0.015 |
Har | -0.015 |
ically | -0.015 |
Token | is |
Token ID | 318 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
do | +0.004 |
wind | +0.004 |
friends | +0.004 |
Neg logit contributions | |
Charl | -0.010 |
Har | -0.010 |
otte | -0.010 |
May | -0.010 |
Jessica | -0.009 |
Token | when |
Token ID | 618 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
idea | +0.037 |
kids | +0.035 |
do | +0.033 |
sun | +0.032 |
wind | +0.032 |
Neg logit contributions | |
otte | -0.060 |
Charl | -0.059 |
Har | -0.056 |
May | -0.056 |
Jessica | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
kids | +0.051 |
idea | +0.043 |
do | +0.040 |
sun | +0.039 |
friends | +0.039 |
Neg logit contributions | |
Charl | -0.140 |
otte | -0.136 |
Har | -0.133 |
ky | -0.133 |
May | -0.132 |
Token | air |
Token ID | 1633 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.004 |
sun | +0.004 |
wind | +0.004 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.022 |
Har | -0.022 |
May | -0.021 |
ky | -0.021 |
Token | moves |
Token ID | 6100 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
idea | +0.020 |
kids | +0.019 |
do | +0.017 |
sun | +0.016 |
wind | +0.016 |
Neg logit contributions | |
Charl | -0.037 |
otte | -0.036 |
Har | -0.035 |
May | -0.034 |
ky | -0.034 |
Token | quickly |
Token ID | 2952 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
kids | +0.020 |
idea | +0.020 |
do | +0.019 |
wind | +0.018 |
of | +0.017 |
Neg logit contributions | |
otte | -0.045 |
Charl | -0.044 |
Har | -0.043 |
Jessica | -0.043 |
May | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
idea | +0.028 |
kids | +0.028 |
do | +0.026 |
wind | +0.024 |
sun | +0.024 |
Neg logit contributions | |
otte | -0.059 |
Charl | -0.059 |
Har | -0.056 |
Jessica | -0.056 |
May | -0.055 |
Token | go |
Token ID | 467 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
do | +0.003 |
sun | +0.002 |
friends | +0.002 |
Neg logit contributions | |
Charl | -0.010 |
otte | -0.010 |
Har | -0.010 |
ky | -0.010 |
May | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.006 |
sun | +0.006 |
friends | +0.005 |
Neg logit contributions | |
Charl | -0.008 |
otte | -0.008 |
Har | -0.008 |
May | -0.008 |
ky | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
otte | +0.076 |
ically | +0.076 |
den | +0.074 |
fly | +0.073 |
abby | +0.072 |
Neg logit contributions | |
kids | -0.028 |
things | -0.024 |
sun | -0.024 |
friends | -0.024 |
fun | -0.022 |
Token | special |
Token ID | 2041 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
otte | +0.025 |
Charl | +0.025 |
Har | +0.023 |
ically | +0.023 |
May | +0.023 |
Neg logit contributions | |
idea | -0.012 |
kids | -0.012 |
do | -0.011 |
sun | -0.010 |
wind | -0.010 |
Token | adventure |
Token ID | 8855 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.005 |
do | +0.005 |
sun | +0.004 |
wind | +0.004 |
Neg logit contributions | |
otte | -0.019 |
Charl | -0.019 |
Har | -0.018 |
May | -0.018 |
ky | -0.018 |
Token | ," |
Token ID | 553 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
do | +0.001 |
of | +0.001 |
friends | +0.001 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
May | -0.001 |
Ba | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
otte | +0.116 |
Charl | +0.114 |
Har | +0.109 |
Smith | +0.109 |
May | +0.109 |
Neg logit contributions | |
idea | -0.118 |
kids | -0.110 |
oops | -0.101 |
sun | -0.101 |
add | -0.100 |
Token | said |
Token ID | 531 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
otte | +0.042 |
Charl | +0.042 |
den | +0.040 |
Har | +0.040 |
la | +0.040 |
Neg logit contributions | |
kids | -0.019 |
idea | -0.019 |
sun | -0.016 |
do | -0.016 |
wind | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Charl | +0.027 |
otte | +0.026 |
Har | +0.026 |
ky | +0.026 |
May | +0.025 |
Neg logit contributions | |
idea | -0.015 |
kids | -0.014 |
do | -0.012 |
friends | -0.012 |
noise | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Charl | +0.044 |
otte | +0.044 |
ky | +0.042 |
Har | +0.042 |
den | +0.041 |
Neg logit contributions | |
kids | -0.031 |
idea | -0.030 |
do | -0.026 |
sun | -0.026 |
wind | -0.025 |
Token | gathered |
Token ID | 9272 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
friends | +0.005 |
sun | +0.005 |
Neg logit contributions | |
Charl | -0.012 |
otte | -0.011 |
Har | -0.011 |
ky | -0.011 |
May | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
idea | +0.030 |
kids | +0.030 |
do | +0.026 |
friends | +0.025 |
sun | +0.025 |
Neg logit contributions | |
Charl | -0.045 |
otte | -0.045 |
Har | -0.043 |
May | -0.042 |
Jessica | -0.042 |
Token | it |
Token ID | 340 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
Avery | +0.049 |
Alexa | +0.048 |
Maya | +0.048 |
otte | +0.047 |
Charl | +0.046 |
Neg logit contributions | |
idea | -0.057 |
add | -0.049 |
ag | -0.047 |
kids | -0.046 |
acquaintance | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
Charl | +0.002 |
otte | +0.002 |
astically | +0.002 |
ky | +0.002 |
Har | +0.002 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
sun | -0.001 |
do | -0.001 |
wind | -0.001 |
Token | raining |
Token ID | 43079 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
do | +0.002 |
sun | +0.002 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.003 |
May | -0.003 |
ky | -0.003 |
Token | outside |
Token ID | 2354 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
otte | +0.025 |
Charl | +0.024 |
Simon | +0.024 |
Har | +0.024 |
April | +0.023 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.012 |
wind | -0.011 |
noise | -0.011 |
do | -0.011 |
Token | ," |
Token ID | 553 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Charl | +0.026 |
otte | +0.025 |
Har | +0.024 |
May | +0.023 |
ically | +0.023 |
Neg logit contributions | |
kids | -0.013 |
idea | -0.012 |
do | -0.011 |
of | -0.011 |
noise | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
otte | +0.135 |
Charl | +0.131 |
ky | +0.129 |
Har | +0.128 |
Alexa | +0.128 |
Neg logit contributions | |
idea | -0.094 |
kids | -0.089 |
sun | -0.078 |
do | -0.076 |
wind | -0.075 |
Token | said |
Token ID | 531 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
otte | +0.059 |
Charl | +0.058 |
la | +0.057 |
Har | +0.057 |
ky | +0.056 |
Neg logit contributions | |
idea | -0.029 |
kids | -0.029 |
sun | -0.026 |
do | -0.024 |
oops | -0.023 |
Token | sadly |
Token ID | 21098 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.004 |
do | +0.004 |
friends | +0.004 |
noise | +0.004 |
Neg logit contributions | |
Charl | -0.014 |
otte | -0.013 |
Har | -0.013 |
May | -0.013 |
April | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.005 |
do | +0.005 |
sun | +0.005 |
friends | +0.005 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
Har | -0.010 |
May | -0.010 |
Jessica | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
Charl | +0.033 |
otte | +0.033 |
Har | +0.031 |
ky | +0.031 |
May | +0.031 |
Neg logit contributions | |
idea | -0.017 |
kids | -0.017 |
do | -0.015 |
sun | -0.014 |
wind | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.018 |
Har | +0.017 |
ky | +0.017 |
May | +0.017 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
do | -0.010 |
sun | -0.009 |
wind | -0.009 |
Token | mixture |
Token ID | 11710 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Charl | +0.032 |
otte | +0.032 |
Har | +0.030 |
May | +0.030 |
ky | +0.030 |
Neg logit contributions | |
idea | -0.020 |
kids | -0.020 |
do | -0.017 |
sun | -0.017 |
wind | -0.016 |
Token | into |
Token ID | 656 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
Charl | +0.005 |
Har | +0.005 |
April | +0.005 |
otte | +0.005 |
Ba | +0.005 |
Neg logit contributions | |
idea | -0.003 |
of | -0.003 |
sun | -0.003 |
kids | -0.002 |
wind | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -7.76e-04 |
Pos logit contributions | |
Charl | +0.025 |
otte | +0.024 |
Har | +0.024 |
astically | +0.023 |
den | +0.023 |
Neg logit contributions | |
kids | -0.012 |
idea | -0.012 |
sun | -0.010 |
do | -0.010 |
friends | -0.010 |
Token | baking |
Token ID | 16871 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Charl | +0.000 |
otte | +0.000 |
Har | +0.000 |
den | +0.000 |
astically | +0.000 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
sun | -0.000 |
do | -0.000 |
friends | -0.000 |
Token | tr |
Token ID | 491 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Charl | +0.022 |
otte | +0.022 |
Har | +0.022 |
astically | +0.021 |
May | +0.020 |
Neg logit contributions | |
idea | -0.012 |
kids | -0.012 |
sun | -0.011 |
do | -0.010 |
wind | -0.010 |
Token | ays |
Token ID | 592 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Charl | +0.099 |
otte | +0.098 |
Har | +0.093 |
May | +0.093 |
den | +0.092 |
Neg logit contributions | |
idea | -0.108 |
kids | -0.107 |
sun | -0.096 |
do | -0.095 |
oops | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Charl | +0.004 |
otte | +0.004 |
Har | +0.004 |
Ba | +0.004 |
May | +0.004 |
Neg logit contributions | |
idea | -0.001 |
kids | -0.001 |
of | -0.001 |
sun | -0.001 |
wind | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.014 |
do | +0.013 |
sun | +0.012 |
wind | +0.012 |
Neg logit contributions | |
otte | -0.020 |
Charl | -0.020 |
Har | -0.019 |
ky | -0.019 |
May | -0.018 |
Token | put |
Token ID | 1234 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
idea | +0.014 |
kids | +0.013 |
do | +0.012 |
friends | +0.012 |
y | +0.011 |
Neg logit contributions | |
Charl | -0.026 |
otte | -0.025 |
Har | -0.025 |
Smith | -0.024 |
Jessica | -0.024 |
Token | them |
Token ID | 606 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.015 |
do | +0.013 |
sun | +0.013 |
wind | +0.012 |
Neg logit contributions | |
Charl | -0.033 |
otte | -0.033 |
Har | -0.031 |
May | -0.031 |
ky | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
kids | +0.020 |
idea | +0.020 |
sun | +0.017 |
do | +0.017 |
wind | +0.016 |
Neg logit contributions | |
Charl | -0.038 |
otte | -0.037 |
Har | -0.037 |
Jessica | -0.035 |
May | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Charl | +0.033 |
otte | +0.033 |
Har | +0.032 |
ky | +0.032 |
May | +0.031 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
do | -0.014 |
sun | -0.013 |
friends | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
do | +0.004 |
sun | +0.004 |
friends | +0.004 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
ky | -0.010 |
Har | -0.010 |
astically | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ky | +0.012 |
work | +0.012 |
den | +0.012 |
Smith | +0.012 |
otte | +0.012 |
Neg logit contributions | |
kids | -0.016 |
idea | -0.015 |
do | -0.015 |
friends | -0.015 |
sun | -0.014 |
Token | No |
Token ID | 2949 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
ky | -0.001 |
astically | -0.001 |
Token | ," |
Token ID | 553 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
idea | +0.012 |
kids | +0.011 |
do | +0.010 |
sun | +0.010 |
wind | +0.009 |
Neg logit contributions | |
Charl | -0.019 |
otte | -0.019 |
Har | -0.018 |
May | -0.018 |
ky | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Charl | +0.109 |
otte | +0.109 |
Har | +0.103 |
May | +0.101 |
ky | +0.101 |
Neg logit contributions | |
idea | -0.102 |
kids | -0.101 |
do | -0.089 |
sun | -0.088 |
wind | -0.086 |
Token | her |
Token ID | 607 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Charl | +0.073 |
astically | +0.070 |
otte | +0.069 |
Har | +0.069 |
ky | +0.069 |
Neg logit contributions | |
idea | -0.058 |
kids | -0.056 |
do | -0.050 |
friends | -0.050 |
sun | -0.048 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Charl | +0.015 |
otte | +0.015 |
Har | +0.015 |
ky | +0.015 |
astically | +0.014 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
friends | -0.004 |
sun | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
Charl | +0.007 |
otte | +0.007 |
Har | +0.007 |
May | +0.007 |
ky | +0.007 |
Neg logit contributions | |
idea | -0.006 |
kids | -0.006 |
do | -0.005 |
sun | -0.005 |
wind | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -6.22e-03 |
Pos logit contributions | |
otte | +0.041 |
Charl | +0.041 |
Har | +0.040 |
den | +0.040 |
ky | +0.039 |
Neg logit contributions | |
kids | -0.015 |
idea | -0.014 |
do | -0.012 |
sun | -0.011 |
friends | -0.011 |
Token | Oh |
Token ID | 5812 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
otte | +0.018 |
astically | +0.018 |
ically | +0.018 |
la | +0.017 |
den | +0.017 |
Neg logit contributions | |
kids | -0.014 |
idea | -0.013 |
sun | -0.013 |
do | -0.012 |
wind | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Charl | +0.037 |
otte | +0.036 |
Har | +0.035 |
May | +0.034 |
ky | +0.034 |
Neg logit contributions | |
idea | -0.031 |
kids | -0.030 |
do | -0.027 |
sun | -0.026 |
wind | -0.025 |
Token | I |
Token ID | 314 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Charl | +0.054 |
otte | +0.053 |
May | +0.050 |
Alexa | +0.050 |
Maya | +0.049 |
Neg logit contributions | |
idea | -0.036 |
kids | -0.035 |
sun | -0.030 |
wind | -0.029 |
oops | -0.029 |
Token | love |
Token ID | 1842 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.023 |
Har | +0.022 |
ky | +0.022 |
May | +0.022 |
Neg logit contributions | |
kids | -0.014 |
idea | -0.013 |
sun | -0.013 |
wind | -0.012 |
choices | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
ically | +0.038 |
Charl | +0.038 |
Har | +0.037 |
otte | +0.037 |
astically | +0.037 |
Neg logit contributions | |
kids | -0.016 |
friends | -0.013 |
sun | -0.013 |
idea | -0.013 |
do | -0.013 |
Token | ," |
Token ID | 553 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
Charl | +0.004 |
Har | +0.004 |
Simon | +0.004 |
April | +0.004 |
otte | +0.003 |
Neg logit contributions | |
idea | -0.001 |
kids | -0.001 |
do | -0.001 |
of | -0.001 |
friends | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
otte | +0.140 |
Charl | +0.140 |
May | +0.132 |
Har | +0.132 |
Alexa | +0.132 |
Neg logit contributions | |
idea | -0.068 |
kids | -0.066 |
sun | -0.054 |
do | -0.054 |
wind | -0.052 |
Token | Ruby |
Token ID | 10888 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Charl | +0.077 |
otte | +0.076 |
astically | +0.074 |
Har | +0.073 |
ky | +0.073 |
Neg logit contributions | |
idea | -0.068 |
kids | -0.067 |
do | -0.060 |
sun | -0.059 |
friends | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Charl | +0.028 |
Har | +0.027 |
otte | +0.027 |
astically | +0.026 |
Jessica | +0.026 |
Neg logit contributions | |
idea | -0.012 |
kids | -0.012 |
friends | -0.010 |
do | -0.010 |
noise | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
otte | +0.025 |
Charl | +0.024 |
la | +0.024 |
ky | +0.024 |
den | +0.024 |
Neg logit contributions | |
kids | -0.009 |
idea | -0.008 |
do | -0.007 |
sun | -0.007 |
noise | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
otte | +0.001 |
Charl | +0.001 |
Har | +0.001 |
astically | +0.001 |
la | +0.001 |
Neg logit contributions | |
kids | -0.001 |
idea | -0.001 |
do | -0.001 |
sun | -0.001 |
wind | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
otte | +0.033 |
Charl | +0.033 |
ky | +0.031 |
Har | +0.031 |
astically | +0.031 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
do | -0.013 |
sun | -0.013 |
friends | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
work | +0.035 |
otte | +0.034 |
den | +0.034 |
astically | +0.033 |
ically | +0.033 |
Neg logit contributions | |
kids | -0.036 |
idea | -0.033 |
do | -0.032 |
friends | -0.030 |
sun | -0.030 |
Token | Sure |
Token ID | 19457 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
otte | +0.016 |
ically | +0.016 |
ky | +0.016 |
astically | +0.016 |
Smith | +0.016 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.007 |
do | -0.007 |
sun | -0.007 |
wind | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
idea | +0.004 |
kids | +0.004 |
do | +0.003 |
sun | +0.003 |
wind | +0.003 |
Neg logit contributions | |
Charl | -0.004 |
otte | -0.004 |
Har | -0.004 |
May | -0.004 |
ky | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
otte | +0.051 |
Charl | +0.051 |
May | +0.050 |
Smith | +0.048 |
Maya | +0.047 |
Neg logit contributions | |
idea | -0.036 |
kids | -0.031 |
oops | -0.028 |
urge | -0.028 |
sun | -0.028 |
Token | ," |
Token ID | 553 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
do | +0.004 |
friends | +0.004 |
sun | +0.004 |
Neg logit contributions | |
Charl | -0.007 |
otte | -0.007 |
Har | -0.007 |
astically | -0.006 |
May | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Charl | +0.148 |
otte | +0.147 |
Har | +0.142 |
May | +0.140 |
ky | +0.140 |
Neg logit contributions | |
idea | -0.061 |
kids | -0.059 |
do | -0.048 |
sun | -0.047 |
wind | -0.045 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
Charl | +0.070 |
otte | +0.068 |
astically | +0.067 |
ically | +0.066 |
den | +0.066 |
Neg logit contributions | |
kids | -0.042 |
idea | -0.040 |
do | -0.034 |
friends | -0.034 |
sun | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Charl | +0.020 |
otte | +0.019 |
astically | +0.019 |
Har | +0.019 |
ically | +0.018 |
Neg logit contributions | |
kids | -0.010 |
idea | -0.009 |
do | -0.007 |
friends | -0.007 |
sun | -0.007 |
Token | Johnson |
Token ID | 5030 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
otte | +0.010 |
Charl | +0.010 |
den | +0.009 |
Har | +0.009 |
ky | +0.009 |
Neg logit contributions | |
kids | -0.015 |
idea | -0.015 |
sun | -0.014 |
do | -0.014 |
friends | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Charl | +0.004 |
otte | +0.004 |
Har | +0.004 |
May | +0.004 |
astically | +0.004 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.002 |
friends | -0.002 |
sun | -0.002 |
Token | hurry |
Token ID | 23290 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
idea | +0.009 |
kids | +0.009 |
sun | +0.008 |
wind | +0.007 |
oops | +0.007 |
Neg logit contributions | |
otte | -0.023 |
Charl | -0.023 |
Har | -0.023 |
May | -0.022 |
astically | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Charl | +0.002 |
Beck | +0.001 |
otte | +0.001 |
Laura | +0.001 |
Gr | +0.001 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
things | -0.000 |
friends | -0.000 |
people | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Smith | +0.009 |
astically | +0.009 |
Har | +0.009 |
athan | +0.009 |
Charl | +0.008 |
Neg logit contributions | |
idea | -0.009 |
kids | -0.008 |
wind | -0.008 |
relief | -0.008 |
urge | -0.008 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
idea | +0.012 |
kids | +0.011 |
do | +0.010 |
sun | +0.010 |
wind | +0.009 |
Neg logit contributions | |
Charl | -0.016 |
otte | -0.016 |
Har | -0.015 |
ky | -0.015 |
May | -0.015 |
Token | their |
Token ID | 511 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Charl | +0.027 |
otte | +0.026 |
Har | +0.025 |
ky | +0.025 |
May | +0.024 |
Neg logit contributions | |
idea | -0.025 |
kids | -0.024 |
do | -0.022 |
sun | -0.021 |
wind | -0.021 |
Token | tr |
Token ID | 491 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
idea | +0.000 |
kids | +0.000 |
do | +0.000 |
sun | +0.000 |
friends | +0.000 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
May | -0.001 |
ky | -0.001 |
Token | unks |
Token ID | 14125 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
Charl | +0.067 |
otte | +0.066 |
May | +0.061 |
Har | +0.061 |
ically | +0.058 |
Neg logit contributions | |
idea | -0.139 |
kids | -0.138 |
do | -0.126 |
friends | -0.125 |
sun | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Beck | +0.006 |
April | +0.006 |
Charl | +0.006 |
Jessica | +0.006 |
otte | +0.005 |
Neg logit contributions | |
kids | -0.002 |
of | -0.001 |
idea | -0.001 |
do | -0.001 |
sun | -0.001 |
Token | set |
Token ID | 900 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Charl | +0.007 |
otte | +0.007 |
Har | +0.007 |
ky | +0.007 |
May | +0.007 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
sun | -0.004 |
wind | -0.004 |
Token | off |
Token ID | 572 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
otte | +0.005 |
Charl | +0.005 |
Har | +0.005 |
May | +0.005 |
ky | +0.005 |
Neg logit contributions | |
idea | -0.006 |
kids | -0.006 |
do | -0.005 |
sun | -0.005 |
wind | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
friends | +0.002 |
of | +0.002 |
do | +0.001 |
Neg logit contributions | |
Charl | -0.004 |
otte | -0.004 |
May | -0.004 |
Simon | -0.004 |
Jason | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.017 |
Har | +0.016 |
May | +0.016 |
ky | +0.015 |
Neg logit contributions | |
idea | -0.024 |
kids | -0.024 |
do | -0.021 |
sun | -0.021 |
wind | -0.021 |
Token | It |
Token ID | 1026 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
otte | +0.010 |
ically | +0.010 |
ky | +0.010 |
astically | +0.010 |
den | +0.010 |
Neg logit contributions | |
kids | -0.005 |
do | -0.005 |
sun | -0.005 |
idea | -0.005 |
wind | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
otte | +0.006 |
Charl | +0.006 |
Har | +0.006 |
side | +0.006 |
ky | +0.005 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
do | -0.002 |
noise | -0.002 |
friends | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
otte | +0.035 |
Charl | +0.033 |
ically | +0.033 |
Har | +0.033 |
astically | +0.033 |
Neg logit contributions | |
idea | -0.017 |
kids | -0.017 |
sun | -0.016 |
do | -0.015 |
friends | -0.015 |
Token | mask |
Token ID | 9335 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
otte | +0.051 |
astically | +0.048 |
la | +0.048 |
ically | +0.047 |
Charl | +0.047 |
Neg logit contributions | |
idea | -0.025 |
do | -0.022 |
kids | -0.021 |
sun | -0.021 |
noise | -0.020 |
Token | ," |
Token ID | 553 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
idea | +0.003 |
do | +0.002 |
kids | +0.002 |
of | +0.002 |
noise | +0.002 |
Neg logit contributions | |
Charl | -0.005 |
otte | -0.005 |
Har | -0.005 |
Simon | -0.004 |
Beck | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Charl | +0.120 |
otte | +0.120 |
Alexa | +0.116 |
May | +0.113 |
April | +0.111 |
Neg logit contributions | |
idea | -0.083 |
kids | -0.081 |
oops | -0.069 |
sun | -0.069 |
wind | -0.068 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Charl | +0.036 |
otte | +0.036 |
Har | +0.034 |
May | +0.034 |
ky | +0.034 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
do | -0.013 |
sun | -0.012 |
wind | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.023 |
Har | +0.022 |
May | +0.021 |
ically | +0.021 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.007 |
do | -0.006 |
sun | -0.005 |
friends | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.004 |
do | +0.004 |
friends | +0.004 |
of | +0.004 |
Neg logit contributions | |
Charl | -0.013 |
Har | -0.012 |
otte | -0.012 |
April | -0.012 |
Ba | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Charl | +0.044 |
otte | +0.043 |
May | +0.041 |
Alexa | +0.041 |
Har | +0.040 |
Neg logit contributions | |
idea | -0.031 |
kids | -0.030 |
do | -0.026 |
wind | -0.025 |
expect | -0.025 |
Token | decided |
Token ID | 3066 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
kids | +0.017 |
idea | +0.016 |
do | +0.014 |
friends | +0.013 |
sun | +0.013 |
Neg logit contributions | |
Charl | -0.032 |
otte | -0.032 |
Har | -0.031 |
ically | -0.031 |
May | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
kids | +0.016 |
do | +0.015 |
things | +0.013 |
people | +0.013 |
friends | +0.013 |
Neg logit contributions | |
Charl | -0.033 |
ky | -0.031 |
otte | -0.031 |
ifying | -0.031 |
ically | -0.031 |
Token | jump |
Token ID | 4391 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
sun | +0.003 |
wind | +0.002 |
do | +0.002 |
Neg logit contributions | |
Charl | -0.006 |
otte | -0.006 |
Har | -0.006 |
astically | -0.006 |
May | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
otte | +0.030 |
Charl | +0.030 |
Har | +0.030 |
Jessica | +0.029 |
Jason | +0.029 |
Neg logit contributions | |
idea | -0.010 |
do | -0.010 |
too | -0.009 |
of | -0.009 |
kids | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
otte | +0.041 |
Charl | +0.041 |
ically | +0.040 |
Har | +0.040 |
astically | +0.040 |
Neg logit contributions | |
kids | -0.011 |
idea | -0.009 |
do | -0.008 |
things | -0.008 |
sun | -0.008 |
Token | tr |
Token ID | 491 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
Charl | +0.042 |
otte | +0.042 |
Har | +0.040 |
May | +0.040 |
ky | +0.040 |
Neg logit contributions | |
idea | -0.027 |
kids | -0.027 |
do | -0.023 |
sun | -0.022 |
wind | -0.022 |
Token | amp |
Token ID | 696 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Charl | +0.075 |
otte | +0.075 |
Har | +0.069 |
May | +0.067 |
ky | +0.067 |
Neg logit contributions | |
idea | -0.133 |
kids | -0.132 |
do | -0.121 |
sun | -0.119 |
wind | -0.117 |
Token | oline |
Token ID | 14453 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
otte | +0.036 |
Charl | +0.036 |
Har | +0.035 |
May | +0.033 |
Simon | +0.032 |
Neg logit contributions | |
kids | -0.038 |
idea | -0.037 |
sun | -0.034 |
do | -0.033 |
wind | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
Charl | +0.016 |
Har | +0.016 |
otte | +0.016 |
Ba | +0.015 |
Jason | +0.015 |
Neg logit contributions | |
idea | -0.005 |
do | -0.005 |
kids | -0.005 |
of | -0.004 |
too | -0.004 |
Token | but |
Token ID | 475 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
kids | +0.020 |
idea | +0.020 |
do | +0.017 |
sun | +0.016 |
wind | +0.016 |
Neg logit contributions | |
otte | -0.042 |
Charl | -0.042 |
Har | -0.040 |
May | -0.039 |
ky | -0.039 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.015 |
do | +0.012 |
sun | +0.012 |
wind | +0.011 |
Neg logit contributions | |
Charl | -0.031 |
otte | -0.031 |
Har | -0.030 |
May | -0.029 |
ky | -0.029 |
Token | Let |
Token ID | 5756 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
do | +0.003 |
sun | +0.003 |
wind | +0.003 |
Neg logit contributions | |
onna | -0.005 |
astically | -0.005 |
otte | -0.005 |
work | -0.005 |
ically | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
idea | +0.031 |
kids | +0.029 |
sun | +0.026 |
do | +0.025 |
oops | +0.025 |
Neg logit contributions | |
Charl | -0.033 |
otte | -0.032 |
Har | -0.031 |
May | -0.030 |
astically | -0.030 |
Token | take |
Token ID | 1011 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
sun | +0.004 |
wind | +0.003 |
do | +0.003 |
Neg logit contributions | |
Charl | -0.016 |
otte | -0.016 |
Har | -0.015 |
May | -0.015 |
astically | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
kids | +0.019 |
idea | +0.018 |
sun | +0.016 |
friends | +0.016 |
do | +0.016 |
Neg logit contributions | |
otte | -0.028 |
Charl | -0.028 |
astically | -0.027 |
ically | -0.027 |
Har | -0.027 |
Token | taxi |
Token ID | 17536 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
do | +0.002 |
sun | +0.002 |
wind | +0.002 |
Neg logit contributions | |
Charl | -0.004 |
otte | -0.003 |
Har | -0.003 |
ky | -0.003 |
May | -0.003 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
idea | +0.008 |
kids | +0.008 |
do | +0.007 |
sun | +0.006 |
wind | +0.006 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
Har | -0.010 |
May | -0.010 |
Simon | -0.010 |
Token | suggested |
Token ID | 5220 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
otte | +0.131 |
Charl | +0.131 |
Har | +0.127 |
May | +0.125 |
ky | +0.124 |
Neg logit contributions | |
idea | -0.076 |
kids | -0.072 |
sun | -0.062 |
do | -0.062 |
wind | -0.060 |
Token | Marco |
Token ID | 16556 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Charl | +0.083 |
ically | +0.081 |
astically | +0.081 |
ky | +0.079 |
any | +0.078 |
Neg logit contributions | |
kids | -0.046 |
idea | -0.038 |
do | -0.038 |
friends | -0.036 |
children | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
idea | +0.012 |
kids | +0.011 |
do | +0.010 |
friends | +0.010 |
of | +0.009 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.022 |
Har | -0.022 |
May | -0.021 |
astically | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
otte | +0.042 |
Charl | +0.042 |
astically | +0.041 |
ky | +0.040 |
work | +0.040 |
Neg logit contributions | |
kids | -0.027 |
idea | -0.026 |
sun | -0.022 |
do | -0.022 |
friends | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
Charl | +0.017 |
otte | +0.017 |
Har | +0.017 |
May | +0.016 |
ky | +0.016 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
do | -0.009 |
sun | -0.009 |
wind | -0.009 |
Token | Please |
Token ID | 5492 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
Charl | +0.000 |
otte | +0.000 |
Har | +0.000 |
ky | +0.000 |
May | +0.000 |
Neg logit contributions | |
idea | -0.000 |
kids | -0.000 |
do | -0.000 |
sun | -0.000 |
wind | -0.000 |
Token | don |
Token ID | 836 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Charl | +0.042 |
otte | +0.042 |
Har | +0.040 |
May | +0.040 |
ky | +0.040 |
Neg logit contributions | |
idea | -0.025 |
kids | -0.025 |
do | -0.022 |
sun | -0.021 |
wind | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Charl | +0.005 |
otte | +0.005 |
Har | +0.005 |
May | +0.005 |
Smith | +0.005 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
choices | -0.010 |
promises | -0.010 |
friends | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Charl | +0.027 |
otte | +0.027 |
Har | +0.026 |
May | +0.025 |
ky | +0.025 |
Neg logit contributions | |
idea | -0.012 |
kids | -0.011 |
do | -0.009 |
sun | -0.009 |
wind | -0.009 |
Token | scared |
Token ID | 12008 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Charl | +0.042 |
otte | +0.042 |
Har | +0.040 |
May | +0.039 |
ky | +0.039 |
Neg logit contributions | |
idea | -0.020 |
kids | -0.019 |
do | -0.016 |
sun | -0.016 |
wind | -0.015 |
Token | ," |
Token ID | 553 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
kids | +0.009 |
idea | +0.008 |
do | +0.007 |
wind | +0.007 |
of | +0.007 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.015 |
Har | -0.015 |
May | -0.014 |
astically | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
otte | +0.130 |
Charl | +0.128 |
Har | +0.124 |
ky | +0.124 |
May | +0.123 |
Neg logit contributions | |
idea | -0.075 |
kids | -0.071 |
sun | -0.060 |
do | -0.059 |
wind | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Charl | +0.106 |
otte | +0.105 |
Har | +0.101 |
May | +0.100 |
astically | +0.100 |
Neg logit contributions | |
idea | -0.057 |
kids | -0.057 |
do | -0.048 |
sun | -0.047 |
wind | -0.045 |
Token | lion |
Token ID | 18744 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Smith | +0.019 |
Charl | +0.019 |
May | +0.019 |
otte | +0.019 |
Har | +0.019 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.012 |
oops | -0.012 |
expect | -0.011 |
promises | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
idea | +0.004 |
kids | +0.004 |
do | +0.003 |
friends | +0.003 |
sun | +0.003 |
Neg logit contributions | |
Charl | -0.006 |
otte | -0.005 |
Har | -0.005 |
May | -0.005 |
ky | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.023 |
Har | +0.022 |
May | +0.022 |
ky | +0.022 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.014 |
do | -0.012 |
sun | -0.011 |
wind | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Charl | +0.045 |
otte | +0.044 |
Har | +0.042 |
May | +0.042 |
Jessica | +0.042 |
Neg logit contributions | |
idea | -0.042 |
kids | -0.041 |
do | -0.037 |
friends | -0.035 |
wind | -0.035 |
Token | Let |
Token ID | 5756 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
otte | +0.013 |
Charl | +0.013 |
ically | +0.013 |
astically | +0.012 |
Alexa | +0.012 |
Neg logit contributions | |
kids | -0.010 |
sun | -0.009 |
do | -0.008 |
idea | -0.008 |
wind | -0.008 |
Token | 's |
Token ID | 338 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
idea | +0.025 |
kids | +0.025 |
do | +0.022 |
sun | +0.021 |
wind | +0.020 |
Neg logit contributions | |
Charl | -0.038 |
otte | -0.038 |
Har | -0.036 |
ky | -0.036 |
May | -0.035 |
Token | weigh |
Token ID | 10164 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.002 |
ky | -0.002 |
May | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
kids | +0.010 |
idea | +0.009 |
do | +0.008 |
friends | +0.008 |
things | +0.008 |
Neg logit contributions | |
Charl | -0.028 |
otte | -0.027 |
Har | -0.027 |
astically | -0.026 |
ically | -0.026 |
Token | ," |
Token ID | 553 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
idea | +0.004 |
kids | +0.004 |
do | +0.004 |
friends | +0.003 |
of | +0.003 |
Neg logit contributions | |
Charl | -0.009 |
Har | -0.009 |
otte | -0.009 |
Simon | -0.009 |
Acc | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
otte | +0.126 |
Charl | +0.125 |
Har | +0.120 |
May | +0.119 |
ky | +0.118 |
Neg logit contributions | |
idea | -0.078 |
kids | -0.076 |
do | -0.065 |
sun | -0.064 |
wind | -0.063 |
Token | said |
Token ID | 531 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
otte | +0.051 |
Charl | +0.051 |
Har | +0.049 |
ky | +0.048 |
May | +0.048 |
Neg logit contributions | |
idea | -0.020 |
kids | -0.020 |
sun | -0.016 |
do | -0.016 |
wind | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Charl | +0.009 |
Har | +0.008 |
otte | +0.008 |
ky | +0.008 |
April | +0.008 |
Neg logit contributions | |
idea | -0.004 |
kids | -0.003 |
do | -0.003 |
of | -0.003 |
noise | -0.003 |
Token | Lisa |
Token ID | 15378 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
do | +0.004 |
people | +0.003 |
noise | +0.003 |
Neg logit contributions | |
Charl | -0.007 |
ically | -0.007 |
otte | -0.007 |
astically | -0.007 |
ky | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
Charl | +0.025 |
Har | +0.023 |
otte | +0.023 |
Simon | +0.023 |
April | +0.022 |
Neg logit contributions | |
idea | -0.009 |
kids | -0.008 |
do | -0.007 |
friends | -0.007 |
of | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
kids | +0.005 |
idea | +0.004 |
do | +0.004 |
sun | +0.003 |
friends | +0.003 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.015 |
ky | -0.014 |
Har | -0.014 |
ically | -0.014 |
Token | did |
Token ID | 750 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
Charl | +0.008 |
otte | +0.008 |
Har | +0.008 |
ky | +0.008 |
May | +0.008 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.007 |
sun | -0.006 |
choices | -0.006 |
oops | -0.006 |
Token | not |
Token ID | 407 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
idea | +0.021 |
kids | +0.021 |
sun | +0.018 |
wind | +0.018 |
do | +0.017 |
Neg logit contributions | |
otte | -0.026 |
Charl | -0.025 |
Har | -0.025 |
May | -0.024 |
astically | -0.024 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
otte | +0.041 |
Charl | +0.041 |
Har | +0.040 |
ky | +0.040 |
Smith | +0.039 |
Neg logit contributions | |
idea | -0.017 |
kids | -0.016 |
sun | -0.014 |
wind | -0.013 |
friends | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.022 |
Har | +0.022 |
Jessica | +0.022 |
May | +0.022 |
Neg logit contributions | |
kids | -0.009 |
idea | -0.009 |
do | -0.008 |
things | -0.007 |
sun | -0.007 |
Token | tr |
Token ID | 491 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
Charl | +0.025 |
otte | +0.025 |
Har | +0.024 |
May | +0.024 |
astically | +0.024 |
Neg logit contributions | |
idea | -0.022 |
kids | -0.021 |
do | -0.019 |
sun | -0.019 |
wind | -0.018 |
Token | uffle |
Token ID | 18137 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Charl | +0.087 |
otte | +0.087 |
May | +0.084 |
Har | +0.082 |
ically | +0.081 |
Neg logit contributions | |
idea | -0.111 |
kids | -0.110 |
do | -0.100 |
sun | -0.098 |
friends | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Charl | +0.024 |
Har | +0.023 |
otte | +0.023 |
May | +0.022 |
Jessica | +0.022 |
Neg logit contributions | |
idea | -0.012 |
kids | -0.012 |
do | -0.011 |
sun | -0.009 |
people | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
idea | +0.018 |
kids | +0.017 |
do | +0.016 |
sun | +0.015 |
wind | +0.015 |
Neg logit contributions | |
Charl | -0.019 |
otte | -0.019 |
Har | -0.018 |
May | -0.018 |
ky | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.018 |
Har | +0.017 |
May | +0.017 |
Smith | +0.017 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
do | -0.009 |
sun | -0.009 |
wind | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Charl | +0.009 |
otte | +0.008 |
Har | +0.008 |
May | +0.008 |
ky | +0.008 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.008 |
do | -0.007 |
sun | -0.007 |
wind | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
otte | +0.008 |
Charl | +0.008 |
Har | +0.008 |
May | +0.008 |
astically | +0.008 |
Neg logit contributions | |
idea | -0.006 |
kids | -0.006 |
do | -0.005 |
sun | -0.005 |
friends | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Charl | +0.045 |
otte | +0.043 |
Har | +0.042 |
Alexa | +0.041 |
Smith | +0.041 |
Neg logit contributions | |
idea | -0.039 |
kids | -0.038 |
do | -0.033 |
friends | -0.032 |
wind | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
Charl | +0.015 |
otte | +0.015 |
Har | +0.014 |
May | +0.014 |
Jessica | +0.014 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
choices | -0.010 |
wind | -0.009 |
urge | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.023 |
Har | +0.022 |
May | +0.021 |
ky | +0.021 |
Neg logit contributions | |
idea | -0.029 |
kids | -0.029 |
do | -0.026 |
sun | -0.025 |
wind | -0.025 |
Token | Hello |
Token ID | 15496 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
otte | +0.012 |
astically | +0.012 |
ically | +0.012 |
Charl | +0.012 |
den | +0.012 |
Neg logit contributions | |
kids | -0.010 |
idea | -0.009 |
sun | -0.009 |
do | -0.009 |
wind | -0.009 |
Token | ," |
Token ID | 553 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
otte | +0.055 |
Charl | +0.055 |
Har | +0.051 |
Smith | +0.051 |
May | +0.051 |
Neg logit contributions | |
idea | -0.048 |
kids | -0.046 |
do | -0.041 |
sun | -0.040 |
wind | -0.040 |
Token | said |
Token ID | 531 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
otte | +0.133 |
Charl | +0.133 |
Alexa | +0.128 |
Har | +0.126 |
May | +0.125 |
Neg logit contributions | |
idea | -0.070 |
kids | -0.067 |
oops | -0.055 |
sun | -0.055 |
do | -0.054 |
Token | Louise |
Token ID | 31774 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
Charl | +0.083 |
otte | +0.083 |
Har | +0.078 |
May | +0.077 |
ky | +0.077 |
Neg logit contributions | |
idea | -0.072 |
kids | -0.071 |
do | -0.063 |
sun | -0.062 |
wind | -0.060 |
Token | with |
Token ID | 351 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Charl | +0.026 |
otte | +0.025 |
Har | +0.025 |
Jessica | +0.024 |
astically | +0.024 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
friends | -0.009 |
do | -0.009 |
noise | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Charl | +0.006 |
Har | +0.006 |
otte | +0.005 |
May | +0.005 |
ky | +0.005 |
Neg logit contributions | |
kids | -0.007 |
idea | -0.007 |
oops | -0.006 |
choices | -0.006 |
friends | -0.006 |
Token | smile |
Token ID | 8212 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
idea | +0.032 |
kids | +0.031 |
do | +0.026 |
sun | +0.025 |
wind | +0.024 |
Neg logit contributions | |
otte | -0.067 |
Charl | -0.067 |
Har | -0.064 |
ky | -0.064 |
May | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
idea | +0.007 |
kids | +0.007 |
do | +0.006 |
sun | +0.006 |
friends | +0.006 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
Har | -0.010 |
May | -0.010 |
ky | -0.010 |
Token | hop |
Token ID | 1725 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.003 |
May | -0.003 |
ky | -0.003 |
Token | around |
Token ID | 1088 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Charl | +0.033 |
otte | +0.032 |
Har | +0.031 |
ky | +0.031 |
May | +0.030 |
Neg logit contributions | |
idea | -0.024 |
kids | -0.024 |
do | -0.020 |
sun | -0.020 |
wind | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
otte | +0.009 |
Charl | +0.009 |
la | +0.009 |
Har | +0.009 |
astically | +0.009 |
Neg logit contributions | |
kids | -0.005 |
idea | -0.005 |
do | -0.004 |
sun | -0.004 |
friends | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
otte | +0.071 |
Charl | +0.071 |
astically | +0.067 |
May | +0.067 |
Har | +0.067 |
Neg logit contributions | |
kids | -0.033 |
idea | -0.031 |
do | -0.027 |
sun | -0.027 |
friends | -0.025 |
Token | tr |
Token ID | 491 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Charl | +0.015 |
otte | +0.015 |
May | +0.015 |
Har | +0.015 |
la | +0.015 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.007 |
friends | -0.007 |
sun | -0.006 |
do | -0.006 |
Token | amp |
Token ID | 696 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
otte | +0.078 |
Charl | +0.078 |
Har | +0.071 |
May | +0.071 |
ky | +0.070 |
Neg logit contributions | |
idea | -0.127 |
kids | -0.126 |
do | -0.115 |
sun | -0.114 |
friends | -0.111 |
Token | oline |
Token ID | 14453 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
otte | +0.036 |
Charl | +0.035 |
Har | +0.033 |
May | +0.033 |
astically | +0.032 |
Neg logit contributions | |
kids | -0.042 |
idea | -0.042 |
sun | -0.038 |
do | -0.037 |
wind | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Charl | +0.072 |
otte | +0.071 |
Har | +0.068 |
May | +0.067 |
Jessica | +0.066 |
Neg logit contributions | |
kids | -0.026 |
idea | -0.025 |
do | -0.022 |
friends | -0.021 |
sun | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Charl | +0.011 |
Har | +0.011 |
Smith | +0.011 |
ky | +0.011 |
Jessica | +0.011 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.008 |
do | -0.007 |
friends | -0.007 |
wind | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
kids | +0.010 |
idea | +0.010 |
choices | +0.009 |
oops | +0.009 |
promises | +0.009 |
Neg logit contributions | |
Charl | -0.016 |
otte | -0.015 |
den | -0.015 |
ky | -0.015 |
Smith | -0.015 |
Token | going |
Token ID | 1016 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.003 |
Har | +0.003 |
May | +0.003 |
ky | +0.002 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
do | -0.002 |
sun | -0.002 |
wind | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
kids | +0.008 |
do | +0.007 |
idea | +0.007 |
friends | +0.007 |
sun | +0.007 |
Neg logit contributions | |
Charl | -0.014 |
otte | -0.013 |
Laura | -0.013 |
ically | -0.013 |
Har | -0.013 |
Token | get |
Token ID | 651 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
idea | +0.009 |
kids | +0.009 |
do | +0.008 |
sun | +0.007 |
friends | +0.007 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.023 |
Har | -0.022 |
ky | -0.022 |
May | -0.022 |
Token | some |
Token ID | 617 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ically | +0.020 |
Charl | +0.019 |
astically | +0.019 |
otte | +0.018 |
side | +0.018 |
Neg logit contributions | |
kids | -0.007 |
friends | -0.006 |
sun | -0.005 |
food | -0.005 |
things | -0.005 |
Token | oil |
Token ID | 3056 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Charl | +0.012 |
otte | +0.012 |
Har | +0.012 |
May | +0.012 |
ky | +0.012 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
sun | -0.004 |
wind | -0.004 |
Token | ," |
Token ID | 553 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
idea | +0.015 |
kids | +0.014 |
do | +0.012 |
of | +0.012 |
wind | +0.011 |
Neg logit contributions | |
Charl | -0.030 |
Jessica | -0.029 |
April | -0.029 |
May | -0.028 |
Laura | -0.028 |
Token | Louise |
Token ID | 31774 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Charl | +0.139 |
otte | +0.139 |
Har | +0.133 |
Alexa | +0.131 |
May | +0.131 |
Neg logit contributions | |
idea | -0.065 |
kids | -0.064 |
do | -0.051 |
sun | -0.051 |
oops | -0.050 |
Token | replied |
Token ID | 8712 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Charl | +0.060 |
otte | +0.058 |
ifying | +0.057 |
side | +0.057 |
Har | +0.057 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.012 |
do | -0.010 |
friends | -0.007 |
noise | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Charl | +0.001 |
otte | +0.001 |
Har | +0.001 |
Jessica | +0.001 |
Ba | +0.001 |
Neg logit contributions | |
idea | -0.000 |
kids | -0.000 |
friends | -0.000 |
of | -0.000 |
do | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
otte | +0.006 |
ky | +0.006 |
Charl | +0.006 |
den | +0.006 |
astically | +0.006 |
Neg logit contributions | |
kids | -0.002 |
idea | -0.002 |
sun | -0.002 |
friends | -0.001 |
do | -0.001 |
Token | My |
Token ID | 3666 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
otte | +0.008 |
Charl | +0.008 |
la | +0.008 |
ky | +0.008 |
astically | +0.008 |
Neg logit contributions | |
kids | -0.006 |
do | -0.006 |
idea | -0.005 |
sun | -0.005 |
wind | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
ky | +0.034 |
work | +0.034 |
otte | +0.033 |
astically | +0.033 |
ically | +0.033 |
Neg logit contributions | |
kids | -0.009 |
idea | -0.008 |
do | -0.008 |
friends | -0.007 |
sun | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
work | +0.026 |
Smith | +0.026 |
ky | +0.025 |
onna | +0.024 |
any | +0.024 |
Neg logit contributions | |
kids | -0.023 |
do | -0.023 |
friends | -0.020 |
idea | -0.020 |
people | -0.019 |
Token | I |
Token ID | 40 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
otte | +0.005 |
Smith | +0.005 |
astically | +0.005 |
Charl | +0.005 |
ky | +0.005 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.003 |
do | -0.003 |
sun | -0.003 |
wind | -0.003 |
Token | love |
Token ID | 1842 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
otte | +0.005 |
Charl | +0.005 |
Har | +0.004 |
ky | +0.004 |
May | +0.004 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.002 |
sun | -0.002 |
friends | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ically | +0.059 |
astically | +0.058 |
otte | +0.058 |
Charl | +0.057 |
Har | +0.057 |
Neg logit contributions | |
kids | -0.037 |
idea | -0.034 |
do | -0.033 |
friends | -0.033 |
sun | -0.031 |
Token | ," |
Token ID | 553 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Charl | +0.008 |
Har | +0.008 |
otte | +0.008 |
ically | +0.007 |
Acc | +0.007 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
friends | -0.003 |
of | -0.003 |
do | -0.003 |
Token | George |
Token ID | 4502 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Charl | +0.159 |
otte | +0.158 |
astically | +0.155 |
ically | +0.154 |
ky | +0.154 |
Neg logit contributions | |
idea | -0.048 |
kids | -0.047 |
do | -0.038 |
friends | -0.034 |
sun | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Charl | +0.116 |
otte | +0.111 |
Har | +0.110 |
ifying | +0.109 |
side | +0.107 |
Neg logit contributions | |
idea | -0.020 |
kids | -0.016 |
friends | -0.013 |
do | -0.012 |
say | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
friends | +0.002 |
of | +0.002 |
do | +0.002 |
Neg logit contributions | |
Charl | -0.005 |
Har | -0.005 |
otte | -0.005 |
astically | -0.005 |
May | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
otte | +0.009 |
Charl | +0.009 |
Har | +0.009 |
astically | +0.009 |
May | +0.009 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.007 |
do | -0.006 |
sun | -0.006 |
wind | -0.006 |
Token | smile |
Token ID | 8212 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
idea | +0.023 |
do | +0.017 |
kids | +0.017 |
sun | +0.016 |
noise | +0.015 |
Neg logit contributions | |
otte | -0.053 |
astically | -0.050 |
ky | -0.050 |
la | -0.050 |
Charl | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
Charl | +0.002 |
otte | +0.002 |
Har | +0.002 |
May | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
wind | -0.002 |
choices | -0.002 |
urge | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Charl | +0.017 |
otte | +0.017 |
Har | +0.016 |
ky | +0.015 |
May | +0.015 |
Neg logit contributions | |
idea | -0.040 |
kids | -0.039 |
sun | -0.035 |
do | -0.035 |
friends | -0.035 |
Token | Hi |
Token ID | 17250 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
otte | +0.006 |
Charl | +0.006 |
astically | +0.006 |
ically | +0.006 |
la | +0.006 |
Neg logit contributions | |
kids | -0.006 |
idea | -0.005 |
sun | -0.005 |
wind | -0.005 |
do | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Smith | +0.051 |
otte | +0.049 |
ky | +0.047 |
Avery | +0.046 |
Alexa | +0.046 |
Neg logit contributions | |
idea | -0.066 |
urge | -0.058 |
temptation | -0.058 |
relief | -0.057 |
choices | -0.057 |
Token | crab |
Token ID | 32202 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
Smith | +0.047 |
fly | +0.044 |
Claus | +0.044 |
Maya | +0.044 |
otte | +0.044 |
Neg logit contributions | |
idea | -0.058 |
choices | -0.051 |
temptation | -0.049 |
persuasion | -0.048 |
promises | -0.048 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
idea | +0.022 |
kids | +0.022 |
do | +0.019 |
sun | +0.019 |
wind | +0.019 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.023 |
Har | -0.022 |
ky | -0.022 |
May | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
otte | +0.112 |
ky | +0.111 |
Har | +0.111 |
Avery | +0.110 |
Charl | +0.110 |
Neg logit contributions | |
idea | -0.085 |
kids | -0.080 |
choices | -0.068 |
oops | -0.068 |
friends | -0.066 |
Token | T |
Token ID | 309 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Charl | +0.081 |
otte | +0.080 |
Har | +0.076 |
ky | +0.075 |
May | +0.074 |
Neg logit contributions | |
idea | -0.089 |
kids | -0.087 |
do | -0.078 |
sun | -0.076 |
wind | -0.075 |
Token | una |
Token ID | 9613 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Charl | +0.056 |
otte | +0.056 |
Har | +0.053 |
May | +0.053 |
ky | +0.052 |
Neg logit contributions | |
idea | -0.038 |
kids | -0.037 |
do | -0.032 |
sun | -0.032 |
wind | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
friends | +0.005 |
do | +0.004 |
sun | +0.004 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
Har | -0.011 |
Jessica | -0.010 |
May | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
otte | +0.027 |
Charl | +0.027 |
Har | +0.025 |
la | +0.025 |
May | +0.025 |
Neg logit contributions | |
kids | -0.012 |
idea | -0.011 |
do | -0.010 |
sun | -0.010 |
wind | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
do | +0.001 |
sun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
otte | -0.002 |
Charl | -0.002 |
ky | -0.002 |
la | -0.002 |
May | -0.002 |
Token | That |
Token ID | 2504 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
otte | +0.023 |
ically | +0.023 |
ky | +0.022 |
Charl | +0.022 |
astically | +0.022 |
Neg logit contributions | |
kids | -0.010 |
do | -0.009 |
sun | -0.008 |
idea | -0.008 |
wind | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
otte | +0.057 |
Charl | +0.057 |
Har | +0.054 |
May | +0.054 |
ky | +0.053 |
Neg logit contributions | |
idea | -0.034 |
kids | -0.033 |
do | -0.029 |
sun | -0.028 |
wind | -0.027 |
Token | my |
Token ID | 616 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Charl | +0.045 |
otte | +0.045 |
Har | +0.042 |
Smith | +0.042 |
Alexa | +0.041 |
Neg logit contributions | |
idea | -0.061 |
kids | -0.060 |
do | -0.054 |
sun | -0.053 |
wind | -0.053 |
Token | son |
Token ID | 3367 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Charl | +0.070 |
otte | +0.070 |
Har | +0.067 |
May | +0.067 |
den | +0.065 |
Neg logit contributions | |
idea | -0.030 |
kids | -0.028 |
do | -0.025 |
sun | -0.024 |
friends | -0.023 |
Token | ," |
Token ID | 553 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Charl | +0.048 |
otte | +0.046 |
Har | +0.045 |
side | +0.044 |
May | +0.043 |
Neg logit contributions | |
idea | -0.027 |
kids | -0.027 |
do | -0.025 |
friends | -0.023 |
sun | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
otte | +0.125 |
Charl | +0.124 |
Har | +0.122 |
ky | +0.118 |
Smith | +0.117 |
Neg logit contributions | |
kids | -0.074 |
idea | -0.074 |
do | -0.061 |
sun | -0.061 |
wind | -0.060 |
Token | his |
Token ID | 465 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Charl | +0.064 |
otte | +0.062 |
May | +0.059 |
astically | +0.059 |
Har | +0.058 |
Neg logit contributions | |
idea | -0.051 |
kids | -0.049 |
friends | -0.043 |
do | -0.043 |
sun | -0.043 |
Token | dad |
Token ID | 9955 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
Charl | +0.033 |
side | +0.031 |
Gr | +0.030 |
otte | +0.030 |
ky | +0.030 |
Neg logit contributions | |
kids | -0.014 |
idea | -0.013 |
friends | -0.011 |
children | -0.010 |
do | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
Charl | +0.039 |
otte | +0.038 |
Har | +0.037 |
May | +0.036 |
astically | +0.035 |
Neg logit contributions | |
idea | -0.023 |
kids | -0.022 |
do | -0.020 |
friends | -0.018 |
sun | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Charl | +0.024 |
otte | +0.024 |
la | +0.023 |
Har | +0.023 |
den | +0.023 |
Neg logit contributions | |
kids | -0.016 |
idea | -0.015 |
do | -0.015 |
noise | -0.014 |
sun | -0.014 |
Token | yourself |
Token ID | 3511 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Charl | +0.014 |
otte | +0.014 |
Har | +0.013 |
ically | +0.013 |
astically | +0.013 |
Neg logit contributions | |
kids | -0.009 |
idea | -0.008 |
do | -0.008 |
things | -0.007 |
noise | -0.007 |
Token | before |
Token ID | 878 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Charl | +0.014 |
April | +0.014 |
Har | +0.013 |
Simon | +0.013 |
Beck | +0.013 |
Neg logit contributions | |
kids | -0.006 |
do | -0.006 |
idea | -0.005 |
of | -0.005 |
noise | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
kids | +0.022 |
idea | +0.021 |
do | +0.018 |
sun | +0.018 |
wind | +0.017 |
Neg logit contributions | |
Charl | -0.045 |
otte | -0.044 |
Har | -0.043 |
ky | -0.043 |
den | -0.043 |
Token | go |
Token ID | 467 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
idea | +0.009 |
kids | +0.009 |
do | +0.007 |
sun | +0.007 |
wind | +0.006 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.027 |
Har | -0.026 |
ky | -0.026 |
May | -0.026 |
Token | home |
Token ID | 1363 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
friends | +0.004 |
do | +0.004 |
sun | +0.004 |
Neg logit contributions | |
Charl | -0.008 |
otte | -0.008 |
Laura | -0.008 |
Har | -0.008 |
Jessica | -0.008 |
Token | ," |
Token ID | 553 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
kids | +0.014 |
idea | +0.014 |
friends | +0.012 |
of | +0.012 |
do | +0.012 |
Neg logit contributions | |
Charl | -0.035 |
Simon | -0.032 |
Har | -0.032 |
ically | -0.032 |
April | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
otte | +0.114 |
Alexa | +0.112 |
Avery | +0.112 |
Har | +0.111 |
ky | +0.109 |
Neg logit contributions | |
idea | -0.074 |
kids | -0.071 |
oops | -0.063 |
expect | -0.061 |
urge | -0.060 |
Token | mother |
Token ID | 2802 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
expect | +0.003 |
do | +0.003 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.010 |
la | -0.009 |
Har | -0.009 |
Charl | -0.009 |
May | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
sun | +0.003 |
do | +0.002 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.005 |
Charl | -0.005 |
ky | -0.005 |
den | -0.005 |
la | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.015 |
do | +0.013 |
friends | +0.013 |
noise | +0.012 |
Neg logit contributions | |
Charl | -0.035 |
Har | -0.033 |
otte | -0.033 |
May | -0.032 |
April | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Charl | +0.042 |
otte | +0.042 |
Har | +0.040 |
May | +0.039 |
ky | +0.039 |
Neg logit contributions | |
idea | -0.041 |
kids | -0.040 |
do | -0.036 |
sun | -0.035 |
wind | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
otte | +0.013 |
Charl | +0.013 |
ky | +0.013 |
den | +0.013 |
astically | +0.013 |
Neg logit contributions | |
kids | -0.005 |
idea | -0.005 |
sun | -0.004 |
do | -0.004 |
friends | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
do | +0.004 |
sun | +0.004 |
friends | +0.003 |
Neg logit contributions | |
Charl | -0.009 |
otte | -0.009 |
ky | -0.009 |
Har | -0.009 |
astically | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
kids | +0.002 |
idea | +0.001 |
do | +0.001 |
sun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
ky | -0.003 |
Smith | -0.003 |
work | -0.003 |
Token | Sure |
Token ID | 19457 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
idea | +0.030 |
kids | +0.029 |
do | +0.026 |
sun | +0.025 |
wind | +0.025 |
Neg logit contributions | |
Charl | -0.040 |
otte | -0.040 |
Har | -0.038 |
ky | -0.038 |
May | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
idea | +0.018 |
kids | +0.018 |
sun | +0.016 |
do | +0.016 |
wind | +0.015 |
Neg logit contributions | |
otte | -0.018 |
Charl | -0.018 |
Smith | -0.017 |
May | -0.017 |
Har | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
otte | +0.009 |
Maya | +0.009 |
May | +0.009 |
Avery | +0.008 |
Alexa | +0.008 |
Neg logit contributions | |
idea | -0.009 |
oops | -0.008 |
urge | -0.008 |
acquaintance | -0.007 |
add | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
idea | +0.049 |
eal | +0.046 |
oops | +0.044 |
kids | +0.044 |
relief | +0.042 |
Neg logit contributions | |
otte | -0.049 |
Smith | -0.045 |
astically | -0.045 |
work | -0.045 |
fly | -0.044 |
Token | careful |
Token ID | 8161 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
expect | +0.005 |
urge | +0.005 |
Neg logit contributions | |
Charl | -0.010 |
otte | -0.010 |
May | -0.010 |
Har | -0.010 |
ky | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
kids | +0.005 |
idea | +0.005 |
do | +0.004 |
friends | +0.004 |
wind | +0.004 |
Neg logit contributions | |
Charl | -0.008 |
otte | -0.008 |
Har | -0.007 |
May | -0.007 |
ky | -0.007 |
Token | It |
Token ID | 632 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
idea | +0.029 |
kids | +0.023 |
friends | +0.022 |
expect | +0.022 |
y | +0.022 |
Neg logit contributions | |
Charl | -0.028 |
Smith | -0.028 |
astically | -0.028 |
May | -0.028 |
otte | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
idea | +0.012 |
kids | +0.011 |
relief | +0.011 |
sun | +0.010 |
expect | +0.010 |
Neg logit contributions | |
astically | -0.012 |
fly | -0.012 |
otte | -0.012 |
la | -0.012 |
Charl | -0.012 |
Token | them |
Token ID | 606 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
Charl | +0.020 |
otte | +0.019 |
astically | +0.019 |
Har | +0.019 |
ically | +0.019 |
Neg logit contributions | |
kids | -0.008 |
idea | -0.007 |
do | -0.006 |
sun | -0.006 |
friends | -0.006 |
Token | back |
Token ID | 736 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.002 |
Har | +0.002 |
Jessica | +0.002 |
den | +0.002 |
Neg logit contributions | |
kids | -0.001 |
idea | -0.001 |
friends | -0.001 |
sun | -0.001 |
do | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
kids | +0.019 |
friends | +0.019 |
sun | +0.016 |
idea | +0.014 |
of | +0.014 |
Neg logit contributions | |
Charl | -0.071 |
Har | -0.069 |
otte | -0.069 |
Jessica | -0.068 |
Jason | -0.067 |
Token | He |
Token ID | 679 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
otte | +0.012 |
Charl | +0.012 |
ky | +0.012 |
Har | +0.012 |
astically | +0.012 |
Neg logit contributions | |
kids | -0.006 |
idea | -0.005 |
sun | -0.005 |
do | -0.004 |
friends | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
otte | +0.009 |
Charl | +0.009 |
Har | +0.008 |
ically | +0.008 |
astically | +0.008 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.003 |
do | -0.003 |
friends | -0.003 |
y | -0.003 |
Token | soft |
Token ID | 2705 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
friends | +0.002 |
do | +0.002 |
sun | +0.002 |
Neg logit contributions | |
Charl | -0.004 |
otte | -0.004 |
Har | -0.004 |
ky | -0.004 |
astically | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
kids | +0.030 |
idea | +0.029 |
sun | +0.025 |
friends | +0.024 |
do | +0.024 |
Neg logit contributions | |
otte | -0.069 |
Charl | -0.068 |
Har | -0.067 |
astically | -0.065 |
Jessica | -0.064 |
Token | wet |
Token ID | 9583 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Charl | +0.030 |
otte | +0.030 |
ky | +0.028 |
May | +0.028 |
Har | +0.028 |
Neg logit contributions | |
idea | -0.021 |
kids | -0.020 |
do | -0.017 |
expect | -0.016 |
sun | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
kids | +0.019 |
idea | +0.017 |
sun | +0.016 |
wind | +0.015 |
friends | +0.014 |
Neg logit contributions | |
Charl | -0.047 |
otte | -0.047 |
Har | -0.046 |
Jessica | -0.044 |
astically | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
sun | +0.001 |
do | +0.001 |
friends | +0.001 |
Neg logit contributions | |
otte | -0.002 |
Charl | -0.002 |
Har | -0.002 |
ky | -0.002 |
astically | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
idea | +0.011 |
kids | +0.011 |
do | +0.009 |
sun | +0.009 |
friends | +0.008 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.023 |
ky | -0.022 |
Har | -0.022 |
astically | -0.022 |
Token | very |
Token ID | 845 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
kids | +0.031 |
idea | +0.031 |
promises | +0.028 |
choices | +0.028 |
oops | +0.027 |
Neg logit contributions | |
otte | -0.028 |
Charl | -0.028 |
Har | -0.027 |
ky | -0.027 |
May | -0.026 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
kids | +0.024 |
idea | +0.024 |
promises | +0.021 |
choices | +0.020 |
do | +0.020 |
Neg logit contributions | |
otte | -0.035 |
Har | -0.033 |
Charl | -0.033 |
May | -0.032 |
den | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
kids | +0.012 |
idea | +0.011 |
do | +0.010 |
sun | +0.010 |
friends | +0.009 |
Neg logit contributions | |
Charl | -0.025 |
otte | -0.024 |
Har | -0.024 |
May | -0.023 |
April | -0.023 |
Token | welcome |
Token ID | 7062 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
idea | +0.031 |
kids | +0.031 |
sun | +0.023 |
friends | +0.023 |
choices | +0.022 |
Neg logit contributions | |
otte | -0.079 |
Charl | -0.078 |
Har | -0.078 |
May | -0.076 |
ky | -0.075 |
Token | all |
Token ID | 477 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
idea | +0.004 |
urge | +0.003 |
oops | +0.003 |
kids | +0.003 |
do | +0.003 |
Neg logit contributions | |
Har | -0.004 |
Charl | -0.004 |
Smith | -0.004 |
otte | -0.004 |
May | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
idea | +0.017 |
kids | +0.016 |
tum | +0.015 |
do | +0.015 |
oops | +0.014 |
Neg logit contributions | |
otte | -0.023 |
ky | -0.023 |
Charl | -0.023 |
den | -0.023 |
Smith | -0.023 |
Token | kids |
Token ID | 3988 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
idea | +0.025 |
oops | +0.022 |
kids | +0.019 |
expect | +0.018 |
do | +0.018 |
Neg logit contributions | |
Charl | -0.067 |
otte | -0.067 |
Har | -0.067 |
May | -0.067 |
Smith | -0.065 |
Token | on |
Token ID | 319 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
kids | +0.016 |
idea | +0.015 |
do | +0.014 |
friends | +0.013 |
of | +0.012 |
Neg logit contributions | |
Charl | -0.031 |
otte | -0.029 |
Har | -0.029 |
Jessica | -0.028 |
Beck | -0.028 |
Token | board |
Token ID | 3096 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
otte | -0.002 |
Charl | -0.002 |
Har | -0.002 |
ky | -0.002 |
May | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
idea | +0.010 |
kids | +0.010 |
do | +0.008 |
friends | +0.008 |
noise | +0.008 |
Neg logit contributions | |
Charl | -0.021 |
otte | -0.021 |
Har | -0.020 |
May | -0.020 |
Beck | -0.019 |
Token | The |
Token ID | 383 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
idea | +0.018 |
kids | +0.017 |
choices | +0.016 |
promises | +0.016 |
expect | +0.016 |
Neg logit contributions | |
Charl | -0.019 |
Smith | -0.019 |
Har | -0.018 |
May | -0.018 |
otte | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
friends | +0.001 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
Har | -0.003 |
ky | -0.003 |
May | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
sun | +0.001 |
do | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.001 |
May | -0.001 |
Smith | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
otte | +0.001 |
Charl | +0.001 |
den | +0.001 |
ically | +0.001 |
la | +0.001 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
sun | -0.000 |
do | -0.000 |
friends | -0.000 |
Token | new |
Token ID | 649 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Charl | +0.007 |
otte | +0.007 |
Har | +0.007 |
May | +0.007 |
ky | +0.007 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.003 |
oops | -0.003 |
expect | -0.002 |
Token | past |
Token ID | 1613 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
kids | +0.003 |
idea | +0.003 |
sun | +0.002 |
friends | +0.002 |
dog | +0.002 |
Neg logit contributions | |
Charl | -0.012 |
ically | -0.012 |
otte | -0.012 |
side | -0.012 |
astically | -0.012 |
Token | el |
Token ID | 417 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Charl | +0.024 |
otte | +0.023 |
Har | +0.023 |
ically | +0.023 |
Jessica | +0.022 |
Neg logit contributions | |
kids | -0.014 |
idea | -0.013 |
sun | -0.012 |
do | -0.012 |
friends | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
kids | +0.031 |
idea | +0.030 |
sun | +0.027 |
friends | +0.025 |
do | +0.024 |
Neg logit contributions | |
Charl | -0.082 |
otte | -0.082 |
Har | -0.079 |
Alexa | -0.077 |
ically | -0.077 |
Token | It |
Token ID | 632 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Charl | +0.039 |
otte | +0.039 |
Har | +0.037 |
May | +0.037 |
ky | +0.037 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.017 |
do | -0.014 |
sun | -0.014 |
wind | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
Charl | +0.009 |
otte | +0.009 |
Har | +0.008 |
May | +0.008 |
ky | +0.008 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.006 |
do | -0.006 |
sun | -0.006 |
wind | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
May | -0.001 |
ically | -0.001 |
Token | pretty |
Token ID | 2495 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
otte | +0.005 |
Charl | +0.005 |
Har | +0.005 |
May | +0.005 |
ky | +0.005 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.002 |
urge | -0.002 |
friends | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
kids | +0.032 |
idea | +0.029 |
friends | +0.028 |
do | +0.028 |
people | +0.024 |
Neg logit contributions | |
Charl | -0.054 |
Har | -0.052 |
otte | -0.052 |
den | -0.050 |
Jessica | -0.050 |
Token | Spot |
Token ID | 15899 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
Charl | +0.029 |
otte | +0.029 |
Har | +0.028 |
May | +0.027 |
ky | +0.027 |
Neg logit contributions | |
idea | -0.017 |
kids | -0.016 |
do | -0.014 |
sun | -0.013 |
wind | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
kids | +0.001 |
idea | +0.001 |
do | +0.001 |
friends | +0.001 |
noise | +0.001 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.002 |
Jessica | -0.002 |
May | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.016 |
do | +0.014 |
sun | +0.013 |
wind | +0.013 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.027 |
Har | -0.026 |
May | -0.026 |
Smith | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
idea | +0.013 |
kids | +0.012 |
wind | +0.011 |
do | +0.011 |
sun | +0.011 |
Neg logit contributions | |
otte | -0.012 |
Charl | -0.012 |
Smith | -0.011 |
ky | -0.011 |
Har | -0.011 |
Token | be |
Token ID | 307 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
kids | +0.025 |
idea | +0.025 |
sun | +0.019 |
wind | +0.019 |
friends | +0.018 |
Neg logit contributions | |
otte | -0.064 |
Charl | -0.064 |
Har | -0.062 |
May | -0.061 |
astically | -0.061 |
Token | clean |
Token ID | 3424 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
idea | +0.042 |
kids | +0.038 |
do | +0.035 |
expect | +0.035 |
oops | +0.033 |
Neg logit contributions | |
Charl | -0.055 |
otte | -0.055 |
Har | -0.054 |
ky | -0.053 |
May | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
idea | +0.007 |
kids | +0.007 |
do | +0.006 |
friends | +0.006 |
noise | +0.006 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.015 |
Har | -0.014 |
astically | -0.014 |
May | -0.014 |
Token | free |
Token ID | 1479 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
add | +0.001 |
expect | +0.001 |
oops | +0.001 |
Neg logit contributions | |
otte | -0.003 |
Charl | -0.002 |
neatly | -0.002 |
proudly | -0.002 |
Smith | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
kids | +0.005 |
idea | +0.005 |
friends | +0.005 |
sun | +0.004 |
of | +0.004 |
Neg logit contributions | |
otte | -0.009 |
Charl | -0.009 |
Har | -0.009 |
Jessica | -0.008 |
astically | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
idea | +0.023 |
kids | +0.021 |
do | +0.019 |
sun | +0.018 |
wind | +0.018 |
Neg logit contributions | |
otte | -0.034 |
Charl | -0.034 |
Har | -0.032 |
May | -0.032 |
ky | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
kids | +0.007 |
idea | +0.007 |
do | +0.006 |
friends | +0.006 |
sun | +0.005 |
Neg logit contributions | |
Charl | -0.017 |
otte | -0.016 |
Har | -0.016 |
ky | -0.016 |
den | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
May | -0.001 |
ky | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.002 |
wind | +0.002 |
sun | +0.002 |
do | +0.002 |
Neg logit contributions | |
otte | -0.010 |
Charl | -0.010 |
den | -0.010 |
Har | -0.010 |
May | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Charl | +0.009 |
otte | +0.009 |
Har | +0.009 |
May | +0.009 |
April | +0.008 |
Neg logit contributions | |
idea | -0.004 |
kids | -0.004 |
do | -0.003 |
sun | -0.003 |
wind | -0.003 |
Token | go |
Token ID | 467 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
otte | +0.013 |
Charl | +0.013 |
Har | +0.013 |
May | +0.013 |
astically | +0.013 |
Neg logit contributions | |
kids | -0.004 |
idea | -0.004 |
sun | -0.003 |
oops | -0.003 |
friends | -0.003 |
Token | home |
Token ID | 1363 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Charl | +0.025 |
otte | +0.024 |
ically | +0.023 |
Har | +0.023 |
May | +0.023 |
Neg logit contributions | |
kids | -0.011 |
idea | -0.010 |
do | -0.009 |
friends | -0.009 |
of | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
idea | +0.012 |
kids | +0.011 |
do | +0.010 |
of | +0.010 |
friends | +0.010 |
Neg logit contributions | |
Charl | -0.040 |
Beck | -0.037 |
ky | -0.036 |
otte | -0.036 |
Har | -0.036 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Charl | +0.012 |
otte | +0.012 |
Har | +0.012 |
ky | +0.012 |
ically | +0.011 |
Neg logit contributions | |
kids | -0.006 |
idea | -0.006 |
do | -0.005 |
friends | -0.005 |
sun | -0.004 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Charl | +0.014 |
otte | +0.014 |
Har | +0.014 |
ky | +0.014 |
work | +0.013 |
Neg logit contributions | |
kids | -0.007 |
idea | -0.007 |
do | -0.007 |
friends | -0.006 |
urge | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
idea | +0.004 |
kids | +0.004 |
do | +0.004 |
sun | +0.003 |
wind | +0.003 |
Neg logit contributions | |
Charl | -0.005 |
otte | -0.005 |
ky | -0.005 |
Har | -0.004 |
den | -0.004 |
Token | find |
Token ID | 1064 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Charl | +0.019 |
otte | +0.019 |
Har | +0.018 |
May | +0.018 |
ky | +0.018 |
Neg logit contributions | |
idea | -0.009 |
kids | -0.009 |
sun | -0.007 |
do | -0.007 |
wind | -0.007 |
Token | disappointed |
Token ID | 11679 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
kids | +0.005 |
idea | +0.005 |
friends | +0.004 |
do | +0.004 |
sun | +0.004 |
Neg logit contributions | |
Charl | -0.010 |
otte | -0.010 |
ky | -0.009 |
Har | -0.009 |
astically | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Charl | +0.005 |
otte | +0.005 |
Har | +0.005 |
Jessica | +0.005 |
Beck | +0.005 |
Neg logit contributions | |
kids | -0.002 |
idea | -0.002 |
do | -0.002 |
friends | -0.002 |
of | -0.002 |
Token | but |
Token ID | 475 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Charl | +0.006 |
otte | +0.005 |
Har | +0.005 |
astically | +0.005 |
May | +0.005 |
Neg logit contributions | |
kids | -0.003 |
idea | -0.003 |
do | -0.002 |
sun | -0.002 |
wind | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
idea | +0.011 |
kids | +0.010 |
sun | +0.009 |
do | +0.009 |
wind | +0.009 |
Neg logit contributions | |
otte | -0.012 |
Charl | -0.011 |
May | -0.011 |
Har | -0.011 |
la | -0.011 |
Token | veterinarian |
Token ID | 41404 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
idea | +0.003 |
oops | +0.003 |
kids | +0.003 |
expect | +0.002 |
do | +0.002 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.002 |
May | -0.002 |
Smith | -0.002 |
Token | promised |
Token ID | 8072 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
idea | +0.000 |
kids | +0.000 |
do | +0.000 |
friends | +0.000 |
sun | +0.000 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
May | -0.001 |
ky | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
kids | +0.029 |
idea | +0.029 |
do | +0.025 |
sun | +0.024 |
friends | +0.024 |
Neg logit contributions | |
Charl | -0.038 |
otte | -0.038 |
Har | -0.036 |
ky | -0.036 |
May | -0.036 |
Token | come |
Token ID | 1282 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
Charl | +0.026 |
otte | +0.026 |
Har | +0.024 |
ky | +0.024 |
May | +0.024 |
Neg logit contributions | |
idea | -0.009 |
kids | -0.009 |
do | -0.008 |
sun | -0.007 |
wind | -0.007 |
Token | back |
Token ID | 736 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Charl | +0.032 |
otte | +0.031 |
Har | +0.029 |
Alexa | +0.029 |
den | +0.029 |
Neg logit contributions | |
kids | -0.014 |
do | -0.014 |
friends | -0.013 |
idea | -0.013 |
sun | -0.012 |
Token | later |
Token ID | 1568 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
kids | +0.013 |
friends | +0.012 |
do | +0.012 |
people | +0.011 |
idea | +0.011 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.021 |
Har | -0.021 |
astically | -0.021 |
ically | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
do | +0.003 |
of | +0.002 |
friends | +0.002 |
Neg logit contributions | |
Charl | -0.010 |
otte | -0.009 |
Beck | -0.009 |
Har | -0.009 |
Ba | -0.009 |
Token | Tom |
Token ID | 4186 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
Adam | +0.013 |
Jessica | +0.013 |
Maya | +0.012 |
Alexa | +0.012 |
Avery | +0.012 |
Neg logit contributions | |
ag | -0.019 |
add | -0.018 |
reath | -0.017 |
tum | -0.017 |
acquaintance | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
do | +0.003 |
sun | +0.002 |
friends | +0.002 |
Neg logit contributions | |
Charl | -0.004 |
otte | -0.004 |
Har | -0.003 |
May | -0.003 |
astically | -0.003 |
Token | Mom |
Token ID | 11254 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Avery | +0.047 |
Alexa | +0.046 |
Jessica | +0.045 |
Smith | +0.044 |
otte | +0.044 |
Neg logit contributions | |
idea | -0.037 |
n | -0.035 |
add | -0.034 |
kids | -0.034 |
belong | -0.034 |
Token | says |
Token ID | 1139 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
Charl | +0.026 |
otte | +0.026 |
May | +0.025 |
ky | +0.025 |
Har | +0.025 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.006 |
do | -0.005 |
sun | -0.005 |
wind | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Charl | +0.001 |
otte | +0.001 |
Har | +0.001 |
May | +0.001 |
ky | +0.001 |
Neg logit contributions | |
kids | -0.001 |
idea | -0.001 |
do | -0.001 |
friends | -0.001 |
sun | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Charl | +0.020 |
otte | +0.020 |
Har | +0.019 |
ky | +0.019 |
May | +0.019 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.018 |
do | -0.016 |
sun | -0.016 |
friends | -0.015 |
Token | cl |
Token ID | 537 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
idea | +0.017 |
kids | +0.016 |
do | +0.014 |
sun | +0.014 |
wind | +0.013 |
Neg logit contributions | |
Charl | -0.028 |
otte | -0.028 |
Har | -0.027 |
May | -0.027 |
ky | -0.027 |
Token | aps |
Token ID | 1686 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Charl | +0.016 |
otte | +0.016 |
ky | +0.015 |
Har | +0.015 |
Alexa | +0.015 |
Neg logit contributions | |
idea | -0.026 |
kids | -0.024 |
do | -0.023 |
wind | -0.022 |
noise | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
idea | +0.007 |
kids | +0.007 |
do | +0.006 |
sun | +0.006 |
friends | +0.006 |
Neg logit contributions | |
otte | -0.010 |
Charl | -0.010 |
astically | -0.010 |
Har | -0.010 |
ically | -0.009 |
Token | hands |
Token ID | 2832 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
idea | +0.025 |
kids | +0.025 |
do | +0.020 |
sun | +0.019 |
friends | +0.019 |
Neg logit contributions | |
Charl | -0.062 |
otte | -0.061 |
Har | -0.059 |
May | -0.058 |
ky | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
idea | +0.006 |
too | +0.006 |
of | +0.006 |
kids | +0.005 |
sun | +0.005 |
Neg logit contributions | |
otte | -0.025 |
Charl | -0.025 |
Har | -0.024 |
Simon | -0.023 |
April | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Charl | +0.014 |
otte | +0.014 |
Har | +0.013 |
May | +0.013 |
ky | +0.013 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.008 |
do | -0.007 |
sun | -0.007 |
wind | -0.006 |
Token | ground |
Token ID | 2323 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
otte | +0.019 |
Charl | +0.019 |
den | +0.018 |
Alexa | +0.018 |
Har | +0.018 |
Neg logit contributions | |
kids | -0.009 |
sun | -0.009 |
wind | -0.008 |
do | -0.008 |
idea | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -8.09e-03 |
Pos logit contributions | |
idea | +0.001 |
of | +0.001 |
kids | +0.001 |
friends | +0.001 |
sun | +0.001 |
Neg logit contributions | |
Charl | -0.004 |
otte | -0.004 |
Har | -0.004 |
Ba | -0.004 |
May | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
otte | +0.000 |
Charl | +0.000 |
ky | +0.000 |
den | +0.000 |
Har | +0.000 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
sun | -0.000 |
do | -0.000 |
wind | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
otte | +0.004 |
Charl | +0.004 |
Har | +0.004 |
Jessica | +0.004 |
ky | +0.004 |
Neg logit contributions | |
kids | -0.002 |
do | -0.002 |
idea | -0.002 |
friends | -0.002 |
sun | -0.002 |
Token | full |
Token ID | 1336 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.003 |
Har | +0.003 |
ky | +0.003 |
May | +0.003 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
do | -0.002 |
sun | -0.002 |
friends | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
kids | +0.006 |
idea | +0.006 |
sun | +0.005 |
do | +0.005 |
wind | +0.005 |
Neg logit contributions | |
otte | -0.018 |
Charl | -0.018 |
Har | -0.017 |
May | -0.017 |
astically | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.018 |
Har | +0.018 |
May | +0.017 |
ky | +0.017 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.008 |
do | -0.006 |
sun | -0.006 |
wind | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.022 |
Har | +0.021 |
May | +0.021 |
ky | +0.021 |
Neg logit contributions | |
kids | -0.011 |
idea | -0.011 |
sun | -0.010 |
friends | -0.010 |
do | -0.010 |
Token | knew |
Token ID | 2993 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
otte | +0.003 |
Charl | +0.003 |
Har | +0.002 |
May | +0.002 |
ky | +0.002 |
Neg logit contributions | |
idea | -0.002 |
kids | -0.002 |
do | -0.001 |
sun | -0.001 |
wind | -0.001 |
Token | this |
Token ID | 428 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Charl | +0.033 |
otte | +0.032 |
ky | +0.032 |
Har | +0.031 |
ically | +0.031 |
Neg logit contributions | |
kids | -0.013 |
idea | -0.013 |
do | -0.012 |
friends | -0.012 |
sun | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
kids | +0.012 |
idea | +0.011 |
do | +0.010 |
sun | +0.010 |
friends | +0.010 |
Neg logit contributions | |
Charl | -0.024 |
otte | -0.023 |
Har | -0.023 |
ky | -0.023 |
den | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.000 |
do | +0.000 |
sun | +0.000 |
oops | +0.000 |
Neg logit contributions | |
otte | -0.001 |
Charl | -0.001 |
la | -0.001 |
den | -0.001 |
Alexa | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
kids | +0.022 |
idea | +0.021 |
sun | +0.018 |
friends | +0.018 |
do | +0.018 |
Neg logit contributions | |
otte | -0.037 |
Charl | -0.037 |
ically | -0.036 |
astically | -0.036 |
Har | -0.035 |
Token | sudden |
Token ID | 4802 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Charl | +0.010 |
otte | +0.010 |
Har | +0.009 |
ky | +0.009 |
May | +0.009 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
do | -0.010 |
sun | -0.010 |
wind | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
kids | +0.006 |
idea | +0.005 |
sun | +0.005 |
friends | +0.005 |
people | +0.005 |
Neg logit contributions | |
Charl | -0.011 |
otte | -0.011 |
Har | -0.011 |
athan | -0.011 |
den | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
kids | +0.010 |
idea | +0.009 |
sun | +0.008 |
do | +0.008 |
friends | +0.008 |
Neg logit contributions | |
Charl | -0.024 |
otte | -0.024 |
Har | -0.023 |
ky | -0.023 |
den | -0.023 |
Token | gust |
Token ID | 35253 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
otte | +0.000 |
Charl | +0.000 |
Har | +0.000 |
ky | +0.000 |
astically | +0.000 |
Neg logit contributions | |
idea | -0.000 |
kids | -0.000 |
do | -0.000 |
sun | -0.000 |
wind | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
Charl | +0.019 |
otte | +0.018 |
ky | +0.018 |
May | +0.018 |
Har | +0.018 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.006 |
choices | -0.005 |
promises | -0.005 |
tum | -0.004 |
Token | wind |
Token ID | 2344 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.003 |
ky | +0.003 |
Har | +0.003 |
May | +0.003 |
Neg logit contributions | |
idea | -0.000 |
kids | -0.000 |
do | -0.000 |
friends | -0.000 |
expect | -0.000 |
Token | blew |
Token ID | 17948 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Charl | +0.023 |
otte | +0.022 |
Har | +0.021 |
Jessica | +0.021 |
May | +0.021 |
Neg logit contributions | |
kids | -0.016 |
idea | -0.015 |
do | -0.014 |
wind | -0.014 |
sun | -0.014 |
Token | by |
Token ID | 416 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
wind | +0.006 |
sun | +0.005 |
noise | +0.005 |
Neg logit contributions | |
otte | -0.011 |
Charl | -0.011 |
astically | -0.010 |
Har | -0.010 |
Jessica | -0.010 |
Token | Mom |
Token ID | 29252 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
otte | +0.027 |
Charl | +0.027 |
Har | +0.026 |
ky | +0.026 |
astically | +0.026 |
Neg logit contributions | |
kids | -0.030 |
idea | -0.029 |
do | -0.026 |
sun | -0.026 |
wind | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
kids | +0.014 |
idea | +0.013 |
do | +0.012 |
friends | +0.011 |
sun | +0.011 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.022 |
Har | -0.022 |
May | -0.021 |
April | -0.020 |
Token | my |
Token ID | 616 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
otte | +0.028 |
Charl | +0.028 |
May | +0.026 |
Smith | +0.026 |
Har | +0.026 |
Neg logit contributions | |
idea | -0.019 |
kids | -0.017 |
sun | -0.015 |
wind | -0.015 |
friends | -0.014 |
Token | red |
Token ID | 2266 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Charl | +0.003 |
otte | +0.003 |
Har | +0.003 |
ky | +0.003 |
side | +0.003 |
Neg logit contributions | |
kids | -0.001 |
idea | -0.001 |
do | -0.001 |
sun | -0.001 |
friends | -0.001 |
Token | cr |
Token ID | 1067 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.017 |
Jessica | +0.017 |
Har | +0.017 |
den | +0.016 |
Neg logit contributions | |
kids | -0.005 |
idea | -0.005 |
do | -0.005 |
sun | -0.005 |
things | -0.004 |
Token | ay |
Token ID | 323 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
otte | +0.055 |
Charl | +0.055 |
Har | +0.053 |
May | +0.052 |
ky | +0.052 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.011 |
do | -0.008 |
sun | -0.007 |
wind | -0.006 |
Token | on |
Token ID | 261 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Charl | +0.037 |
otte | +0.036 |
Har | +0.035 |
May | +0.034 |
astically | +0.034 |
Neg logit contributions | |
kids | -0.023 |
idea | -0.022 |
do | -0.020 |
of | -0.019 |
friends | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Charl | +0.016 |
Har | +0.016 |
otte | +0.015 |
Simon | +0.014 |
May | +0.014 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.007 |
do | -0.007 |
of | -0.006 |
sun | -0.006 |
Token | dry |
Token ID | 5894 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
otte | +0.041 |
Charl | +0.041 |
Har | +0.040 |
den | +0.040 |
Simon | +0.039 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.016 |
sun | -0.016 |
y | -0.015 |
do | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
of | +0.006 |
sun | +0.005 |
wind | +0.005 |
Neg logit contributions | |
Har | -0.021 |
Charl | -0.021 |
otte | -0.021 |
April | -0.021 |
Simon | -0.020 |
Token | broken |
Token ID | 5445 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Charl | +0.032 |
otte | +0.032 |
Har | +0.031 |
May | +0.030 |
ky | +0.030 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.018 |
do | -0.015 |
sun | -0.015 |
wind | -0.014 |
Token | shady |
Token ID | 36135 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
otte | +0.009 |
Charl | +0.009 |
astically | +0.009 |
la | +0.008 |
Har | +0.008 |
Neg logit contributions | |
idea | -0.004 |
kids | -0.004 |
do | -0.003 |
sun | -0.003 |
noise | -0.003 |
Token | looking |
Token ID | 2045 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
sun | +0.005 |
wind | +0.005 |
Neg logit contributions | |
Charl | -0.014 |
otte | -0.014 |
Har | -0.014 |
ky | -0.014 |
May | -0.014 |
Token | man |
Token ID | 582 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
Charl | +0.021 |
otte | +0.021 |
astically | +0.019 |
Har | +0.019 |
May | +0.019 |
Neg logit contributions | |
idea | -0.010 |
kids | -0.009 |
do | -0.008 |
sun | -0.008 |
wind | -0.008 |
Token | at |
Token ID | 379 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Charl | +0.000 |
otte | +0.000 |
Har | +0.000 |
astically | +0.000 |
May | +0.000 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
do | -0.000 |
friends | -0.000 |
sun | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
kids | +0.006 |
idea | +0.006 |
do | +0.005 |
people | +0.005 |
animals | +0.005 |
Neg logit contributions | |
Charl | -0.018 |
otte | -0.018 |
astically | -0.017 |
ically | -0.017 |
Har | -0.017 |
Token | end |
Token ID | 886 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
Charl | +0.034 |
otte | +0.034 |
den | +0.031 |
astically | +0.031 |
Alexa | +0.031 |
Neg logit contributions | |
kids | -0.017 |
idea | -0.015 |
sun | -0.014 |
do | -0.014 |
wind | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Charl | +0.057 |
otte | +0.055 |
Har | +0.054 |
May | +0.052 |
ky | +0.052 |
Neg logit contributions | |
of | -0.002 |
kids | -0.002 |
idea | -0.001 |
sun | +0.001 |
do | +0.001 |
Token | the |
Token ID | 262 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
kids | +0.008 |
idea | +0.007 |
do | +0.006 |
sun | +0.006 |
friends | +0.006 |
Neg logit contributions | |
Charl | -0.022 |
otte | -0.022 |
astically | -0.022 |
ically | -0.021 |
ky | -0.021 |
Token | street |
Token ID | 4675 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Charl | +0.021 |
otte | +0.021 |
Har | +0.020 |
ky | +0.019 |
Smith | +0.019 |
Neg logit contributions | |
idea | -0.014 |
kids | -0.014 |
do | -0.012 |
sun | -0.011 |
friends | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -8.24e-03 |
Pos logit contributions | |
Charl | +0.028 |
otte | +0.027 |
Har | +0.026 |
Ba | +0.026 |
May | +0.025 |
Neg logit contributions | |
kids | -0.012 |
idea | -0.011 |
do | -0.010 |
of | -0.010 |
friends | -0.009 |
Token | Joe |
Token ID | 5689 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
otte | +0.000 |
Charl | +0.000 |
ky | +0.000 |
Har | +0.000 |
May | +0.000 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
sun | -0.000 |
do | -0.000 |
friends | -0.000 |
Token | curious |
Token ID | 11040 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
wind | +0.001 |
Neg logit contributions | |
Charl | -0.001 |
otte | -0.001 |
Har | -0.001 |
May | -0.001 |
ky | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
do | +0.004 |
sun | +0.004 |
wind | +0.004 |
Neg logit contributions | |
Charl | -0.007 |
otte | -0.007 |
ky | -0.007 |
Har | -0.007 |
May | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
idea | +0.005 |
kids | +0.005 |
do | +0.004 |
sun | +0.004 |
wind | +0.004 |
Neg logit contributions | |
otte | -0.009 |
Charl | -0.009 |
Har | -0.009 |
May | -0.009 |
ky | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
Charl | +0.010 |
otte | +0.010 |
Har | +0.009 |
ky | +0.009 |
May | +0.009 |
Neg logit contributions | |
idea | -0.006 |
kids | -0.005 |
do | -0.005 |
friends | -0.004 |
sun | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Charl | +0.002 |
otte | +0.002 |
astically | +0.002 |
ically | +0.002 |
Har | +0.002 |
Neg logit contributions | |
kids | -0.001 |
idea | -0.001 |
do | -0.001 |
friends | -0.001 |
people | -0.001 |
Token | play |
Token ID | 711 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.004 |
wind | +0.003 |
choices | +0.003 |
sun | +0.003 |
Neg logit contributions | |
otte | -0.007 |
Charl | -0.007 |
Har | -0.007 |
astically | -0.006 |
May | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
May | +0.018 |
otte | +0.018 |
Charl | +0.018 |
ky | +0.018 |
Alexa | +0.018 |
Neg logit contributions | |
kids | -0.022 |
idea | -0.022 |
wind | -0.021 |
oops | -0.020 |
sun | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
kids | +0.005 |
idea | +0.005 |
do | +0.004 |
friends | +0.004 |
sun | +0.004 |
Neg logit contributions | |
Charl | -0.014 |
otte | -0.014 |
Har | -0.014 |
astically | -0.014 |
ically | -0.013 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
oops | +0.001 |
wind | +0.001 |
Neg logit contributions | |
otte | -0.002 |
Charl | -0.002 |
May | -0.002 |
ky | -0.002 |
Har | -0.002 |
Token | ay |
Token ID | 323 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
Charl | +0.077 |
otte | +0.077 |
Har | +0.074 |
ky | +0.074 |
May | +0.073 |
Neg logit contributions | |
idea | -0.023 |
kids | -0.023 |
do | -0.017 |
sun | -0.016 |
wind | -0.016 |
Token | ons |
Token ID | 684 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
otte | +0.023 |
Jessica | +0.023 |
Alexa | +0.022 |
Charl | +0.022 |
ky | +0.022 |
Neg logit contributions | |
idea | -0.041 |
kids | -0.040 |
wind | -0.038 |
urge | -0.038 |
tum | -0.037 |
Token | ran |
Token ID | 4966 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
kids | +0.014 |
do | +0.012 |
idea | +0.012 |
friends | +0.011 |
wind | +0.010 |
Neg logit contributions | |
Charl | -0.032 |
otte | -0.032 |
Har | -0.031 |
astically | -0.031 |
work | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
kids | +0.015 |
idea | +0.015 |
do | +0.013 |
sun | +0.012 |
wind | +0.012 |
Neg logit contributions | |
Charl | -0.022 |
otte | -0.022 |
Har | -0.021 |
May | -0.020 |
astically | -0.020 |
Token | jumped |
Token ID | 11687 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
kids | +0.013 |
idea | +0.013 |
do | +0.011 |
sun | +0.011 |
friends | +0.011 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.023 |
Har | -0.022 |
May | -0.022 |
astically | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
idea | +0.008 |
kids | +0.008 |
do | +0.007 |
sun | +0.007 |
wind | +0.007 |
Neg logit contributions | |
otte | -0.016 |
Charl | -0.016 |
Har | -0.015 |
Jessica | -0.015 |
den | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
idea | +0.021 |
kids | +0.019 |
do | +0.017 |
expect | +0.017 |
tum | +0.017 |
Neg logit contributions | |
ky | -0.033 |
otte | -0.033 |
Charl | -0.032 |
May | -0.031 |
den | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
idea | +0.016 |
kids | +0.016 |
sun | +0.014 |
do | +0.014 |
wind | +0.013 |
Neg logit contributions | |
Charl | -0.027 |
otte | -0.026 |
May | -0.025 |
Har | -0.025 |
Jessica | -0.025 |
Token | But |
Token ID | 887 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Charl | +0.018 |
Har | +0.017 |
Ba | +0.017 |
Alexa | +0.017 |
April | +0.016 |
Neg logit contributions | |
idea | -0.019 |
kids | -0.018 |
choices | -0.017 |
expect | -0.017 |
deal | -0.016 |
Token | then |
Token ID | 788 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Charl | +0.008 |
otte | +0.008 |
Har | +0.008 |
ky | +0.008 |
May | +0.008 |
Neg logit contributions | |
idea | -0.007 |
kids | -0.007 |
do | -0.006 |
sun | -0.006 |
expect | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Charl | +0.007 |
otte | +0.007 |
Har | +0.007 |
May | +0.006 |
ky | +0.006 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
sun | -0.004 |
friends | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.017 |
Har | +0.017 |
ky | +0.016 |
Alexa | +0.016 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.017 |
oops | -0.016 |
choices | -0.015 |
expect | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
kids | +0.011 |
idea | +0.009 |
do | +0.009 |
friends | +0.009 |
sun | +0.008 |
Neg logit contributions | |
Charl | -0.023 |
otte | -0.022 |
Har | -0.021 |
May | -0.021 |
den | -0.021 |
Token | we |
Token ID | 356 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
kids | +0.008 |
idea | +0.008 |
do | +0.008 |
sun | +0.007 |
friends | +0.007 |
Neg logit contributions | |
Charl | -0.015 |
otte | -0.014 |
Har | -0.014 |
ky | -0.014 |
astically | -0.014 |
Token | can |
Token ID | 460 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
noise | +0.002 |
choices | +0.002 |
sun | +0.002 |
Neg logit contributions | |
Charl | -0.003 |
otte | -0.003 |
May | -0.003 |
Smith | -0.003 |
Har | -0.003 |
Token | have |
Token ID | 423 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
Charl | +0.014 |
otte | +0.014 |
Har | +0.014 |
ky | +0.014 |
May | +0.014 |
Neg logit contributions | |
idea | -0.005 |
kids | -0.005 |
do | -0.004 |
sun | -0.004 |
friends | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
otte | +0.037 |
Charl | +0.036 |
den | +0.035 |
ically | +0.035 |
Har | +0.035 |
Neg logit contributions | |
kids | -0.017 |
idea | -0.016 |
sun | -0.014 |
do | -0.014 |
friends | -0.013 |
Token | juice |
Token ID | 13135 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
sun | +0.005 |
wind | +0.004 |
Neg logit contributions | |
Charl | -0.016 |
otte | -0.016 |
Har | -0.015 |
May | -0.015 |
ky | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
kids | +0.000 |
idea | +0.000 |
do | +0.000 |
sun | +0.000 |
friends | +0.000 |
Neg logit contributions | |
Charl | -0.001 |
Har | -0.001 |
otte | -0.001 |
den | -0.001 |
April | -0.001 |
Token | cookies |
Token ID | 14746 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Charl | +0.049 |
otte | +0.049 |
Har | +0.047 |
den | +0.047 |
ically | +0.046 |
Neg logit contributions | |
kids | -0.015 |
idea | -0.014 |
do | -0.013 |
sun | -0.012 |
friends | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
kids | +0.007 |
idea | +0.006 |
do | +0.006 |
sun | +0.006 |
friends | +0.005 |
Neg logit contributions | |
otte | -0.013 |
Charl | -0.013 |
Har | -0.012 |
den | -0.012 |
Simon | -0.012 |
Token | How |
Token ID | 1374 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Charl | +0.003 |
May | +0.003 |
otte | +0.002 |
Smith | +0.002 |
astically | +0.002 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.002 |
friends | -0.002 |
do | -0.002 |
urge | -0.002 |
Token | does |
Token ID | 857 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
kids | +0.002 |
idea | +0.002 |
sun | +0.002 |
urge | +0.002 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.007 |
Charl | -0.006 |
astically | -0.006 |
May | -0.006 |
den | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
idea | +0.018 |
kids | +0.017 |
sun | +0.014 |
wind | +0.014 |
friends | +0.014 |
Neg logit contributions | |
otte | -0.026 |
Charl | -0.026 |
Har | -0.025 |
May | -0.024 |
Alexa | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
otte | +0.027 |
Charl | +0.027 |
Har | +0.026 |
May | +0.025 |
Jessica | +0.025 |
Neg logit contributions | |
idea | -0.016 |
kids | -0.015 |
do | -0.015 |
sun | -0.013 |
y | -0.013 |
Token | cold |
Token ID | 4692 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
otte | +0.035 |
Charl | +0.035 |
Har | +0.034 |
ically | +0.033 |
astically | +0.033 |
Neg logit contributions | |
idea | -0.017 |
kids | -0.016 |
do | -0.014 |
sun | -0.014 |
wind | -0.013 |
Token | � |
Token ID | 6184 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
kids | +0.013 |
idea | +0.012 |
sun | +0.012 |
wind | +0.012 |
of | +0.011 |
Neg logit contributions | |
otte | -0.030 |
Charl | -0.030 |
Har | -0.030 |
April | -0.029 |
Mart | -0.029 |
Token | � |
Token ID | 95 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Charl | +0.028 |
otte | +0.028 |
Har | +0.026 |
May | +0.026 |
ky | +0.026 |
Neg logit contributions | |
idea | -0.032 |
kids | -0.032 |
do | -0.028 |
sun | -0.028 |
friends | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Charl | +0.019 |
May | +0.018 |
ky | +0.017 |
ically | +0.017 |
Har | +0.017 |
Neg logit contributions | |
kids | -0.021 |
idea | -0.021 |
friends | -0.019 |
sun | -0.018 |
wind | -0.017 |
Token | � |
Token ID | 447 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Charl | +0.037 |
otte | +0.035 |
Har | +0.034 |
Smith | +0.033 |
May | +0.033 |
Neg logit contributions | |
idea | -0.039 |
kids | -0.038 |
sun | -0.034 |
wind | -0.034 |
do | -0.033 |
Token | � |
Token ID | 250 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
otte | +0.066 |
Charl | +0.064 |
den | +0.063 |
la | +0.061 |
Har | +0.060 |
Neg logit contributions | |
idea | -0.062 |
kids | -0.062 |
do | -0.058 |
sun | -0.057 |
wind | -0.055 |
Token | not |
Token ID | 407 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
otte | +0.040 |
Charl | +0.040 |
astically | +0.037 |
Har | +0.037 |
Alexa | +0.036 |
Neg logit contributions | |
kids | -0.032 |
idea | -0.030 |
do | -0.028 |
sun | -0.028 |
wind | -0.027 |
Token | like |
Token ID | 588 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Charl | +0.043 |
otte | +0.043 |
Har | +0.041 |
astically | +0.040 |
ically | +0.040 |
Neg logit contributions | |
kids | -0.023 |
idea | -0.022 |
do | -0.020 |
sun | -0.018 |
wind | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
Charl | +0.060 |
otte | +0.060 |
Har | +0.059 |
astically | +0.058 |
ically | +0.058 |
Neg logit contributions | |
kids | -0.025 |
idea | -0.022 |
do | -0.021 |
sun | -0.020 |
friends | -0.018 |
Token | warm |
Token ID | 5814 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
idea | +0.002 |
kids | +0.002 |
sun | +0.002 |
do | +0.002 |
wind | +0.002 |
Neg logit contributions | |
otte | -0.004 |
Charl | -0.004 |
Har | -0.004 |
la | -0.004 |
ky | -0.004 |
Token | know |
Token ID | 760 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Charl | +0.018 |
otte | +0.018 |
Har | +0.017 |
May | +0.017 |
ky | +0.017 |
Neg logit contributions | |
idea | -0.009 |
kids | -0.008 |
do | -0.007 |
sun | -0.007 |
wind | -0.007 |
Token | what |
Token ID | 644 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Charl | +0.030 |
otte | +0.029 |
Har | +0.029 |
ky | +0.028 |
ically | +0.027 |
Neg logit contributions | |
kids | -0.016 |
idea | -0.014 |
do | -0.014 |
friends | -0.013 |
things | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
kids | +0.004 |
idea | +0.003 |
do | +0.003 |
friends | +0.003 |
sun | +0.003 |
Neg logit contributions | |
Charl | -0.008 |
otte | -0.008 |
ky | -0.008 |
ically | -0.007 |
Har | -0.007 |
Token | 'll |
Token ID | 1183 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
kids | +0.007 |
idea | +0.007 |
sun | +0.006 |
wind | +0.006 |
friends | +0.005 |
Neg logit contributions | |
Charl | -0.012 |
otte | -0.012 |
astically | -0.011 |
Har | -0.011 |
May | -0.011 |
Token | do |
Token ID | 466 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Charl | +0.004 |
otte | +0.004 |
Har | +0.004 |
ky | +0.004 |
May | +0.004 |
Neg logit contributions | |
idea | -0.001 |
kids | -0.001 |
do | -0.001 |
sun | -0.001 |
wind | -0.001 |
Token | ," |
Token ID | 553 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
idea | +0.009 |
do | +0.008 |
kids | +0.008 |
of | +0.007 |
friends | +0.007 |
Neg logit contributions | |
Charl | -0.017 |
Har | -0.017 |
otte | -0.016 |
Ba | -0.016 |
April | -0.016 |
Token | Bill |
Token ID | 3941 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Charl | +0.085 |
otte | +0.084 |
Har | +0.081 |
ky | +0.080 |
astically | +0.080 |
Neg logit contributions | |
idea | -0.056 |
kids | -0.055 |
do | -0.048 |
sun | -0.046 |
friends | -0.045 |
Token | ie |
Token ID | 494 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Charl | +0.059 |
ifying | +0.056 |
otte | +0.056 |
Har | +0.055 |
astically | +0.054 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.013 |
do | -0.010 |
friends | -0.009 |
children | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Charl | +0.037 |
otte | +0.036 |
Har | +0.035 |
May | +0.034 |
ky | +0.034 |
Neg logit contributions | |
idea | -0.011 |
kids | -0.010 |
friends | -0.008 |
do | -0.007 |
noise | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
idea | +0.007 |
kids | +0.006 |
do | +0.005 |
of | +0.005 |
friends | +0.005 |
Neg logit contributions | |
Charl | -0.017 |
otte | -0.016 |
Har | -0.016 |
April | -0.016 |
May | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
otte | +0.002 |
Charl | +0.002 |
ky | +0.001 |
den | +0.001 |
work | +0.001 |
Neg logit contributions | |
kids | -0.000 |
idea | -0.000 |
sun | -0.000 |
It | -0.000 |
do | -0.000 |
Token | 't |
Token ID | 470 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
Charl | +0.009 |
otte | +0.009 |
Har | +0.008 |
May | +0.008 |
astically | +0.008 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.012 |
sun | -0.011 |
wind | -0.011 |
friends | -0.011 |
Token | know |
Token ID | 760 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Har | +0.034 |
den | +0.033 |
otte | +0.032 |
ky | +0.032 |
Charl | +0.032 |
Neg logit contributions | |
kids | -0.018 |
tum | -0.017 |
promises | -0.017 |
oops | -0.017 |
choices | -0.017 |
Token | how |
Token ID | 703 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Charl | +0.032 |
otte | +0.032 |
Har | +0.031 |
Jessica | +0.030 |
ky | +0.029 |
Neg logit contributions | |
kids | -0.019 |
idea | -0.017 |
do | -0.016 |
friends | -0.015 |
sun | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Charl | +0.016 |
otte | +0.016 |
Har | +0.015 |
ky | +0.015 |
May | +0.015 |
Neg logit contributions | |
kids | -0.013 |
idea | -0.013 |
do | -0.012 |
friends | -0.012 |
sun | -0.011 |
Token | swim |
Token ID | 9422 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
otte | +0.012 |
Charl | +0.012 |
Har | +0.011 |
ky | +0.011 |
May | +0.011 |
Neg logit contributions | |
idea | -0.006 |
kids | -0.006 |
sun | -0.005 |
wind | -0.005 |
do | -0.004 |
Token | ," |
Token ID | 553 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Charl | +0.026 |
Jessica | +0.025 |
otte | +0.025 |
Laura | +0.025 |
Har | +0.024 |
Neg logit contributions | |
idea | -0.011 |
do | -0.010 |
kids | -0.010 |
too | -0.009 |
things | -0.008 |
Token | replied |
Token ID | 8712 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
otte | +0.082 |
Charl | +0.082 |
Har | +0.079 |
May | +0.079 |
ky | +0.078 |
Neg logit contributions | |
idea | -0.043 |
kids | -0.042 |
oops | -0.036 |
sun | -0.035 |
do | -0.034 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Charl | +0.061 |
otte | +0.060 |
Har | +0.057 |
astically | +0.057 |
May | +0.056 |
Neg logit contributions | |
idea | -0.035 |
kids | -0.034 |
do | -0.029 |
sun | -0.029 |
friends | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
idea | +0.003 |
kids | +0.003 |
friends | +0.002 |
do | +0.002 |
urge | +0.002 |
Neg logit contributions | |
Charl | -0.006 |
otte | -0.006 |
Har | -0.006 |
astically | -0.006 |
May | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
otte | +0.012 |
Charl | +0.012 |
den | +0.012 |
Har | +0.012 |
la | +0.012 |
Neg logit contributions | |
kids | -0.004 |
idea | -0.004 |
sun | -0.004 |
do | -0.004 |
friends | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
idea | +0.006 |
kids | +0.006 |
do | +0.005 |
sun | +0.005 |
friends | +0.005 |
Neg logit contributions | |
Charl | -0.012 |
otte | -0.012 |
Har | -0.012 |
ky | -0.012 |
May | -0.011 |
Token | something |
Token ID | 1223 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
otte | +0.014 |
Charl | +0.013 |
ically | +0.013 |
ky | +0.013 |
astically | +0.013 |
Neg logit contributions | |
kids | -0.009 |
idea | -0.009 |
sun | -0.008 |
do | -0.008 |
friends | -0.008 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
Charl | +0.034 |
otte | +0.034 |
Har | +0.032 |
ically | +0.032 |
astically | +0.032 |
Neg logit contributions | |
idea | -0.018 |
kids | -0.018 |
do | -0.016 |
sun | -0.015 |
friends | -0.015 |
Token | � |
Token ID | 6184 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
idea | +0.001 |
kids | +0.001 |
do | +0.001 |
sun | +0.001 |
things | +0.001 |
Neg logit contributions | |
Charl | -0.002 |
otte | -0.002 |
Har | -0.002 |
Jessica | -0.002 |
April | -0.002 |
Token | � |
Token ID | 95 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Charl | +0.048 |
otte | +0.047 |
Har | +0.045 |
ky | +0.044 |
May | +0.044 |
Neg logit contributions | |
idea | -0.050 |
kids | -0.049 |
do | -0.044 |
sun | -0.043 |
wind | -0.042 |
Token | € |
Token ID | 26391 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Charl | +0.035 |
ky | +0.033 |
Har | +0.033 |
otte | +0.033 |
May | +0.033 |
Neg logit contributions | |
idea | -0.038 |
kids | -0.037 |
friends | -0.034 |
wind | -0.032 |
do | -0.032 |
Token | � |
Token ID | 447 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Charl | +0.052 |
otte | +0.049 |
Har | +0.048 |
astically | +0.047 |
Smith | +0.047 |
Neg logit contributions | |
idea | -0.072 |
kids | -0.066 |
wind | -0.061 |
urge | -0.060 |
sun | -0.059 |
Token | � |
Token ID | 250 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
otte | +0.072 |
Charl | +0.071 |
den | +0.066 |
Har | +0.066 |
May | +0.065 |
Neg logit contributions | |
kids | -0.089 |
idea | -0.089 |
do | -0.082 |
sun | -0.081 |
wind | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
otte | +0.050 |
Charl | +0.048 |
athan | +0.045 |
den | +0.044 |
ically | +0.044 |
Neg logit contributions | |
kids | -0.037 |
sun | -0.035 |
do | -0.032 |
idea | -0.031 |
wind | -0.030 |
Token | cob |
Token ID | 22843 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
otte | +0.037 |
Charl | +0.037 |
astically | +0.037 |
ically | +0.036 |
Har | +0.035 |
Neg logit contributions | |
kids | -0.017 |
idea | -0.017 |
do | -0.015 |
sun | -0.015 |
wind | -0.014 |
Token | web |
Token ID | 12384 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Charl | +0.021 |
otte | +0.021 |
Har | +0.021 |
astically | +0.020 |
ically | +0.019 |
Neg logit contributions | |
kids | -0.027 |
idea | -0.027 |
do | -0.025 |
sun | -0.024 |
wind | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Har | +0.040 |
otte | +0.040 |
Charl | +0.040 |
Simon | +0.037 |
Jessica | +0.037 |
Neg logit contributions | |
idea | -0.019 |
do | -0.019 |
kids | -0.018 |
of | -0.017 |
noise | -0.016 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
otte | +0.008 |
Charl | +0.008 |
ky | +0.007 |
la | +0.007 |
ically | +0.007 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.003 |
friends | -0.002 |
sun | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
otte | +0.039 |
Charl | +0.039 |
Har | +0.038 |
May | +0.037 |
ky | +0.037 |
Neg logit contributions | |
idea | -0.013 |
kids | -0.012 |
do | -0.010 |
sun | -0.009 |
friends | -0.009 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Charl | +0.025 |
otte | +0.025 |
ky | +0.024 |
astically | +0.024 |
Har | +0.024 |
Neg logit contributions | |
idea | -0.019 |
kids | -0.018 |
do | -0.015 |
wind | -0.015 |
sun | -0.015 |
Token | at |
Token ID | 379 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Charl | +0.010 |
otte | +0.010 |
Har | +0.009 |
May | +0.009 |
astically | +0.009 |
Neg logit contributions | |
idea | -0.003 |
kids | -0.003 |
do | -0.003 |
sun | -0.002 |
friends | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Charl | +0.012 |
otte | +0.011 |
ically | +0.011 |
astically | +0.011 |
Har | +0.011 |
Neg logit contributions | |
kids | -0.004 |
idea | -0.003 |
friends | -0.003 |
sun | -0.003 |
do | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Charl | +0.041 |
otte | +0.040 |
Har | +0.037 |
astically | +0.037 |
den | +0.037 |
Neg logit contributions | |
idea | -0.044 |
kids | -0.044 |
sun | -0.040 |
do | -0.040 |
wind | -0.038 |
Token | caul |
Token ID | 46087 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Charl | +0.060 |
otte | +0.060 |
Har | +0.056 |
astically | +0.055 |
May | +0.055 |
Neg logit contributions | |
idea | -0.071 |
kids | -0.070 |
do | -0.064 |
sun | -0.064 |
wind | -0.062 |
Token | iflower |
Token ID | 42642 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Charl | +0.040 |
otte | +0.038 |
astically | +0.036 |
Har | +0.036 |
den | +0.035 |
Neg logit contributions | |
idea | -0.068 |
kids | -0.067 |
do | -0.063 |
sun | -0.063 |
friends | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Charl | +0.017 |
otte | +0.016 |
Har | +0.016 |
Jessica | +0.015 |
May | +0.015 |
Neg logit contributions | |
idea | -0.008 |
kids | -0.007 |
do | -0.007 |
sun | -0.007 |
friends | -0.007 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Charl | +0.030 |
otte | +0.029 |
Har | +0.029 |
May | +0.028 |
astically | +0.028 |
Neg logit contributions | |
kids | -0.013 |
idea | -0.012 |
do | -0.011 |
sun | -0.011 |
friends | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Charl | +0.046 |
otte | +0.045 |
May | +0.044 |
Har | +0.043 |
ky | +0.043 |
Neg logit contributions | |
idea | -0.043 |
kids | -0.043 |
wind | -0.037 |
do | -0.037 |
expect | -0.037 |