Token | with |
Token ID | 351 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
First | +0.069 |
Morty | +0.060 |
Pr | +0.058 |
First | +0.057 |
Stri | +0.057 |
Neg logit contributions | |
hy | -0.035 |
sed | -0.026 |
alo | -0.025 |
anne | -0.025 |
face | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
First | +0.026 |
Morty | +0.021 |
Sn | +0.021 |
One | +0.021 |
Stri | +0.021 |
Neg logit contributions | |
hy | -0.026 |
thia | -0.023 |
sed | -0.023 |
cousins | -0.022 |
anne | -0.022 |
Token | family |
Token ID | 1641 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
First | +0.024 |
One | +0.020 |
Sn | +0.020 |
Pr | +0.020 |
Morty | +0.019 |
Neg logit contributions | |
hy | -0.017 |
sed | -0.016 |
thia | -0.015 |
cousins | -0.015 |
anne | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
First | +0.020 |
Ro | +0.019 |
Br | +0.018 |
Sn | +0.018 |
Stri | +0.018 |
Neg logit contributions | |
cousins | -0.005 |
hy | -0.005 |
album | -0.004 |
- | -0.004 |
uncle | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
First | +0.028 |
Sn | +0.022 |
Morty | +0.022 |
Pr | +0.022 |
One | +0.022 |
Neg logit contributions | |
cousins | -0.022 |
hy | -0.021 |
sed | -0.021 |
happened | -0.019 |
thia | -0.019 |
Token | rad |
Token ID | 2511 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
First | +0.056 |
Pr | +0.048 |
Morty | +0.048 |
One | +0.048 |
Stri | +0.047 |
Neg logit contributions | |
hy | -0.055 |
anne | -0.051 |
thia | -0.051 |
cousins | -0.050 |
sed | -0.050 |
Token | ishes |
Token ID | 5614 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
First | +0.119 |
One | +0.103 |
Sn | +0.102 |
Morty | +0.101 |
Ro | +0.099 |
Neg logit contributions | |
hy | -0.095 |
sed | -0.091 |
cousins | -0.091 |
thia | -0.091 |
anne | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
First | +0.064 |
Ro | +0.058 |
Pr | +0.057 |
Sn | +0.057 |
One | +0.056 |
Neg logit contributions | |
hy | -0.032 |
cousins | -0.030 |
sed | -0.029 |
happened | -0.029 |
appeared | -0.028 |
Token | One |
Token ID | 1881 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
hy | +0.001 |
Katy | +0.001 |
anne | +0.001 |
thia | +0.001 |
Susan | +0.001 |
Neg logit contributions | |
First | -0.001 |
Pr | -0.001 |
ba | -0.001 |
b | -0.001 |
Sn | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
First | +0.022 |
One | +0.018 |
Pr | +0.017 |
Morty | +0.017 |
Sn | +0.016 |
Neg logit contributions | |
hy | -0.050 |
anne | -0.047 |
sed | -0.047 |
thia | -0.047 |
alo | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
hy | +0.001 |
anne | +0.001 |
thia | +0.001 |
alo | +0.001 |
andra | +0.001 |
Neg logit contributions | |
First | -0.001 |
One | -0.001 |
Finn | -0.001 |
Morty | -0.001 |
D | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
First | +0.023 |
One | +0.020 |
Pr | +0.020 |
Stri | +0.020 |
Morty | +0.020 |
Neg logit contributions | |
hy | -0.016 |
anne | -0.014 |
alo | -0.014 |
thia | -0.014 |
sed | -0.014 |
Token | grew |
Token ID | 6348 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
First | +0.034 |
One | +0.030 |
Pr | +0.030 |
Morty | +0.030 |
Sn | +0.029 |
Neg logit contributions | |
hy | -0.021 |
anne | -0.019 |
thia | -0.018 |
sed | -0.018 |
alo | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
First | +0.046 |
One | +0.040 |
Pr | +0.039 |
Morty | +0.039 |
Sn | +0.038 |
Neg logit contributions | |
hy | -0.042 |
anne | -0.039 |
thia | -0.038 |
alo | -0.038 |
sed | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
First | +0.010 |
Pr | +0.009 |
Morty | +0.009 |
Sn | +0.009 |
One | +0.009 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.007 |
sed | -0.006 |
alo | -0.006 |
thia | -0.006 |
Token | like |
Token ID | 588 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
First | +0.027 |
Pr | +0.024 |
One | +0.024 |
Morty | +0.023 |
Sn | +0.023 |
Neg logit contributions | |
hy | -0.024 |
anne | -0.022 |
thia | -0.021 |
sed | -0.021 |
alo | -0.021 |
Token | mint |
Token ID | 21043 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
First | +0.022 |
Morty | +0.019 |
One | +0.019 |
bowl | +0.019 |
Pr | +0.018 |
Neg logit contributions | |
hy | -0.020 |
sed | -0.018 |
thia | -0.018 |
alo | -0.018 |
cousins | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
First | +0.108 |
Ro | +0.093 |
Stri | +0.092 |
Morty | +0.091 |
One | +0.091 |
Neg logit contributions | |
ly | -0.081 |
hy | -0.079 |
anne | -0.077 |
led | -0.077 |
thia | -0.075 |
Token | rose |
Token ID | 8278 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
First | +0.051 |
Morty | +0.042 |
One | +0.041 |
Pr | +0.041 |
inn | +0.041 |
Neg logit contributions | |
hy | -0.048 |
sed | -0.048 |
thia | -0.047 |
faces | -0.047 |
happened | -0.044 |
Token | mary |
Token ID | 6874 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
First | +0.075 |
One | +0.062 |
Morty | +0.062 |
Pr | +0.061 |
Stri | +0.060 |
Neg logit contributions | |
hy | -0.064 |
alo | -0.060 |
anne | -0.060 |
ly | -0.056 |
thia | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
First | +0.111 |
Pr | +0.095 |
One | +0.095 |
Stri | +0.094 |
Morty | +0.094 |
Neg logit contributions | |
hy | -0.079 |
anne | -0.070 |
ly | -0.069 |
sed | -0.068 |
alo | -0.067 |
Token | They |
Token ID | 1119 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Pr | +0.001 |
First | +0.001 |
stal | +0.001 |
bowl | +0.001 |
log | +0.001 |
Neg logit contributions | |
hy | -0.001 |
thia | -0.001 |
anne | -0.001 |
Katy | -0.001 |
rav | -0.001 |
Token | always |
Token ID | 1464 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
First | +0.028 |
Pr | +0.025 |
Sn | +0.024 |
Morty | +0.024 |
Stri | +0.023 |
Neg logit contributions | |
hy | -0.021 |
thia | -0.019 |
grin | -0.018 |
anne | -0.018 |
sed | -0.017 |
Token | ask |
Token ID | 1265 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
First | +0.033 |
One | +0.029 |
Pr | +0.027 |
Morty | +0.027 |
bowl | +0.026 |
Neg logit contributions | |
hy | -0.041 |
anne | -0.039 |
sed | -0.038 |
alo | -0.038 |
thia | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
First | +0.008 |
One | +0.007 |
Pr | +0.007 |
Sn | +0.007 |
Morty | +0.007 |
Neg logit contributions | |
hy | -0.005 |
anne | -0.005 |
sed | -0.005 |
thia | -0.005 |
alo | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
First | +0.071 |
Sn | +0.061 |
Pr | +0.059 |
One | +0.059 |
Morty | +0.059 |
Neg logit contributions | |
cousins | -0.032 |
hy | -0.030 |
sed | -0.029 |
thia | -0.029 |
uncle | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
First | +0.042 |
Pr | +0.038 |
Sn | +0.037 |
Ro | +0.037 |
Morty | +0.036 |
Neg logit contributions | |
hy | -0.027 |
anne | -0.024 |
cousins | -0.024 |
thia | -0.023 |
rav | -0.022 |
Token | plant |
Token ID | 4618 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
First | +0.038 |
Pr | +0.032 |
Morty | +0.032 |
One | +0.032 |
Sn | +0.032 |
Neg logit contributions | |
hy | -0.032 |
thia | -0.029 |
anne | -0.029 |
sed | -0.028 |
alo | -0.028 |
Token | more |
Token ID | 517 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
First | +0.136 |
Ro | +0.119 |
Sn | +0.117 |
slope | +0.113 |
One | +0.112 |
Neg logit contributions | |
back | -0.059 |
Katy | -0.052 |
- | -0.051 |
face | -0.050 |
appeared | -0.049 |
Token | in |
Token ID | 287 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
First | +0.022 |
Stri | +0.021 |
Ro | +0.020 |
Morty | +0.020 |
Sn | +0.020 |
Neg logit contributions | |
ly | -0.012 |
hy | -0.012 |
anne | -0.012 |
thia | -0.012 |
Katy | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
First | +0.052 |
Stri | +0.047 |
Sn | +0.046 |
Ro | +0.045 |
Morty | +0.044 |
Neg logit contributions | |
Katy | -0.025 |
happened | -0.021 |
Susan | -0.021 |
hy | -0.020 |
framed | -0.020 |
Token | garden |
Token ID | 11376 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
First | +0.027 |
Stri | +0.025 |
Morty | +0.024 |
Pr | +0.023 |
Sn | +0.023 |
Neg logit contributions | |
hy | -0.019 |
anne | -0.018 |
thia | -0.018 |
mailbox | -0.018 |
Katy | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
First | +0.073 |
Sn | +0.064 |
Pr | +0.064 |
Morty | +0.063 |
Ro | +0.062 |
Neg logit contributions | |
hy | -0.049 |
anne | -0.044 |
alo | -0.042 |
thia | -0.040 |
cousins | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
hy | +0.022 |
anne | +0.019 |
thia | +0.019 |
alo | +0.019 |
sed | +0.019 |
Neg logit contributions | |
First | -0.025 |
Pr | -0.021 |
Morty | -0.021 |
One | -0.021 |
Sn | -0.021 |
Token | field |
Token ID | 2214 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
First | +0.007 |
One | +0.006 |
Pr | +0.006 |
Morty | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.010 |
thia | -0.010 |
sed | -0.010 |
alo | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.007 |
Morty | +0.007 |
Sn | +0.007 |
Stri | +0.007 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
thia | -0.004 |
bell | -0.003 |
alo | -0.003 |
Token | started |
Token ID | 2067 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.004 |
hugged | +0.004 |
sed | +0.004 |
happened | +0.004 |
Neg logit contributions | |
First | -0.009 |
One | -0.008 |
Pr | -0.008 |
Morty | -0.008 |
Sn | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
First | +0.074 |
One | +0.066 |
Pr | +0.065 |
Morty | +0.064 |
Sn | +0.063 |
Neg logit contributions | |
hy | -0.020 |
sed | -0.017 |
cousins | -0.016 |
appeared | -0.016 |
happened | -0.016 |
Token | plant |
Token ID | 4618 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
First | +0.026 |
Pr | +0.023 |
Morty | +0.023 |
One | +0.022 |
Sn | +0.022 |
Neg logit contributions | |
hy | -0.017 |
thia | -0.014 |
anne | -0.014 |
grin | -0.014 |
Katy | -0.014 |
Token | seeds |
Token ID | 11904 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
First | +0.136 |
Ro | +0.114 |
One | +0.113 |
Sn | +0.111 |
Pr | +0.110 |
Neg logit contributions | |
back | -0.067 |
appeared | -0.060 |
face | -0.059 |
- | -0.059 |
ed | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
First | +0.050 |
Pr | +0.045 |
Sn | +0.045 |
Morty | +0.044 |
Ro | +0.044 |
Neg logit contributions | |
hy | -0.024 |
alo | -0.021 |
appeared | -0.020 |
ly | -0.020 |
back | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.001 |
thia | +0.001 |
Katy | +0.001 |
bell | +0.001 |
Neg logit contributions | |
Pr | -0.004 |
First | -0.004 |
ba | -0.004 |
st | -0.004 |
One | -0.004 |
Token | worked |
Token ID | 3111 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
First | +0.007 |
Pr | +0.006 |
Morty | +0.006 |
One | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
sed | -0.004 |
thia | -0.004 |
alo | -0.004 |
Token | hard |
Token ID | 1327 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
First | +0.023 |
Pr | +0.021 |
Morty | +0.020 |
Sn | +0.020 |
Ro | +0.019 |
Neg logit contributions | |
hy | -0.016 |
anne | -0.015 |
sed | -0.014 |
thia | -0.014 |
alo | -0.014 |
Token | found |
Token ID | 1043 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
First | +0.016 |
Pr | +0.014 |
One | +0.014 |
Morty | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.008 |
thia | -0.008 |
sed | -0.008 |
alo | -0.007 |
Token | seeds |
Token ID | 11904 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
First | +0.022 |
One | +0.019 |
Pr | +0.019 |
Sn | +0.019 |
Morty | +0.018 |
Neg logit contributions | |
hy | -0.014 |
sed | -0.014 |
ed | -0.013 |
cousins | -0.013 |
Katy | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
First | +0.027 |
Pr | +0.024 |
One | +0.024 |
Morty | +0.023 |
Sn | +0.023 |
Neg logit contributions | |
hy | -0.015 |
anne | -0.013 |
thia | -0.013 |
sed | -0.013 |
alo | -0.013 |
Token | started |
Token ID | 2067 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
First | +0.006 |
One | +0.005 |
Pr | +0.005 |
Morty | +0.005 |
Sn | +0.005 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
First | +0.076 |
Morty | +0.067 |
One | +0.066 |
Sn | +0.065 |
Pr | +0.065 |
Neg logit contributions | |
hy | -0.030 |
sed | -0.027 |
alo | -0.026 |
anne | -0.026 |
thia | -0.026 |
Token | plant |
Token ID | 4618 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
First | +0.039 |
Morty | +0.036 |
Stri | +0.034 |
Finn | +0.034 |
Pr | +0.034 |
Neg logit contributions | |
hy | -0.030 |
thia | -0.027 |
bell | -0.027 |
anne | -0.027 |
grin | -0.026 |
Token | some |
Token ID | 617 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
First | +0.129 |
Sn | +0.108 |
Pr | +0.106 |
One | +0.106 |
Ro | +0.105 |
Neg logit contributions | |
appeared | -0.061 |
back | -0.061 |
alo | -0.060 |
anne | -0.059 |
Katy | -0.058 |
Token | vegetables |
Token ID | 13701 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
First | +0.017 |
Morty | +0.015 |
Pr | +0.014 |
One | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
hy | -0.019 |
anne | -0.018 |
thia | -0.018 |
sed | -0.018 |
alo | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
First | +0.074 |
Ro | +0.067 |
Stri | +0.066 |
Pr | +0.066 |
Sn | +0.066 |
Neg logit contributions | |
hy | -0.035 |
alo | -0.032 |
anne | -0.031 |
ly | -0.031 |
back | -0.030 |
Token | fruits |
Token ID | 15921 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
First | +0.037 |
One | +0.031 |
Pr | +0.031 |
Morty | +0.030 |
Sn | +0.030 |
Neg logit contributions | |
hy | -0.050 |
anne | -0.047 |
thia | -0.046 |
sed | -0.046 |
alo | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
First | +0.041 |
Pr | +0.035 |
Morty | +0.035 |
One | +0.035 |
Sn | +0.035 |
Neg logit contributions | |
hy | -0.032 |
anne | -0.029 |
alo | -0.028 |
thia | -0.027 |
sed | -0.027 |
Token | bit |
Token ID | 1643 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
hy | +0.033 |
anne | +0.032 |
cousins | +0.031 |
thia | +0.031 |
alo | +0.031 |
Neg logit contributions | |
First | -0.024 |
One | -0.022 |
Pr | -0.022 |
Sn | -0.021 |
stream | -0.020 |
Token | better |
Token ID | 1365 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
First | +0.025 |
Stri | +0.022 |
One | +0.022 |
Morty | +0.021 |
Pr | +0.021 |
Neg logit contributions | |
hy | -0.019 |
anne | -0.016 |
ly | -0.016 |
relieved | -0.016 |
grin | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
hy | +0.016 |
anne | +0.014 |
sed | +0.014 |
alo | +0.014 |
thia | +0.014 |
Neg logit contributions | |
First | -0.020 |
Pr | -0.017 |
One | -0.017 |
Morty | -0.017 |
Sn | -0.017 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
First | +0.004 |
Finn | +0.003 |
D | +0.003 |
Morty | +0.003 |
Stri | +0.003 |
Neg logit contributions | |
hy | -0.005 |
alo | -0.005 |
anne | -0.005 |
thia | -0.004 |
sed | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
First | +0.008 |
One | +0.007 |
Pr | +0.007 |
Sn | +0.006 |
Ro | +0.006 |
Neg logit contributions | |
hy | -0.005 |
cousins | -0.005 |
anne | -0.005 |
ly | -0.005 |
Katy | -0.005 |
Token | rad |
Token ID | 2511 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
First | +0.046 |
Stri | +0.041 |
Morty | +0.038 |
Sn | +0.036 |
Pr | +0.034 |
Neg logit contributions | |
hy | -0.045 |
thia | -0.045 |
sed | -0.045 |
grin | -0.044 |
face | -0.044 |
Token | ish |
Token ID | 680 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
First | +0.132 |
One | +0.113 |
Sn | +0.112 |
Stri | +0.110 |
Ro | +0.109 |
Neg logit contributions | |
sed | -0.059 |
ed | -0.058 |
ly | -0.057 |
ushed | -0.054 |
thia | -0.053 |
Token | where |
Token ID | 810 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
First | +0.119 |
Sn | +0.101 |
Ro | +0.099 |
One | +0.097 |
Pr | +0.096 |
Neg logit contributions | |
hy | -0.046 |
goodbye | -0.046 |
back | -0.044 |
anne | -0.042 |
sed | -0.041 |
Token | he |
Token ID | 339 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
hy | +0.032 |
anne | +0.028 |
sed | +0.028 |
happened | +0.028 |
Katy | +0.027 |
Neg logit contributions | |
First | -0.027 |
One | -0.022 |
Pr | -0.022 |
Sn | -0.021 |
Morty | -0.020 |
Token | could |
Token ID | 714 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
First | +0.025 |
One | +0.024 |
Stri | +0.022 |
Morty | +0.022 |
Finn | +0.022 |
Neg logit contributions | |
hy | -0.024 |
alo | -0.023 |
anne | -0.023 |
thia | -0.022 |
cousins | -0.021 |
Token | find |
Token ID | 1064 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.007 |
One | +0.007 |
Morty | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
First | +0.032 |
Pr | +0.028 |
Morty | +0.027 |
One | +0.027 |
Stri | +0.027 |
Neg logit contributions | |
hy | -0.023 |
anne | -0.020 |
thia | -0.020 |
alo | -0.019 |
sed | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
First | +0.037 |
Pr | +0.032 |
One | +0.031 |
Sn | +0.030 |
Morty | +0.030 |
Neg logit contributions | |
hy | -0.036 |
anne | -0.032 |
thia | -0.031 |
sed | -0.031 |
alo | -0.031 |
Token | certain |
Token ID | 1728 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
First | +0.022 |
Pr | +0.019 |
One | +0.019 |
Stri | +0.018 |
Morty | +0.018 |
Neg logit contributions | |
hy | -0.019 |
anne | -0.018 |
sed | -0.017 |
thia | -0.017 |
alo | -0.017 |
Token | food |
Token ID | 2057 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
First | +0.021 |
Pr | +0.018 |
Sn | +0.017 |
Stri | +0.017 |
One | +0.017 |
Neg logit contributions | |
hy | -0.018 |
anne | -0.017 |
sed | -0.017 |
alo | -0.016 |
thia | -0.016 |
Token | : |
Token ID | 25 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.007 |
One | +0.007 |
Sn | +0.007 |
Morty | +0.007 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.005 |
sed | -0.005 |
alo | -0.005 |
cousins | -0.005 |
Token | rad |
Token ID | 2511 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
First | +0.053 |
Pr | +0.045 |
Sn | +0.043 |
One | +0.043 |
Morty | +0.042 |
Neg logit contributions | |
hy | -0.046 |
sed | -0.041 |
thia | -0.040 |
anne | -0.040 |
cousins | -0.039 |
Token | ishes |
Token ID | 5614 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
First | +0.098 |
One | +0.083 |
Pr | +0.082 |
Sn | +0.080 |
Morty | +0.079 |
Neg logit contributions | |
hy | -0.097 |
sed | -0.091 |
anne | -0.090 |
thia | -0.089 |
cousins | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
First | +0.070 |
Pr | +0.063 |
One | +0.061 |
Sn | +0.060 |
Ro | +0.059 |
Neg logit contributions | |
hy | -0.048 |
anne | -0.040 |
sed | -0.039 |
happened | -0.039 |
thia | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
hy | +0.009 |
thia | +0.009 |
anne | +0.009 |
Katy | +0.008 |
cousins | +0.008 |
Neg logit contributions | |
Pr | -0.008 |
First | -0.008 |
stream | -0.007 |
Morty | -0.007 |
bowl | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
anne | +0.010 |
hy | +0.009 |
thia | +0.009 |
Jennifer | +0.009 |
rav | +0.008 |
Neg logit contributions | |
First | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
stream | -0.009 |
Pr | -0.008 |
Token | James |
Token ID | 14731 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.005 |
thia | +0.005 |
cousins | +0.005 |
bell | +0.004 |
Neg logit contributions | |
First | -0.001 |
Pr | -0.001 |
Morty | -0.001 |
D | -0.001 |
Stri | -0.001 |
Token | potatoes |
Token ID | 18821 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
First | +0.013 |
One | +0.011 |
Pr | +0.011 |
Morty | +0.011 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.016 |
anne | -0.015 |
thia | -0.015 |
sed | -0.015 |
alo | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
First | +0.075 |
Pr | +0.070 |
One | +0.069 |
Sn | +0.068 |
Ro | +0.068 |
Neg logit contributions | |
hy | -0.027 |
sed | -0.023 |
anne | -0.023 |
thia | -0.022 |
alo | -0.022 |
Token | carrots |
Token ID | 34397 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
First | +0.020 |
Pr | +0.018 |
One | +0.018 |
Morty | +0.018 |
Sn | +0.018 |
Neg logit contributions | |
hy | -0.010 |
thia | -0.009 |
anne | -0.009 |
sed | -0.009 |
alo | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
First | +0.072 |
Pr | +0.066 |
Sn | +0.065 |
One | +0.065 |
Ro | +0.065 |
Neg logit contributions | |
hy | -0.024 |
sed | -0.020 |
anne | -0.019 |
alo | -0.018 |
thia | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
First | +0.019 |
One | +0.017 |
Pr | +0.017 |
Morty | +0.016 |
Sn | +0.016 |
Neg logit contributions | |
hy | -0.011 |
anne | -0.009 |
thia | -0.009 |
sed | -0.009 |
alo | -0.009 |
Token | onions |
Token ID | 24681 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
First | +0.019 |
Pr | +0.016 |
One | +0.016 |
Morty | +0.016 |
Sn | +0.015 |
Neg logit contributions | |
hy | -0.027 |
thia | -0.025 |
anne | -0.025 |
sed | -0.024 |
cousins | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
First | +0.130 |
Ro | +0.124 |
Pr | +0.122 |
One | +0.119 |
Sn | +0.117 |
Neg logit contributions | |
hy | -0.054 |
ly | -0.051 |
ed | -0.051 |
appeared | -0.049 |
led | -0.048 |
Token | It |
Token ID | 632 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Pr | +0.009 |
First | +0.009 |
ba | +0.009 |
b | +0.008 |
st | +0.008 |
Neg logit contributions | |
hy | -0.004 |
Someone | -0.003 |
Katy | -0.003 |
thia | -0.003 |
Sarah | -0.003 |
Token | smelled |
Token ID | 37609 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
First | +0.011 |
Pr | +0.010 |
Stri | +0.010 |
One | +0.010 |
Morty | +0.010 |
Neg logit contributions | |
anne | -0.004 |
thia | -0.004 |
hy | -0.003 |
happened | -0.003 |
led | -0.003 |
Token | delicious |
Token ID | 12625 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
First | +0.028 |
Pr | +0.024 |
One | +0.024 |
Morty | +0.024 |
Stri | +0.024 |
Neg logit contributions | |
hy | -0.023 |
anne | -0.021 |
thia | -0.020 |
sed | -0.020 |
alo | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
First | +0.023 |
One | +0.021 |
Pr | +0.021 |
Morty | +0.020 |
Sn | +0.020 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.016 |
thia | -0.015 |
sed | -0.015 |
alo | -0.015 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.002 |
sed | +0.002 |
thia | +0.002 |
alo | +0.002 |
Neg logit contributions | |
First | -0.006 |
One | -0.006 |
Pr | -0.006 |
Morty | -0.005 |
Sn | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
First | +0.037 |
One | +0.031 |
Pr | +0.031 |
Sn | +0.030 |
bowl | +0.030 |
Neg logit contributions | |
hy | -0.023 |
anne | -0.020 |
sed | -0.020 |
alo | -0.020 |
thia | -0.020 |
Token | Lilly |
Token ID | 35134 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
First | +0.061 |
One | +0.046 |
bowl | +0.045 |
bank | +0.044 |
Sn | +0.043 |
Neg logit contributions | |
ige | -0.056 |
dear | -0.055 |
hy | -0.054 |
face | -0.054 |
grin | -0.053 |
Token | ," |
Token ID | 553 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
First | +0.066 |
One | +0.057 |
Pr | +0.056 |
Sn | +0.055 |
Morty | +0.054 |
Neg logit contributions | |
hy | -0.064 |
anne | -0.061 |
thia | -0.056 |
sed | -0.056 |
alo | -0.054 |
Token | said |
Token ID | 531 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
First | +0.054 |
One | +0.046 |
Ro | +0.045 |
slope | +0.045 |
ipples | +0.045 |
Neg logit contributions | |
hy | -0.028 |
hugged | -0.028 |
Katy | -0.028 |
Jennifer | -0.026 |
face | -0.025 |
Token | D |
Token ID | 360 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
First | +0.022 |
One | +0.018 |
Ro | +0.016 |
bowl | +0.016 |
Sn | +0.016 |
Neg logit contributions | |
hy | -0.026 |
Katy | -0.024 |
sed | -0.023 |
alo | -0.023 |
grin | -0.022 |
Token | alia |
Token ID | 9752 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
First | +0.107 |
One | +0.091 |
Sn | +0.088 |
stream | +0.088 |
Stri | +0.087 |
Neg logit contributions | |
hy | -0.082 |
rav | -0.081 |
ly | -0.080 |
anne | -0.080 |
ige | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
First | +0.012 |
One | +0.010 |
Pr | +0.010 |
Morty | +0.010 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
thia | -0.009 |
sed | -0.009 |
alo | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
First | +0.001 |
Pr | +0.001 |
Morty | +0.001 |
One | +0.001 |
Stri | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | but |
Token ID | 4360 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
First | +0.010 |
Morty | +0.009 |
Stri | +0.009 |
Pr | +0.009 |
Pr | +0.008 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.009 |
thia | -0.009 |
alo | -0.008 |
rav | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
First | +0.004 |
One | +0.004 |
Pr | +0.004 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.003 |
thia | -0.003 |
sed | -0.003 |
alo | -0.003 |
Token | like |
Token ID | 588 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
First | +0.021 |
One | +0.018 |
Pr | +0.018 |
Morty | +0.018 |
Sn | +0.017 |
Neg logit contributions | |
hy | -0.024 |
anne | -0.023 |
thia | -0.022 |
sed | -0.022 |
alo | -0.022 |
Token | cheese |
Token ID | 9891 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
First | +0.018 |
Pr | +0.016 |
One | +0.016 |
Sn | +0.015 |
Morty | +0.015 |
Neg logit contributions | |
hy | -0.013 |
sed | -0.011 |
cousins | -0.011 |
thia | -0.011 |
Katy | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
First | +0.063 |
Pr | +0.057 |
One | +0.055 |
Sn | +0.055 |
Morty | +0.053 |
Neg logit contributions | |
hy | -0.044 |
anne | -0.040 |
sed | -0.039 |
alo | -0.039 |
thia | -0.039 |
Token | tomatoes |
Token ID | 23972 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
First | +0.025 |
Pr | +0.022 |
One | +0.021 |
Morty | +0.021 |
Sn | +0.021 |
Neg logit contributions | |
hy | -0.027 |
anne | -0.025 |
thia | -0.025 |
sed | -0.025 |
alo | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
First | +0.081 |
Pr | +0.073 |
One | +0.072 |
Sn | +0.071 |
Morty | +0.071 |
Neg logit contributions | |
hy | -0.046 |
anne | -0.040 |
sed | -0.040 |
thia | -0.039 |
alo | -0.039 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
First | +0.025 |
Pr | +0.020 |
Morty | +0.020 |
One | +0.020 |
Sn | +0.020 |
Neg logit contributions | |
hy | -0.032 |
thia | -0.030 |
anne | -0.030 |
sed | -0.030 |
alo | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
First | +0.118 |
Pr | +0.105 |
One | +0.104 |
Sn | +0.104 |
Ro | +0.104 |
Neg logit contributions | |
hy | -0.070 |
sed | -0.067 |
alo | -0.065 |
anne | -0.064 |
thia | -0.063 |
Token | They |
Token ID | 1119 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
First | +0.013 |
Pr | +0.011 |
One | +0.011 |
Morty | +0.011 |
Sn | +0.011 |
Neg logit contributions | |
hy | -0.011 |
anne | -0.010 |
thia | -0.010 |
sed | -0.010 |
alo | -0.009 |
Token | cut |
Token ID | 2005 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
First | +0.019 |
Pr | +0.017 |
Morty | +0.017 |
One | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
hy | -0.011 |
anne | -0.011 |
thia | -0.011 |
sed | -0.010 |
hugged | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
First | +0.026 |
One | +0.022 |
Pr | +0.022 |
Morty | +0.022 |
Sn | +0.022 |
Neg logit contributions | |
hy | -0.029 |
anne | -0.028 |
thia | -0.027 |
sed | -0.027 |
alo | -0.026 |
Token | ingredients |
Token ID | 9391 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
First | +0.009 |
One | +0.008 |
Pr | +0.008 |
Morty | +0.008 |
Sn | +0.008 |
Neg logit contributions | |
hy | -0.012 |
anne | -0.011 |
thia | -0.011 |
alo | -0.011 |
sed | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
First | +0.017 |
One | +0.015 |
Morty | +0.014 |
Sn | +0.014 |
Stri | +0.014 |
Neg logit contributions | |
hy | -0.016 |
alo | -0.016 |
rav | -0.015 |
sed | -0.014 |
anne | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
hy | +0.001 |
anne | +0.001 |
thia | +0.001 |
sed | +0.001 |
Katy | +0.001 |
Neg logit contributions | |
First | -0.002 |
Pr | -0.002 |
One | -0.002 |
Sn | -0.002 |
Morty | -0.002 |
Token | help |
Token ID | 1037 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.007 |
One | +0.007 |
Morty | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
alo | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.002 |
thia | +0.002 |
sed | +0.002 |
alo | +0.002 |
Neg logit contributions | |
First | -0.003 |
Pr | -0.002 |
One | -0.002 |
Morty | -0.002 |
Sn | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
First | +0.036 |
Pr | +0.034 |
Ro | +0.032 |
Stri | +0.032 |
Sn | +0.032 |
Neg logit contributions | |
hy | -0.017 |
face | -0.017 |
grin | -0.016 |
anne | -0.015 |
back | -0.015 |
Token | rad |
Token ID | 2511 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
First | +0.032 |
Pr | +0.027 |
One | +0.026 |
Sn | +0.026 |
Morty | +0.025 |
Neg logit contributions | |
hy | -0.024 |
Katy | -0.021 |
sed | -0.020 |
thia | -0.020 |
happened | -0.020 |
Token | ishes |
Token ID | 5614 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
First | +0.095 |
One | +0.081 |
Pr | +0.080 |
Sn | +0.079 |
Morty | +0.079 |
Neg logit contributions | |
hy | -0.094 |
anne | -0.088 |
sed | -0.088 |
thia | -0.087 |
cousins | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
First | +0.066 |
Pr | +0.059 |
One | +0.057 |
Sn | +0.057 |
Ro | +0.057 |
Neg logit contributions | |
hy | -0.039 |
anne | -0.032 |
alo | -0.031 |
grin | -0.031 |
ly | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
hy | +0.016 |
anne | +0.015 |
thia | +0.014 |
sed | +0.014 |
alo | +0.014 |
Neg logit contributions | |
First | -0.015 |
One | -0.013 |
Pr | -0.013 |
Morty | -0.012 |
Sn | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
hy | +0.027 |
anne | +0.025 |
thia | +0.025 |
alo | +0.024 |
sed | +0.024 |
Neg logit contributions | |
First | -0.015 |
Pr | -0.013 |
Morty | -0.013 |
Stri | -0.012 |
One | -0.012 |
Token | So |
Token ID | 2396 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
hy | +0.019 |
anne | +0.018 |
thia | +0.018 |
sed | +0.017 |
alo | +0.017 |
Neg logit contributions | |
First | -0.014 |
One | -0.012 |
Pr | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
First | +0.024 |
One | +0.021 |
Pr | +0.021 |
Sn | +0.020 |
Morty | +0.020 |
Neg logit contributions | |
Katy | -0.015 |
hy | -0.014 |
anne | -0.013 |
thia | -0.013 |
alo | -0.013 |
Token | wagon |
Token ID | 31860 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
First | +0.005 |
One | +0.005 |
Pr | +0.004 |
Morty | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
alo | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
First | +0.015 |
Pr | +0.014 |
Morty | +0.013 |
Stri | +0.013 |
One | +0.013 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.008 |
alo | -0.008 |
thia | -0.008 |
sed | -0.008 |
Token | soil |
Token ID | 9260 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
hy | +0.016 |
faces | +0.015 |
face | +0.014 |
sed | +0.014 |
cousins | +0.014 |
Neg logit contributions | |
First | -0.015 |
Morty | -0.013 |
One | -0.013 |
Pr | -0.013 |
Stri | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
First | +0.103 |
Pr | +0.096 |
Ro | +0.095 |
One | +0.094 |
Sn | +0.093 |
Neg logit contributions | |
hy | -0.033 |
ly | -0.033 |
back | -0.031 |
alo | -0.030 |
sed | -0.029 |
Token | plant |
Token ID | 4618 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
First | +0.031 |
One | +0.026 |
Pr | +0.026 |
Morty | +0.026 |
Sn | +0.025 |
Neg logit contributions | |
hy | -0.038 |
anne | -0.035 |
thia | -0.035 |
sed | -0.035 |
alo | -0.034 |
Token | some |
Token ID | 617 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
First | +0.116 |
Ro | +0.106 |
One | +0.105 |
Morty | +0.099 |
Pr | +0.098 |
Neg logit contributions | |
ed | -0.064 |
back | -0.064 |
- | -0.062 |
appeared | -0.061 |
faces | -0.061 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
First | +0.017 |
Morty | +0.015 |
Stri | +0.014 |
Pr | +0.014 |
One | +0.014 |
Neg logit contributions | |
hy | -0.023 |
sed | -0.021 |
thia | -0.021 |
anne | -0.021 |
alo | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
First | +0.033 |
Morty | +0.030 |
Pr | +0.029 |
One | +0.029 |
Sn | +0.029 |
Neg logit contributions | |
hy | -0.020 |
alo | -0.019 |
anne | -0.018 |
sed | -0.018 |
thia | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.002 |
Katy | +0.002 |
sed | +0.002 |
thia | +0.002 |
Neg logit contributions | |
First | -0.006 |
Pr | -0.006 |
One | -0.006 |
ba | -0.005 |
bowl | -0.005 |
Token | took |
Token ID | 1718 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
First | +0.014 |
Pr | +0.012 |
Morty | +0.012 |
One | +0.012 |
Stri | +0.012 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.010 |
thia | -0.009 |
sed | -0.009 |
alo | -0.009 |
Token | bed |
Token ID | 3996 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
First | +0.059 |
Pr | +0.051 |
One | +0.050 |
Sn | +0.049 |
Morty | +0.049 |
Neg logit contributions | |
hy | -0.050 |
anne | -0.047 |
thia | -0.046 |
sed | -0.045 |
alo | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
First | +0.007 |
One | +0.006 |
Pr | +0.006 |
Morty | +0.006 |
Sn | +0.005 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token | happily |
Token ID | 18177 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
First | +0.051 |
One | +0.044 |
Pr | +0.044 |
Morty | +0.043 |
Sn | +0.042 |
Neg logit contributions | |
hy | -0.047 |
anne | -0.044 |
thia | -0.043 |
sed | -0.042 |
alo | -0.042 |
Token | dream |
Token ID | 4320 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
First | +0.035 |
One | +0.030 |
Pr | +0.030 |
Morty | +0.030 |
Sn | +0.029 |
Neg logit contributions | |
hy | -0.035 |
anne | -0.032 |
thia | -0.031 |
sed | -0.031 |
alo | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
hy | +0.004 |
anne | +0.004 |
thia | +0.004 |
alo | +0.003 |
sed | +0.003 |
Neg logit contributions | |
First | -0.005 |
Pr | -0.004 |
One | -0.004 |
Morty | -0.004 |
Sn | -0.004 |
Token | rad |
Token ID | 2511 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
First | +0.023 |
Pr | +0.019 |
Sn | +0.018 |
One | +0.018 |
Morty | +0.018 |
Neg logit contributions | |
hy | -0.019 |
sed | -0.017 |
thia | -0.017 |
anne | -0.017 |
cousins | -0.017 |
Token | ishes |
Token ID | 5614 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
First | +0.102 |
One | +0.088 |
Sn | +0.085 |
Pr | +0.085 |
Morty | +0.085 |
Neg logit contributions | |
hy | -0.084 |
thia | -0.080 |
anne | -0.079 |
sed | -0.079 |
cousins | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
First | +0.055 |
Pr | +0.049 |
One | +0.048 |
Sn | +0.047 |
Morty | +0.045 |
Neg logit contributions | |
hy | -0.045 |
anne | -0.040 |
alo | -0.038 |
thia | -0.038 |
sed | -0.037 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
First | +0.003 |
Pr | +0.003 |
One | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.005 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
rav | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
First | +0.029 |
Pr | +0.026 |
Morty | +0.023 |
Sn | +0.023 |
One | +0.022 |
Neg logit contributions | |
hy | -0.036 |
anne | -0.035 |
happened | -0.033 |
thia | -0.033 |
appeared | -0.032 |
Token | there |
Token ID | 612 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
First | +0.017 |
Pr | +0.015 |
One | +0.014 |
Morty | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
hy | -0.022 |
anne | -0.021 |
thia | -0.020 |
sed | -0.020 |
alo | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
First | +0.010 |
Pr | +0.009 |
Morty | +0.009 |
Sn | +0.009 |
One | +0.009 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.007 |
sed | -0.006 |
alo | -0.006 |
thia | -0.006 |
Token | like |
Token ID | 588 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
First | +0.027 |
Pr | +0.024 |
One | +0.024 |
Morty | +0.023 |
Sn | +0.023 |
Neg logit contributions | |
hy | -0.024 |
anne | -0.022 |
thia | -0.021 |
sed | -0.021 |
alo | -0.021 |
Token | mint |
Token ID | 21043 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
First | +0.022 |
Morty | +0.019 |
One | +0.019 |
bowl | +0.019 |
Pr | +0.018 |
Neg logit contributions | |
hy | -0.020 |
sed | -0.018 |
thia | -0.018 |
alo | -0.018 |
cousins | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
First | +0.108 |
Ro | +0.093 |
Stri | +0.092 |
Morty | +0.091 |
One | +0.091 |
Neg logit contributions | |
ly | -0.081 |
hy | -0.079 |
anne | -0.077 |
led | -0.077 |
thia | -0.075 |
Token | rose |
Token ID | 8278 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
First | +0.051 |
Morty | +0.042 |
One | +0.041 |
Pr | +0.041 |
inn | +0.041 |
Neg logit contributions | |
hy | -0.048 |
sed | -0.048 |
thia | -0.047 |
faces | -0.047 |
happened | -0.044 |
Token | mary |
Token ID | 6874 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
First | +0.075 |
One | +0.062 |
Morty | +0.062 |
Pr | +0.061 |
Stri | +0.060 |
Neg logit contributions | |
hy | -0.064 |
alo | -0.060 |
anne | -0.060 |
ly | -0.056 |
thia | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
First | +0.111 |
Pr | +0.095 |
One | +0.095 |
Stri | +0.094 |
Morty | +0.094 |
Neg logit contributions | |
hy | -0.079 |
anne | -0.070 |
ly | -0.069 |
sed | -0.068 |
alo | -0.067 |
Token | They |
Token ID | 1119 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
Pr | +0.001 |
First | +0.001 |
stal | +0.001 |
bowl | +0.001 |
log | +0.001 |
Neg logit contributions | |
hy | -0.001 |
thia | -0.001 |
anne | -0.001 |
Katy | -0.001 |
rav | -0.001 |
Token | liked |
Token ID | 8288 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
First | +0.017 |
Morty | +0.015 |
Pr | +0.015 |
Sn | +0.015 |
Stri | +0.015 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
thia | -0.009 |
sed | -0.008 |
cousins | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
First | +0.031 |
Pr | +0.027 |
Morty | +0.027 |
One | +0.027 |
Sn | +0.026 |
Neg logit contributions | |
hy | -0.012 |
sed | -0.011 |
anne | -0.011 |
thia | -0.011 |
alo | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
First | +0.025 |
Pr | +0.022 |
One | +0.021 |
Morty | +0.021 |
Sn | +0.021 |
Neg logit contributions | |
hy | -0.023 |
anne | -0.021 |
thia | -0.021 |
sed | -0.021 |
alo | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
First | +0.012 |
Pr | +0.011 |
Sn | +0.011 |
One | +0.011 |
Stri | +0.011 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.005 |
sed | -0.005 |
thia | -0.005 |
alo | -0.004 |
Token | brought |
Token ID | 3181 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
First | +0.034 |
One | +0.031 |
Pr | +0.030 |
Sn | +0.029 |
Morty | +0.027 |
Neg logit contributions | |
hy | -0.029 |
sed | -0.027 |
anne | -0.025 |
thia | -0.025 |
cousins | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
First | +0.042 |
One | +0.037 |
Pr | +0.037 |
Sn | +0.036 |
Morty | +0.034 |
Neg logit contributions | |
hy | -0.030 |
anne | -0.027 |
Katy | -0.026 |
sed | -0.026 |
ed | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
First | +0.040 |
Pr | +0.038 |
Morty | +0.036 |
One | +0.036 |
Sn | +0.036 |
Neg logit contributions | |
hy | -0.011 |
sed | -0.008 |
anne | -0.008 |
thia | -0.007 |
alo | -0.007 |
Token | D |
Token ID | 360 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
First | +0.048 |
One | +0.037 |
Sn | +0.036 |
Pr | +0.036 |
bowl | +0.035 |
Neg logit contributions | |
hy | -0.036 |
sed | -0.033 |
face | -0.031 |
Katy | -0.030 |
goodbye | -0.030 |
Token | ucky |
Token ID | 5309 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
First | +0.084 |
Pr | +0.068 |
Stri | +0.068 |
Sn | +0.065 |
One | +0.065 |
Neg logit contributions | |
hy | -0.085 |
anne | -0.083 |
rav | -0.081 |
ly | -0.081 |
sed | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
First | +0.138 |
Pr | +0.131 |
Ro | +0.126 |
Sn | +0.125 |
One | +0.125 |
Neg logit contributions | |
back | -0.051 |
hy | -0.047 |
face | -0.045 |
goodbye | -0.043 |
cousins | -0.041 |
Token | D |
Token ID | 360 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
First | +0.032 |
One | +0.028 |
Pr | +0.027 |
ba | +0.026 |
Bee | +0.024 |
Neg logit contributions | |
relieved | -0.031 |
sed | -0.029 |
ed | -0.029 |
hy | -0.029 |
goodbye | -0.028 |
Token | ucky |
Token ID | 5309 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
First | +0.051 |
One | +0.042 |
Pr | +0.041 |
Stri | +0.040 |
Sn | +0.039 |
Neg logit contributions | |
hy | -0.068 |
anne | -0.063 |
sed | -0.063 |
rav | -0.063 |
thia | -0.062 |
Token | was |
Token ID | 373 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
First | +0.037 |
Pr | +0.033 |
One | +0.033 |
Morty | +0.032 |
Sn | +0.032 |
Neg logit contributions | |
hy | -0.014 |
sed | -0.014 |
thia | -0.013 |
anne | -0.013 |
hugged | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.007 |
thia | +0.006 |
sed | +0.006 |
alo | +0.006 |
Neg logit contributions | |
First | -0.009 |
Pr | -0.008 |
One | -0.008 |
Morty | -0.008 |
Sn | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
First | +0.096 |
One | +0.082 |
Ro | +0.080 |
Pr | +0.080 |
Stri | +0.079 |
Neg logit contributions | |
hy | -0.077 |
ly | -0.074 |
anne | -0.074 |
led | -0.071 |
thia | -0.070 |
Token | basil |
Token ID | 37792 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
First | +0.039 |
One | +0.031 |
Pr | +0.031 |
Morty | +0.031 |
Sn | +0.030 |
Neg logit contributions | |
hy | -0.041 |
sed | -0.038 |
thia | -0.038 |
alo | -0.036 |
cousins | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
First | +0.122 |
One | +0.109 |
Pr | +0.108 |
Sn | +0.106 |
Stri | +0.105 |
Neg logit contributions | |
hy | -0.052 |
sed | -0.046 |
anne | -0.045 |
alo | -0.044 |
thia | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
First | +0.033 |
One | +0.026 |
Morty | +0.026 |
Pr | +0.026 |
Sn | +0.025 |
Neg logit contributions | |
hy | -0.038 |
sed | -0.036 |
thia | -0.036 |
anne | -0.035 |
alo | -0.035 |
Token | rose |
Token ID | 8278 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
First | +0.035 |
Morty | +0.028 |
One | +0.028 |
Sn | +0.028 |
Stri | +0.027 |
Neg logit contributions | |
hy | -0.040 |
sed | -0.038 |
thia | -0.036 |
cousins | -0.036 |
faces | -0.035 |
Token | mary |
Token ID | 6874 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
First | +0.071 |
One | +0.058 |
Pr | +0.057 |
Morty | +0.056 |
bowl | +0.056 |
Neg logit contributions | |
hy | -0.058 |
alo | -0.053 |
anne | -0.053 |
sed | -0.051 |
thia | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
First | +0.118 |
One | +0.101 |
Pr | +0.100 |
Stri | +0.098 |
Morty | +0.097 |
Neg logit contributions | |
hy | -0.069 |
ly | -0.063 |
anne | -0.059 |
ed | -0.058 |
alo | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
First | +0.011 |
b | +0.011 |
Pr | +0.011 |
ba | +0.011 |
stream | +0.011 |
Neg logit contributions | |
anne | -0.008 |
thia | -0.008 |
hy | -0.008 |
Katy | -0.007 |
sed | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Ot | +0.008 |
minerals | +0.008 |
Morty | +0.008 |
cuc | +0.008 |
wood | +0.008 |
Neg logit contributions | |
anne | -0.008 |
thia | -0.007 |
hy | -0.007 |
Jennifer | -0.007 |
bell | -0.006 |
Token | One |
Token ID | 3198 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Stri | +0.010 |
Ot | +0.010 |
O | +0.009 |
Finn | +0.009 |
bank | +0.009 |
Neg logit contributions | |
anne | -0.021 |
thia | -0.020 |
Jennifer | -0.020 |
hy | -0.019 |
bell | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
First | +0.040 |
Stri | +0.034 |
Morty | +0.033 |
Sn | +0.033 |
Pr | +0.032 |
Neg logit contributions | |
anne | -0.048 |
hy | -0.046 |
thia | -0.043 |
rav | -0.042 |
sed | -0.042 |
Token | not |
Token ID | 407 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
hy | +0.012 |
sed | +0.011 |
anne | +0.011 |
thia | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.010 |
One | -0.010 |
Morty | -0.009 |
Sn | -0.009 |
Stri | -0.009 |
Token | hear |
Token ID | 3285 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
hy | +0.018 |
sed | +0.018 |
anne | +0.017 |
thia | +0.017 |
alo | +0.016 |
Neg logit contributions | |
First | -0.027 |
One | -0.025 |
Pr | -0.024 |
Morty | -0.023 |
Sn | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.003 |
alo | +0.003 |
thia | +0.003 |
sed | +0.003 |
Neg logit contributions | |
First | -0.004 |
One | -0.004 |
Pr | -0.004 |
Morty | -0.004 |
Sn | -0.003 |
Token | Hello |
Token ID | 15496 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
First | +0.015 |
Morty | +0.014 |
Finn | +0.014 |
log | +0.014 |
First | +0.013 |
Neg logit contributions | |
hy | -0.015 |
rav | -0.013 |
bell | -0.013 |
ed | -0.013 |
happened | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
First | +0.035 |
Pr | +0.029 |
One | +0.029 |
Sn | +0.028 |
Morty | +0.028 |
Neg logit contributions | |
hy | -0.031 |
anne | -0.028 |
thia | -0.028 |
alo | -0.027 |
sed | -0.027 |
Token | pepper |
Token ID | 13385 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
First | +0.019 |
Pr | +0.017 |
One | +0.017 |
Morty | +0.017 |
Stri | +0.016 |
Neg logit contributions | |
hy | -0.020 |
anne | -0.019 |
thia | -0.018 |
sed | -0.018 |
alo | -0.018 |
Token | ". |
Token ID | 1911 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
First | +0.120 |
One | +0.097 |
Pr | +0.095 |
First | +0.094 |
Sn | +0.093 |
Neg logit contributions | |
hy | -0.072 |
anne | -0.071 |
thia | -0.068 |
sed | -0.065 |
appeared | -0.064 |
Token | She |
Token ID | 1375 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
First | +0.014 |
Pr | +0.012 |
One | +0.012 |
Morty | +0.012 |
Sn | +0.012 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
thia | -0.009 |
sed | -0.009 |
alo | -0.009 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
hy | +0.015 |
rav | +0.014 |
alo | +0.014 |
anne | +0.014 |
agged | +0.013 |
Neg logit contributions | |
First | -0.011 |
Stri | -0.011 |
One | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
hy | +0.036 |
anne | +0.034 |
sed | +0.033 |
thia | +0.033 |
alo | +0.032 |
Neg logit contributions | |
First | -0.032 |
One | -0.028 |
Pr | -0.028 |
Morty | -0.027 |
Sn | -0.026 |
Token | loud |
Token ID | 7812 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.012 |
thia | +0.012 |
sed | +0.011 |
alo | +0.011 |
Neg logit contributions | |
First | -0.017 |
Pr | -0.016 |
One | -0.016 |
stream | -0.016 |
Morty | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
First | +0.030 |
Pr | +0.026 |
One | +0.026 |
Morty | +0.026 |
Sn | +0.026 |
Neg logit contributions | |
hy | -0.020 |
anne | -0.018 |
thia | -0.017 |
sed | -0.017 |
alo | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
First | +0.010 |
Pr | +0.009 |
One | +0.009 |
Sn | +0.009 |
Morty | +0.008 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.008 |
sed | -0.007 |
thia | -0.007 |
alo | -0.007 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
First | +0.026 |
Pr | +0.023 |
One | +0.022 |
Morty | +0.022 |
Sn | +0.022 |
Neg logit contributions | |
hy | -0.014 |
anne | -0.014 |
sed | -0.013 |
thia | -0.013 |
witnessed | -0.012 |
Token | asking |
Token ID | 4737 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
First | +0.050 |
Pr | +0.042 |
Sn | +0.042 |
One | +0.041 |
Morty | +0.041 |
Neg logit contributions | |
hy | -0.025 |
sed | -0.023 |
anne | -0.022 |
alo | -0.021 |
thia | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
First | +0.020 |
One | +0.017 |
Pr | +0.017 |
Sn | +0.017 |
Morty | +0.016 |
Neg logit contributions | |
hy | -0.016 |
anne | -0.015 |
sed | -0.014 |
thia | -0.014 |
alo | -0.014 |
Token | rad |
Token ID | 2511 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
First | +0.060 |
Stri | +0.057 |
Morty | +0.053 |
Sn | +0.051 |
First | +0.048 |
Neg logit contributions | |
face | -0.046 |
sed | -0.046 |
mailbox | -0.045 |
thia | -0.045 |
back | -0.044 |
Token | ish |
Token ID | 680 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
First | +0.121 |
Sn | +0.105 |
Ro | +0.105 |
One | +0.105 |
Stri | +0.102 |
Neg logit contributions | |
sed | -0.059 |
ly | -0.057 |
thia | -0.057 |
ed | -0.056 |
elled | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
First | +0.077 |
Sn | +0.070 |
Pr | +0.068 |
Ro | +0.066 |
Stri | +0.065 |
Neg logit contributions | |
hy | -0.050 |
anne | -0.046 |
sed | -0.044 |
goodbye | -0.043 |
thia | -0.043 |
Token | surrender |
Token ID | 16908 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
First | +0.029 |
Pr | +0.025 |
Sn | +0.025 |
Morty | +0.025 |
One | +0.024 |
Neg logit contributions | |
hy | -0.020 |
anne | -0.017 |
thia | -0.017 |
sed | -0.017 |
alo | -0.016 |
Token | until |
Token ID | 1566 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
First | +0.030 |
One | +0.026 |
Pr | +0.026 |
Sn | +0.025 |
Morty | +0.025 |
Neg logit contributions | |
hy | -0.026 |
anne | -0.024 |
thia | -0.023 |
sed | -0.023 |
alo | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
First | +0.040 |
Pr | +0.033 |
Sn | +0.033 |
One | +0.032 |
bowl | +0.031 |
Neg logit contributions | |
hy | -0.035 |
anne | -0.031 |
sed | -0.031 |
Katy | -0.031 |
alo | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
hy | +0.019 |
anne | +0.019 |
thia | +0.018 |
sed | +0.018 |
rav | +0.017 |
Neg logit contributions | |
First | -0.013 |
O | -0.012 |
Morty | -0.012 |
Pr | -0.011 |
Finn | -0.011 |
Token | showed |
Token ID | 3751 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
First | +0.036 |
One | +0.032 |
Pr | +0.032 |
Morty | +0.031 |
Sn | +0.031 |
Neg logit contributions | |
hy | -0.023 |
anne | -0.021 |
thia | -0.020 |
sed | -0.020 |
alo | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.010 |
sed | +0.010 |
thia | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.007 |
One | -0.005 |
Pr | -0.005 |
Morty | -0.005 |
Stri | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
First | +0.010 |
One | +0.008 |
Pr | +0.008 |
Morty | +0.008 |
Sn | +0.008 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.008 |
thia | -0.008 |
sed | -0.008 |
alo | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
First | +0.000 |
Ro | +0.000 |
Pr | +0.000 |
Sn | +0.000 |
One | +0.000 |
Neg logit contributions | |
hy | -0.000 |
anne | -0.000 |
cousins | -0.000 |
Katy | -0.000 |
thia | -0.000 |
Token | rad |
Token ID | 2511 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
First | +0.025 |
Stri | +0.022 |
Morty | +0.021 |
Sn | +0.021 |
Pr | +0.020 |
Neg logit contributions | |
hy | -0.033 |
thia | -0.033 |
sed | -0.032 |
anne | -0.031 |
Katy | -0.031 |
Token | ish |
Token ID | 680 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
First | +0.103 |
One | +0.089 |
Sn | +0.087 |
Pr | +0.087 |
Morty | +0.087 |
Neg logit contributions | |
hy | -0.080 |
sed | -0.077 |
thia | -0.077 |
anne | -0.075 |
alo | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
First | +0.056 |
Pr | +0.048 |
One | +0.048 |
Ro | +0.047 |
Sn | +0.047 |
Neg logit contributions | |
hy | -0.026 |
sed | -0.023 |
thia | -0.023 |
alo | -0.022 |
anne | -0.022 |
Token | she |
Token ID | 673 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.006 |
thia | +0.006 |
sed | +0.006 |
alo | +0.006 |
Neg logit contributions | |
First | -0.007 |
One | -0.006 |
Pr | -0.006 |
Morty | -0.006 |
Stri | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
First | +0.020 |
One | +0.018 |
Pr | +0.018 |
Morty | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
hy | -0.015 |
anne | -0.014 |
thia | -0.013 |
alo | -0.013 |
sed | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
hy | +0.001 |
anne | +0.001 |
thia | +0.001 |
sed | +0.001 |
alo | +0.001 |
Neg logit contributions | |
First | -0.001 |
One | -0.001 |
Pr | -0.001 |
Morty | -0.001 |
Sn | -0.001 |
Token | carrots |
Token ID | 34397 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
First | +0.028 |
Stri | +0.024 |
One | +0.024 |
Morty | +0.023 |
Pr | +0.023 |
Neg logit contributions | |
thia | -0.030 |
hy | -0.030 |
anne | -0.030 |
sed | -0.030 |
ly | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
First | +0.039 |
Pr | +0.036 |
One | +0.035 |
Sn | +0.035 |
Ro | +0.035 |
Neg logit contributions | |
hy | -0.012 |
anne | -0.010 |
ly | -0.010 |
alo | -0.010 |
sed | -0.010 |
Token | potatoes |
Token ID | 18821 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
First | +0.011 |
One | +0.009 |
Pr | +0.009 |
Morty | +0.009 |
Sn | +0.009 |
Neg logit contributions | |
hy | -0.015 |
anne | -0.015 |
thia | -0.014 |
sed | -0.014 |
Katy | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
First | +0.077 |
Pr | +0.071 |
One | +0.070 |
Sn | +0.069 |
Ro | +0.069 |
Neg logit contributions | |
hy | -0.026 |
sed | -0.022 |
thia | -0.021 |
anne | -0.021 |
alo | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
First | +0.016 |
One | +0.014 |
Pr | +0.014 |
Morty | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.008 |
thia | -0.008 |
sed | -0.008 |
alo | -0.008 |
Token | onions |
Token ID | 24681 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
First | +0.012 |
One | +0.010 |
Pr | +0.010 |
Morty | +0.010 |
Sn | +0.009 |
Neg logit contributions | |
hy | -0.015 |
anne | -0.015 |
thia | -0.015 |
sed | -0.014 |
alo | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
First | +0.126 |
Ro | +0.118 |
Pr | +0.117 |
One | +0.116 |
Sn | +0.113 |
Neg logit contributions | |
happened | -0.051 |
ed | -0.050 |
hy | -0.050 |
appeared | -0.050 |
led | -0.049 |
Token | put |
Token ID | 1234 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
First | +0.033 |
One | +0.028 |
Pr | +0.027 |
Morty | +0.027 |
Sn | +0.026 |
Neg logit contributions | |
hy | -0.043 |
thia | -0.041 |
anne | -0.040 |
sed | -0.040 |
cousins | -0.039 |
Token | them |
Token ID | 606 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
First | +0.049 |
Pr | +0.043 |
Ro | +0.041 |
One | +0.041 |
Sn | +0.041 |
Neg logit contributions | |
hy | -0.026 |
Katy | -0.025 |
led | -0.025 |
anne | -0.025 |
ly | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
First | +0.024 |
Stri | +0.022 |
Pr | +0.022 |
Morty | +0.022 |
One | +0.022 |
Neg logit contributions | |
hy | -0.008 |
led | -0.007 |
anne | -0.007 |
alo | -0.007 |
ly | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
First | +0.036 |
Ro | +0.034 |
unn | +0.034 |
ba | +0.033 |
Pr | +0.033 |
Neg logit contributions | |
Katy | -0.011 |
back | -0.010 |
and | -0.010 |
freshly | -0.010 |
relief | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
hy | +0.004 |
Katy | +0.004 |
anne | +0.004 |
Susan | +0.004 |
thia | +0.004 |
Neg logit contributions | |
Pr | -0.006 |
First | -0.006 |
st | -0.005 |
b | -0.005 |
ba | -0.005 |
Token | would |
Token ID | 561 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.003 |
One | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
thia | -0.002 |
sed | -0.002 |
cousins | -0.002 |
Token | race |
Token ID | 3234 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.010 |
thia | +0.010 |
sed | +0.010 |
grin | +0.010 |
Neg logit contributions | |
First | -0.015 |
Pr | -0.014 |
Sn | -0.013 |
Morty | -0.013 |
One | -0.013 |
Token | make |
Token ID | 787 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
hy | +0.033 |
anne | +0.032 |
thia | +0.032 |
sed | +0.031 |
alo | +0.031 |
Neg logit contributions | |
First | -0.027 |
One | -0.024 |
Morty | -0.023 |
Stri | -0.022 |
stream | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
hy | +0.018 |
anne | +0.016 |
thia | +0.016 |
sed | +0.016 |
alo | +0.016 |
Neg logit contributions | |
First | -0.020 |
Pr | -0.017 |
One | -0.017 |
Morty | -0.017 |
Sn | -0.017 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
hy | +0.023 |
anne | +0.021 |
thia | +0.021 |
alo | +0.020 |
sed | +0.020 |
Neg logit contributions | |
First | -0.033 |
Morty | -0.029 |
One | -0.029 |
Pr | -0.029 |
Sn | -0.028 |
Token | ieve |
Token ID | 12311 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
hy | +0.101 |
anne | +0.096 |
sed | +0.094 |
thia | +0.092 |
alo | +0.090 |
Neg logit contributions | |
First | -0.110 |
One | -0.096 |
Pr | -0.093 |
Morty | -0.091 |
Sn | -0.091 |
Token | cars |
Token ID | 5006 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.011 |
thia | +0.010 |
sed | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.015 |
One | -0.013 |
Morty | -0.013 |
Pr | -0.013 |
Stri | -0.013 |
Token | around |
Token ID | 1088 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
hy | +0.017 |
anne | +0.016 |
thia | +0.016 |
sed | +0.015 |
alo | +0.015 |
Neg logit contributions | |
First | -0.025 |
One | -0.022 |
Pr | -0.021 |
Morty | -0.021 |
Stri | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
hy | +0.020 |
anne | +0.018 |
sed | +0.017 |
alo | +0.017 |
thia | +0.017 |
Neg logit contributions | |
First | -0.022 |
Pr | -0.019 |
One | -0.018 |
Sn | -0.018 |
Morty | -0.018 |
Token | track |
Token ID | 2610 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
hy | +0.004 |
anne | +0.003 |
thia | +0.003 |
sed | +0.003 |
alo | +0.003 |
Neg logit contributions | |
First | -0.003 |
Pr | -0.003 |
One | -0.003 |
Morty | -0.003 |
Sn | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.008 |
Morty | +0.007 |
Sn | +0.007 |
One | +0.007 |
Neg logit contributions | |
hy | -0.006 |
sed | -0.005 |
anne | -0.005 |
thia | -0.005 |
alo | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
hy | +0.021 |
anne | +0.020 |
alo | +0.019 |
thia | +0.019 |
sed | +0.019 |
Neg logit contributions | |
First | -0.019 |
One | -0.016 |
Pr | -0.015 |
Morty | -0.015 |
Stri | -0.015 |
Token | threw |
Token ID | 9617 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.005 |
alo | +0.005 |
sed | +0.005 |
thia | +0.005 |
Neg logit contributions | |
First | -0.009 |
One | -0.008 |
Pr | -0.008 |
Stri | -0.008 |
Morty | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
anne | +0.000 |
hy | +0.000 |
alo | +0.000 |
thia | +0.000 |
sed | +0.000 |
Neg logit contributions | |
First | -0.000 |
One | -0.000 |
stream | -0.000 |
D | -0.000 |
bowl | -0.000 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
hy | +0.036 |
anne | +0.032 |
thia | +0.032 |
sed | +0.032 |
alo | +0.031 |
Neg logit contributions | |
First | -0.039 |
Morty | -0.034 |
One | -0.033 |
Pr | -0.033 |
Finn | -0.032 |
Token | opl |
Token ID | 20106 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
hy | +0.067 |
sed | +0.066 |
anne | +0.064 |
thia | +0.062 |
alo | +0.062 |
Neg logit contributions | |
First | -0.059 |
One | -0.053 |
Pr | -0.051 |
Stri | -0.050 |
Sn | -0.049 |
Token | ane |
Token ID | 1531 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
anne | +0.116 |
sed | +0.115 |
grin | +0.113 |
hy | +0.108 |
Katy | +0.108 |
Neg logit contributions | |
First | -0.076 |
Stri | -0.075 |
One | -0.071 |
Pr | -0.071 |
bar | -0.068 |
Token | high |
Token ID | 1029 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
hy | +0.044 |
thia | +0.043 |
anne | +0.042 |
sed | +0.040 |
andra | +0.040 |
Neg logit contributions | |
First | -0.046 |
One | -0.041 |
stream | -0.041 |
log | -0.040 |
bowl | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
hy | +0.026 |
anne | +0.024 |
thia | +0.024 |
sed | +0.023 |
alo | +0.023 |
Neg logit contributions | |
First | -0.037 |
One | -0.033 |
Morty | -0.032 |
Sn | -0.032 |
Stri | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
hy | +0.047 |
anne | +0.045 |
thia | +0.044 |
sed | +0.043 |
alo | +0.043 |
Neg logit contributions | |
First | -0.034 |
One | -0.029 |
Pr | -0.028 |
Morty | -0.028 |
Sn | -0.027 |
Token | air |
Token ID | 1633 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
sed | +0.039 |
hy | +0.039 |
alo | +0.038 |
anne | +0.038 |
rav | +0.038 |
Neg logit contributions | |
First | -0.030 |
stream | -0.027 |
One | -0.026 |
Pr | -0.024 |
Sn | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
First | +0.000 |
One | +0.000 |
Pr | +0.000 |
Morty | +0.000 |
Stri | +0.000 |
Neg logit contributions | |
hy | -0.000 |
anne | -0.000 |
sed | -0.000 |
thia | -0.000 |
alo | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
First | +0.001 |
Pr | +0.001 |
One | +0.001 |
Morty | +0.001 |
Sn | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | see |
Token ID | 766 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
First | +0.017 |
Pr | +0.016 |
Sn | +0.015 |
bowl | +0.014 |
One | +0.014 |
Neg logit contributions | |
hy | -0.012 |
Katy | -0.010 |
thia | -0.010 |
anne | -0.010 |
cousins | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
hy | +0.008 |
cousins | +0.007 |
anne | +0.007 |
thia | +0.007 |
Katy | +0.007 |
Neg logit contributions | |
First | -0.010 |
Pr | -0.009 |
One | -0.009 |
Sn | -0.009 |
Morty | -0.009 |
Token | aer |
Token ID | 9551 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
hy | +0.016 |
anne | +0.014 |
sed | +0.014 |
thia | +0.014 |
alo | +0.014 |
Neg logit contributions | |
First | -0.018 |
One | -0.015 |
Pr | -0.015 |
Morty | -0.015 |
Sn | -0.015 |
Token | opl |
Token ID | 20106 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
hy | +0.076 |
sed | +0.074 |
anne | +0.070 |
alo | +0.069 |
rav | +0.069 |
Neg logit contributions | |
First | -0.070 |
One | -0.063 |
Pr | -0.060 |
Stri | -0.057 |
Sn | -0.057 |
Token | ane |
Token ID | 1531 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
sed | +0.102 |
anne | +0.102 |
grin | +0.101 |
hy | +0.100 |
relief | +0.099 |
Neg logit contributions | |
First | -0.087 |
One | -0.083 |
Stri | -0.079 |
Pr | -0.077 |
bar | -0.077 |
Token | in |
Token ID | 287 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hy | +0.030 |
anne | +0.028 |
thia | +0.027 |
sed | +0.027 |
alo | +0.026 |
Neg logit contributions | |
First | -0.034 |
Pr | -0.029 |
One | -0.029 |
Morty | -0.029 |
Sn | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
hy | +0.004 |
Katy | +0.004 |
anne | +0.003 |
Jennifer | +0.003 |
Jennifer | +0.003 |
Neg logit contributions | |
First | -0.005 |
Pr | -0.005 |
Sn | -0.005 |
bowl | -0.004 |
Stri | -0.004 |
Token | sky |
Token ID | 6766 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
hy | +0.020 |
anne | +0.018 |
thia | +0.018 |
sed | +0.017 |
alo | +0.017 |
Neg logit contributions | |
First | -0.021 |
Morty | -0.018 |
Pr | -0.018 |
One | -0.018 |
Stri | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
hy | +0.016 |
anne | +0.015 |
thia | +0.014 |
alo | +0.014 |
sed | +0.013 |
Neg logit contributions | |
First | -0.020 |
Pr | -0.018 |
Morty | -0.017 |
Sn | -0.017 |
Stri | -0.017 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.007 |
sed | +0.007 |
alo | +0.007 |
thia | +0.007 |
Neg logit contributions | |
First | -0.014 |
One | -0.013 |
Pr | -0.012 |
Morty | -0.012 |
Sn | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
hy | +0.003 |
thia | +0.003 |
anne | +0.003 |
cousins | +0.003 |
alo | +0.003 |
Neg logit contributions | |
First | -0.006 |
Pr | -0.005 |
Morty | -0.005 |
One | -0.005 |
Sn | -0.005 |
Token | play |
Token ID | 711 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.003 |
Morty | +0.003 |
One | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
thia | -0.003 |
anne | -0.003 |
alo | -0.003 |
grin | -0.003 |
Token | make |
Token ID | 787 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
alo | +0.009 |
thia | +0.009 |
sed | +0.008 |
Neg logit contributions | |
First | -0.020 |
Pr | -0.018 |
Morty | -0.017 |
One | -0.017 |
Pr | -0.017 |
Token | - |
Token ID | 12 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
hy | +0.021 |
anne | +0.019 |
thia | +0.019 |
sed | +0.018 |
alo | +0.018 |
Neg logit contributions | |
First | -0.026 |
One | -0.022 |
Pr | -0.022 |
Morty | -0.022 |
Sn | -0.021 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
hy | +0.032 |
anne | +0.029 |
thia | +0.028 |
sed | +0.028 |
alo | +0.027 |
Neg logit contributions | |
First | -0.043 |
One | -0.038 |
Pr | -0.038 |
Morty | -0.037 |
Sn | -0.037 |
Token | ieve |
Token ID | 12311 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
hy | +0.097 |
anne | +0.091 |
sed | +0.089 |
thia | +0.087 |
alo | +0.085 |
Neg logit contributions | |
First | -0.110 |
One | -0.095 |
Pr | -0.093 |
Morty | -0.091 |
Sn | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
hy | +0.009 |
anne | +0.009 |
thia | +0.008 |
sed | +0.008 |
alo | +0.008 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
Sn | -0.009 |
Token | Today |
Token ID | 6288 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
hy | +0.001 |
bell | +0.001 |
Katy | +0.001 |
anne | +0.001 |
thia | +0.001 |
Neg logit contributions | |
First | -0.001 |
Morty | -0.001 |
Flip | -0.001 |
Pr | -0.001 |
Stri | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
hy | +0.011 |
sed | +0.010 |
anne | +0.010 |
thia | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.011 |
One | -0.010 |
stream | -0.009 |
Morty | -0.009 |
Pr | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
First | +0.004 |
One | +0.004 |
Pr | +0.004 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.002 |
thia | -0.002 |
sed | -0.002 |
alo | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.008 |
thia | +0.007 |
sed | +0.007 |
alo | +0.007 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
Stri | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.002 |
sed | +0.002 |
alo | +0.002 |
thia | +0.002 |
Neg logit contributions | |
First | -0.003 |
Pr | -0.003 |
One | -0.003 |
Sn | -0.003 |
bowl | -0.003 |
Token | threw |
Token ID | 9617 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
First | +0.010 |
One | +0.009 |
Stri | +0.009 |
Morty | +0.009 |
Sn | +0.008 |
Neg logit contributions | |
hy | -0.010 |
alo | -0.009 |
anne | -0.009 |
rav | -0.009 |
thia | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
First | +0.022 |
Pr | +0.019 |
One | +0.019 |
Sn | +0.018 |
Morty | +0.018 |
Neg logit contributions | |
hy | -0.022 |
anne | -0.019 |
sed | -0.019 |
alo | -0.019 |
thia | -0.018 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
hy | +0.020 |
anne | +0.020 |
thia | +0.019 |
alo | +0.018 |
sed | +0.018 |
Neg logit contributions | |
First | -0.015 |
One | -0.013 |
Pr | -0.012 |
Morty | -0.012 |
Sn | -0.012 |
Token | opl |
Token ID | 20106 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
hy | +0.069 |
sed | +0.069 |
anne | +0.066 |
cousins | +0.065 |
thia | +0.065 |
Neg logit contributions | |
First | -0.059 |
One | -0.053 |
Pr | -0.051 |
Stri | -0.050 |
Sn | -0.049 |
Token | ane |
Token ID | 1531 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
anne | +0.107 |
sed | +0.104 |
grin | +0.103 |
Katy | +0.100 |
hy | +0.099 |
Neg logit contributions | |
First | -0.080 |
Stri | -0.079 |
Pr | -0.077 |
One | -0.077 |
bar | -0.071 |
Token | in |
Token ID | 287 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
hy | +0.024 |
anne | +0.022 |
thia | +0.021 |
sed | +0.021 |
alo | +0.021 |
Neg logit contributions | |
First | -0.034 |
One | -0.030 |
Pr | -0.030 |
Morty | -0.029 |
Sn | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
hy | +0.008 |
Katy | +0.007 |
grin | +0.006 |
anne | +0.006 |
Jennifer | +0.006 |
Neg logit contributions | |
First | -0.010 |
Pr | -0.009 |
Sn | -0.009 |
bowl | -0.008 |
Morty | -0.008 |
Token | air |
Token ID | 1633 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
hy | +0.021 |
anne | +0.020 |
thia | +0.019 |
sed | +0.019 |
alo | +0.019 |
Neg logit contributions | |
First | -0.021 |
One | -0.018 |
Pr | -0.018 |
Morty | -0.018 |
Sn | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.006 |
sed | +0.006 |
alo | +0.005 |
thia | +0.005 |
Neg logit contributions | |
First | -0.016 |
Pr | -0.015 |
One | -0.015 |
Sn | -0.014 |
Morty | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
First | +0.043 |
Pr | +0.037 |
One | +0.037 |
Morty | +0.036 |
Sn | +0.035 |
Neg logit contributions | |
hy | -0.035 |
anne | -0.031 |
thia | -0.030 |
sed | -0.030 |
alo | -0.030 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
thia | +0.008 |
Katy | +0.008 |
Susan | +0.008 |
Neg logit contributions | |
First | -0.013 |
Pr | -0.012 |
Sn | -0.011 |
Morty | -0.011 |
log | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
First | +0.007 |
Pr | +0.006 |
One | +0.006 |
Morty | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
hy | -0.005 |
anne | -0.005 |
thia | -0.005 |
sed | -0.004 |
cousins | -0.004 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
hy | +0.004 |
anne | +0.004 |
thia | +0.004 |
sed | +0.004 |
cousins | +0.003 |
Neg logit contributions | |
First | -0.009 |
Pr | -0.008 |
One | -0.008 |
Morty | -0.008 |
Sn | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
hy | +0.023 |
anne | +0.021 |
alo | +0.021 |
sed | +0.021 |
thia | +0.021 |
Neg logit contributions | |
First | -0.030 |
One | -0.026 |
Pr | -0.026 |
Morty | -0.024 |
Sn | -0.024 |
Token | amaz |
Token ID | 40642 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
hy | +0.019 |
anne | +0.017 |
sed | +0.017 |
thia | +0.017 |
alo | +0.016 |
Neg logit contributions | |
First | -0.016 |
Pr | -0.014 |
One | -0.014 |
Morty | -0.013 |
Sn | -0.013 |
Token | ement |
Token ID | 972 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
hy | +0.099 |
sed | +0.095 |
cousins | +0.083 |
Jennifer | +0.082 |
thia | +0.082 |
Neg logit contributions | |
One | -0.091 |
First | -0.090 |
stal | -0.083 |
st | -0.081 |
if | -0.080 |
Token | as |
Token ID | 355 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
hy | +0.033 |
anne | +0.031 |
thia | +0.030 |
sed | +0.029 |
alo | +0.029 |
Neg logit contributions | |
First | -0.032 |
One | -0.028 |
Morty | -0.028 |
Pr | -0.027 |
Stri | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
hy | +0.014 |
anne | +0.013 |
thia | +0.012 |
sed | +0.012 |
alo | +0.012 |
Neg logit contributions | |
First | -0.010 |
Pr | -0.009 |
One | -0.009 |
Morty | -0.008 |
Sn | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
First | +0.019 |
One | +0.017 |
Stri | +0.017 |
Pr | +0.017 |
Morty | +0.017 |
Neg logit contributions | |
hy | -0.014 |
anne | -0.013 |
alo | -0.012 |
thia | -0.012 |
sed | -0.012 |
Token | stars |
Token ID | 5788 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.004 |
One | +0.004 |
Morty | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
thia | -0.004 |
sed | -0.004 |
alo | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.007 |
thia | +0.007 |
sed | +0.007 |
alo | +0.007 |
Neg logit contributions | |
First | -0.012 |
Pr | -0.010 |
One | -0.010 |
Morty | -0.010 |
Sn | -0.010 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.006 |
thia | +0.006 |
sed | +0.006 |
alo | +0.006 |
Neg logit contributions | |
First | -0.014 |
Pr | -0.012 |
One | -0.012 |
Morty | -0.012 |
Stri | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
hy | +0.020 |
anne | +0.018 |
thia | +0.018 |
sed | +0.018 |
alo | +0.017 |
Neg logit contributions | |
First | -0.024 |
One | -0.021 |
Pr | -0.021 |
Morty | -0.021 |
Sn | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
hy | +0.022 |
anne | +0.020 |
sed | +0.019 |
Katy | +0.019 |
cousins | +0.019 |
Neg logit contributions | |
First | -0.018 |
Pr | -0.016 |
One | -0.015 |
Sn | -0.015 |
Stri | -0.014 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.007 |
thia | +0.007 |
sed | +0.007 |
alo | +0.007 |
Neg logit contributions | |
First | -0.009 |
One | -0.008 |
Pr | -0.008 |
Morty | -0.007 |
Sn | -0.007 |
Token | opl |
Token ID | 20106 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
sed | +0.062 |
alo | +0.059 |
hy | +0.059 |
cousins | +0.057 |
rav | +0.057 |
Neg logit contributions | |
First | -0.044 |
One | -0.042 |
Pr | -0.037 |
Stri | -0.036 |
Sn | -0.035 |
Token | ane |
Token ID | 1531 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
relief | +0.099 |
sed | +0.097 |
anne | +0.096 |
grin | +0.096 |
icol | +0.095 |
Neg logit contributions | |
First | -0.078 |
bar | -0.074 |
One | -0.073 |
Stri | -0.073 |
Pr | -0.067 |
Token | painting |
Token ID | 12036 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
hy | +0.030 |
anne | +0.028 |
sed | +0.028 |
thia | +0.028 |
alo | +0.028 |
Neg logit contributions | |
First | -0.031 |
One | -0.027 |
Morty | -0.026 |
Pr | -0.026 |
Stri | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
hy | +0.027 |
anne | +0.026 |
sed | +0.025 |
thia | +0.025 |
alo | +0.024 |
Neg logit contributions | |
First | -0.028 |
One | -0.025 |
Morty | -0.024 |
Pr | -0.024 |
Stri | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
First | +0.010 |
Pr | +0.009 |
Sn | +0.009 |
ba | +0.009 |
stream | +0.009 |
Neg logit contributions | |
anne | -0.006 |
thia | -0.005 |
Katy | -0.005 |
Susan | -0.005 |
Steve | -0.005 |
Token | hung |
Token ID | 9174 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.007 |
sed | +0.007 |
thia | +0.007 |
alo | +0.007 |
Neg logit contributions | |
First | -0.012 |
One | -0.011 |
Pr | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
First | +0.033 |
Pr | +0.030 |
One | +0.029 |
Morty | +0.028 |
Sn | +0.028 |
Neg logit contributions | |
hy | -0.024 |
anne | -0.022 |
thia | -0.021 |
sed | -0.020 |
alo | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.004 |
st | +0.004 |
log | +0.004 |
ba | +0.004 |
Neg logit contributions | |
hy | -0.002 |
Katy | -0.002 |
anne | -0.002 |
Susan | -0.002 |
thia | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
anne | +0.009 |
thia | +0.009 |
Jennifer | +0.008 |
hy | +0.007 |
Susan | +0.007 |
Neg logit contributions | |
peas | -0.013 |
cuc | -0.012 |
minerals | -0.012 |
stalk | -0.012 |
potatoes | -0.012 |
Token | To |
Token ID | 2514 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
anne | +0.011 |
Jennifer | +0.011 |
thia | +0.010 |
hy | +0.010 |
Katy | +0.009 |
Neg logit contributions | |
peas | -0.012 |
Stri | -0.011 |
minerals | -0.011 |
log | -0.011 |
stream | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
hy | +0.018 |
anne | +0.016 |
thia | +0.016 |
sed | +0.016 |
alo | +0.015 |
Neg logit contributions | |
First | -0.018 |
Pr | -0.015 |
One | -0.015 |
Sn | -0.015 |
Morty | -0.015 |
Token | amaz |
Token ID | 40642 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
First | +0.017 |
One | +0.015 |
Pr | +0.015 |
Morty | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
hy | -0.012 |
anne | -0.011 |
thia | -0.010 |
sed | -0.010 |
alo | -0.010 |
Token | ement |
Token ID | 972 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
hy | +0.082 |
sed | +0.075 |
rav | +0.072 |
thia | +0.070 |
cousins | +0.068 |
Neg logit contributions | |
One | -0.100 |
First | -0.099 |
stal | -0.097 |
st | -0.092 |
bar | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
hy | +0.028 |
anne | +0.025 |
thia | +0.025 |
sed | +0.025 |
alo | +0.024 |
Neg logit contributions | |
First | -0.035 |
One | -0.030 |
Morty | -0.030 |
Pr | -0.030 |
Stri | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
First | +0.013 |
Pr | +0.011 |
One | +0.011 |
Sn | +0.011 |
Morty | +0.011 |
Neg logit contributions | |
hy | -0.013 |
anne | -0.012 |
thia | -0.011 |
sed | -0.011 |
alo | -0.011 |
Token | clothes |
Token ID | 8242 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
hy | +0.009 |
anne | +0.008 |
sed | +0.008 |
thia | +0.008 |
alo | +0.008 |
Neg logit contributions | |
First | -0.011 |
One | -0.010 |
Pr | -0.009 |
Morty | -0.009 |
Stri | -0.009 |
Token | came |
Token ID | 1625 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.002 |
thia | +0.001 |
sed | +0.001 |
alo | +0.001 |
Neg logit contributions | |
First | -0.002 |
stream | -0.002 |
Morty | -0.002 |
One | -0.002 |
Pr | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
First | +0.006 |
One | +0.005 |
Morty | +0.005 |
Pr | +0.005 |
D | +0.005 |
Neg logit contributions | |
hy | -0.011 |
anne | -0.010 |
thia | -0.010 |
sed | -0.010 |
alo | -0.010 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
hy | +0.008 |
alo | +0.007 |
sed | +0.007 |
anne | +0.007 |
rav | +0.007 |
Neg logit contributions | |
First | -0.008 |
One | -0.007 |
stream | -0.007 |
Stri | -0.007 |
bowl | -0.007 |
Token | dropped |
Token ID | 5710 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
First | +0.072 |
Pr | +0.064 |
One | +0.063 |
Stri | +0.063 |
Morty | +0.063 |
Neg logit contributions | |
hy | -0.053 |
anne | -0.049 |
thia | -0.047 |
sed | -0.046 |
alo | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
First | +0.051 |
One | +0.044 |
Pr | +0.043 |
Morty | +0.043 |
Sn | +0.042 |
Neg logit contributions | |
hy | -0.031 |
Katy | -0.027 |
alo | -0.027 |
sed | -0.026 |
back | -0.026 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
hy | +0.031 |
anne | +0.029 |
sed | +0.028 |
thia | +0.028 |
alo | +0.028 |
Neg logit contributions | |
First | -0.027 |
One | -0.023 |
Pr | -0.023 |
Morty | -0.022 |
Sn | -0.022 |
Token | tr |
Token ID | 2213 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
hy | +0.033 |
anne | +0.032 |
thia | +0.031 |
rav | +0.031 |
cousins | +0.031 |
Neg logit contributions | |
First | -0.050 |
One | -0.046 |
Pr | -0.045 |
Stri | -0.045 |
Pr | -0.044 |
Token | ay |
Token ID | 323 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
anne | +0.063 |
thia | +0.061 |
ote | +0.060 |
hy | +0.059 |
cousins | +0.058 |
Neg logit contributions | |
First | -0.122 |
bar | -0.118 |
One | -0.114 |
Stri | -0.111 |
Pr | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
hy | +0.052 |
thia | +0.050 |
sed | +0.050 |
anne | +0.050 |
alo | +0.048 |
Neg logit contributions | |
First | -0.064 |
Stri | -0.056 |
One | -0.056 |
Pr | -0.055 |
Sn | -0.055 |
Token | it |
Token ID | 340 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.013 |
thia | +0.012 |
sed | +0.012 |
alo | +0.012 |
Neg logit contributions | |
First | -0.010 |
Stri | -0.009 |
Pr | -0.009 |
Morty | -0.008 |
Sn | -0.008 |
Token | broke |
Token ID | 6265 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
First | +0.004 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.002 |
thia | -0.002 |
sed | -0.002 |
alo | -0.002 |
Token | into |
Token ID | 656 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
First | +0.066 |
One | +0.057 |
Pr | +0.056 |
Morty | +0.056 |
Sn | +0.054 |
Neg logit contributions | |
hy | -0.052 |
anne | -0.048 |
thia | -0.046 |
sed | -0.046 |
alo | -0.046 |
Token | cleaned |
Token ID | 20750 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.005 |
thia | +0.005 |
sed | +0.005 |
alo | +0.005 |
Neg logit contributions | |
First | -0.007 |
One | -0.006 |
Pr | -0.006 |
Morty | -0.006 |
Sn | -0.006 |
Token | up |
Token ID | 510 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
First | +0.013 |
Morty | +0.011 |
Finn | +0.011 |
Pr | +0.011 |
Stri | +0.011 |
Neg logit contributions | |
hy | -0.018 |
sed | -0.016 |
anne | -0.016 |
alo | -0.016 |
thia | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hy | +0.043 |
anne | +0.041 |
sed | +0.040 |
thia | +0.040 |
rav | +0.039 |
Neg logit contributions | |
First | -0.024 |
Pr | -0.020 |
Pr | -0.020 |
Stri | -0.019 |
One | -0.019 |
Token | broken |
Token ID | 5445 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
hy | +0.028 |
anne | +0.027 |
thia | +0.025 |
alo | +0.025 |
sed | +0.025 |
Neg logit contributions | |
First | -0.025 |
One | -0.022 |
Pr | -0.022 |
Sn | -0.021 |
Stri | -0.020 |
Token | ash |
Token ID | 12530 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
First | +0.006 |
One | +0.005 |
Pr | +0.005 |
Sn | +0.005 |
Stri | +0.005 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.008 |
thia | -0.008 |
sed | -0.008 |
alo | -0.007 |
Token | tr |
Token ID | 2213 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
hy | +0.038 |
anne | +0.034 |
thia | +0.033 |
sed | +0.032 |
rav | +0.032 |
Neg logit contributions | |
First | -0.067 |
One | -0.060 |
Stri | -0.058 |
Pr | -0.058 |
Sn | -0.058 |
Token | ay |
Token ID | 323 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
hy | +0.063 |
ote | +0.060 |
anne | +0.060 |
thia | +0.057 |
sed | +0.056 |
Neg logit contributions | |
First | -0.125 |
bar | -0.116 |
One | -0.114 |
Stri | -0.113 |
Sp | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
hy | +0.081 |
sed | +0.079 |
thia | +0.075 |
alo | +0.074 |
ote | +0.073 |
Neg logit contributions | |
First | -0.089 |
Stri | -0.077 |
One | -0.074 |
Pr | -0.073 |
Sp | -0.073 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
hy | +0.020 |
anne | +0.020 |
ote | +0.019 |
agging | +0.019 |
agged | +0.018 |
Neg logit contributions | |
First | -0.010 |
stream | -0.009 |
Stri | -0.009 |
sometimes | -0.009 |
if | -0.009 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
First | +0.009 |
Sn | +0.007 |
Stri | +0.007 |
Pr | +0.007 |
One | +0.007 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
alo | -0.006 |
sed | -0.006 |
thia | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
First | +0.003 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.003 |
sed | -0.003 |
thia | -0.003 |
alo | -0.003 |
Token | fire |
Token ID | 2046 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
hy | +0.001 |
thia | +0.001 |
cousins | +0.001 |
anne | +0.001 |
sed | +0.001 |
Neg logit contributions | |
First | -0.001 |
Pr | -0.001 |
One | -0.001 |
Sn | -0.001 |
Morty | -0.001 |
Token | safety |
Token ID | 3747 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
First | +0.019 |
One | +0.017 |
Morty | +0.016 |
Pr | +0.016 |
Stri | +0.016 |
Neg logit contributions | |
hy | -0.020 |
anne | -0.018 |
thia | -0.018 |
sed | -0.018 |
alo | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
hy | +0.009 |
anne | +0.009 |
thia | +0.009 |
sed | +0.009 |
alo | +0.009 |
Neg logit contributions | |
First | -0.008 |
One | -0.007 |
Pr | -0.007 |
Morty | -0.007 |
Stri | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
hy | +0.018 |
anne | +0.016 |
thia | +0.016 |
sed | +0.015 |
cousins | +0.014 |
Neg logit contributions | |
First | -0.023 |
Pr | -0.021 |
Morty | -0.020 |
Sn | -0.020 |
One | -0.020 |
Token | waved |
Token ID | 26834 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.003 |
thia | +0.003 |
sed | +0.003 |
cousins | +0.003 |
Neg logit contributions | |
First | -0.005 |
Pr | -0.004 |
One | -0.004 |
Morty | -0.004 |
Sn | -0.004 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
thia | +0.044 |
anne | +0.042 |
hy | +0.040 |
alo | +0.039 |
andra | +0.038 |
Neg logit contributions | |
D | -0.041 |
First | -0.041 |
Finn | -0.040 |
if | -0.040 |
stream | -0.039 |
Token | as |
Token ID | 355 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
hy | +0.110 |
anne | +0.105 |
thia | +0.104 |
alo | +0.101 |
Jennifer | +0.101 |
Neg logit contributions | |
First | -0.074 |
stream | -0.063 |
One | -0.063 |
Pr | -0.063 |
D | -0.062 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
hy | +0.014 |
anne | +0.014 |
sed | +0.014 |
thia | +0.014 |
alo | +0.013 |
Neg logit contributions | |
First | -0.012 |
One | -0.010 |
Pr | -0.010 |
Stri | -0.010 |
Morty | -0.010 |
Token | drove |
Token ID | 10357 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
First | +0.006 |
One | +0.006 |
Pr | +0.006 |
Morty | +0.006 |
Stri | +0.006 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
alo | -0.004 |
sed | -0.004 |
thia | -0.004 |
Token | away |
Token ID | 1497 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.010 |
thia | +0.010 |
sed | +0.010 |
alo | +0.009 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
Stri | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
hy | +0.017 |
anne | +0.016 |
thia | +0.016 |
sed | +0.015 |
alo | +0.015 |
Neg logit contributions | |
First | -0.020 |
One | -0.017 |
Pr | -0.017 |
Morty | -0.017 |
Stri | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
hy | +0.029 |
anne | +0.028 |
sed | +0.028 |
thia | +0.027 |
alo | +0.026 |
Neg logit contributions | |
First | -0.022 |
One | -0.019 |
Pr | -0.018 |
Morty | -0.018 |
Sn | -0.017 |
Token | airplane |
Token ID | 19401 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
sed | +0.053 |
anne | +0.052 |
rav | +0.051 |
hy | +0.049 |
ushed | +0.049 |
Neg logit contributions | |
First | -0.048 |
One | -0.045 |
stream | -0.045 |
Sn | -0.041 |
Pr | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.011 |
thia | +0.011 |
alo | +0.010 |
sed | +0.010 |
Neg logit contributions | |
First | -0.013 |
Pr | -0.012 |
One | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
First | +0.009 |
Pr | +0.008 |
One | +0.008 |
Morty | +0.008 |
Sn | +0.008 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
anne | +0.030 |
hy | +0.030 |
sed | +0.029 |
thia | +0.028 |
alo | +0.028 |
Neg logit contributions | |
First | -0.035 |
One | -0.032 |
stream | -0.031 |
Pr | -0.030 |
Sn | -0.029 |
Token | opl |
Token ID | 20106 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
sed | +0.087 |
hy | +0.080 |
cousins | +0.078 |
rav | +0.078 |
alo | +0.078 |
Neg logit contributions | |
First | -0.050 |
One | -0.048 |
Pr | -0.040 |
Stri | -0.040 |
Sn | -0.038 |
Token | ane |
Token ID | 1531 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
sed | +0.117 |
grin | +0.114 |
hy | +0.109 |
anne | +0.109 |
relief | +0.109 |
Neg logit contributions | |
First | -0.063 |
One | -0.061 |
Pr | -0.054 |
Stri | -0.054 |
st | -0.052 |
Token | flew |
Token ID | 13112 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
hy | +0.034 |
anne | +0.031 |
sed | +0.030 |
thia | +0.030 |
alo | +0.030 |
Neg logit contributions | |
First | -0.043 |
One | -0.038 |
Pr | -0.037 |
Stri | -0.037 |
Sn | -0.037 |
Token | up |
Token ID | 510 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
First | +0.001 |
One | +0.001 |
Morty | +0.001 |
stream | +0.001 |
Stri | +0.001 |
Neg logit contributions | |
hy | -0.001 |
thia | -0.001 |
sed | -0.001 |
anne | -0.001 |
alo | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
hy | +0.030 |
thia | +0.028 |
anne | +0.028 |
sed | +0.027 |
rav | +0.026 |
Neg logit contributions | |
First | -0.036 |
One | -0.032 |
stream | -0.031 |
Morty | -0.031 |
Stri | -0.030 |
Token | high |
Token ID | 1029 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.007 |
Morty | +0.007 |
bowl | +0.007 |
Stri | +0.007 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
alo | -0.006 |
sed | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
First | +0.016 |
Pr | +0.015 |
Morty | +0.014 |
Sn | +0.014 |
Stri | +0.014 |
Neg logit contributions | |
hy | -0.014 |
anne | -0.012 |
alo | -0.012 |
sed | -0.012 |
bell | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
First | +0.003 |
Pr | +0.003 |
ba | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.001 |
thia | -0.001 |
Sarah | -0.001 |
Susan | -0.001 |
sed | -0.001 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
First | +0.017 |
Pr | +0.016 |
Morty | +0.015 |
One | +0.015 |
Sn | +0.015 |
Neg logit contributions | |
hy | -0.011 |
anne | -0.010 |
sed | -0.010 |
thia | -0.010 |
alo | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
hy | +0.001 |
sed | +0.001 |
Katy | +0.001 |
alo | +0.001 |
anne | +0.001 |
Neg logit contributions | |
First | -0.001 |
One | -0.001 |
Pr | -0.001 |
bowl | -0.001 |
bank | -0.001 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
hy | +0.019 |
alo | +0.015 |
sed | +0.015 |
cousins | +0.014 |
rav | +0.014 |
Neg logit contributions | |
First | -0.022 |
Finn | -0.020 |
Morty | -0.019 |
Flip | -0.018 |
bowl | -0.018 |
Token | opl |
Token ID | 20106 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
hy | +0.063 |
sed | +0.062 |
anne | +0.060 |
thia | +0.059 |
cousins | +0.058 |
Neg logit contributions | |
First | -0.056 |
One | -0.051 |
Pr | -0.047 |
Stri | -0.047 |
Sn | -0.046 |
Token | ane |
Token ID | 1531 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
anne | +0.107 |
sed | +0.104 |
grin | +0.102 |
hy | +0.099 |
thia | +0.099 |
Neg logit contributions | |
First | -0.076 |
One | -0.071 |
Stri | -0.070 |
Pr | -0.068 |
Sn | -0.064 |
Token | with |
Token ID | 351 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
hy | +0.015 |
anne | +0.014 |
thia | +0.013 |
sed | +0.013 |
alo | +0.013 |
Neg logit contributions | |
First | -0.028 |
One | -0.025 |
Pr | -0.025 |
Morty | -0.025 |
Sn | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
First | +0.003 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.003 |
thia | -0.003 |
sed | -0.003 |
alo | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
hy | +0.009 |
sed | +0.008 |
thia | +0.008 |
anne | +0.008 |
alo | +0.008 |
Neg logit contributions | |
First | -0.012 |
Pr | -0.010 |
One | -0.010 |
Morty | -0.010 |
Sn | -0.010 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
First | +0.044 |
Pr | +0.039 |
One | +0.039 |
Morty | +0.038 |
Stri | +0.038 |
Neg logit contributions | |
hy | -0.032 |
anne | -0.030 |
thia | -0.029 |
alo | -0.028 |
sed | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.005 |
thia | +0.005 |
sed | +0.005 |
rav | +0.005 |
Neg logit contributions | |
First | -0.006 |
One | -0.005 |
stream | -0.005 |
Stri | -0.005 |
Sn | -0.005 |
Token | fast |
Token ID | 3049 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.013 |
thia | +0.012 |
alo | +0.012 |
sed | +0.012 |
Neg logit contributions | |
First | -0.011 |
One | -0.010 |
Morty | -0.010 |
Pr | -0.009 |
Stri | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
First | +0.013 |
Pr | +0.011 |
One | +0.011 |
Morty | +0.011 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.011 |
sed | -0.009 |
anne | -0.009 |
alo | -0.009 |
thia | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
First | +0.009 |
Pr | +0.008 |
One | +0.008 |
Sn | +0.008 |
Morty | +0.008 |
Neg logit contributions | |
hy | -0.005 |
sed | -0.004 |
anne | -0.004 |
thia | -0.004 |
alo | -0.004 |
Token | merry |
Token ID | 44570 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
hy | +0.029 |
anne | +0.026 |
thia | +0.026 |
sed | +0.026 |
alo | +0.025 |
Neg logit contributions | |
First | -0.034 |
Pr | -0.029 |
One | -0.029 |
Morty | -0.029 |
Sn | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
Katy | +0.044 |
hy | +0.044 |
anne | +0.042 |
Jennifer | +0.042 |
Michelle | +0.041 |
Neg logit contributions | |
stream | -0.051 |
season | -0.051 |
log | -0.050 |
First | -0.049 |
Stri | -0.049 |
Token | go |
Token ID | 2188 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
sed | +0.075 |
Katy | +0.071 |
grin | +0.070 |
Jennifer | +0.069 |
thia | +0.068 |
Neg logit contributions | |
First | -0.109 |
Sn | -0.099 |
One | -0.099 |
Pr | -0.098 |
Stri | -0.097 |
Token | - |
Token ID | 12 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
hy | +0.034 |
sed | +0.034 |
thia | +0.033 |
anne | +0.033 |
Katy | +0.031 |
Neg logit contributions | |
First | -0.072 |
Stri | -0.066 |
One | -0.066 |
Morty | -0.066 |
Sn | -0.065 |
Token | round |
Token ID | 744 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
sed | +0.061 |
hy | +0.061 |
thia | +0.058 |
anne | +0.058 |
alo | +0.058 |
Neg logit contributions | |
First | -0.062 |
One | -0.054 |
Sn | -0.052 |
Pr | -0.052 |
Stri | -0.051 |
Token | spins |
Token ID | 37621 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.007 |
sed | +0.007 |
thia | +0.007 |
alo | +0.007 |
Neg logit contributions | |
First | -0.012 |
Pr | -0.010 |
One | -0.010 |
Morty | -0.010 |
Sn | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.003 |
One | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.003 |
thia | -0.002 |
sed | -0.002 |
alo | -0.002 |
Token | go |
Token ID | 467 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
hy | +0.015 |
anne | +0.014 |
sed | +0.013 |
thia | +0.013 |
alo | +0.013 |
Neg logit contributions | |
First | -0.021 |
One | -0.019 |
Pr | -0.019 |
Morty | -0.019 |
Sn | -0.018 |
Token | home |
Token ID | 1363 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
hy | +0.022 |
anne | +0.021 |
sed | +0.021 |
thia | +0.020 |
alo | +0.019 |
Neg logit contributions | |
First | -0.026 |
One | -0.023 |
Pr | -0.022 |
Morty | -0.022 |
Sn | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
hy | +0.019 |
anne | +0.018 |
thia | +0.017 |
sed | +0.017 |
alo | +0.017 |
Neg logit contributions | |
First | -0.019 |
Pr | -0.016 |
One | -0.016 |
Morty | -0.016 |
Sn | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
hy | +0.015 |
anne | +0.014 |
thia | +0.014 |
sed | +0.014 |
alo | +0.013 |
Neg logit contributions | |
First | -0.017 |
One | -0.014 |
Pr | -0.014 |
Morty | -0.014 |
Sn | -0.014 |
Token | waved |
Token ID | 26834 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.002 |
thia | +0.002 |
sed | +0.002 |
alo | +0.002 |
Neg logit contributions | |
First | -0.003 |
One | -0.003 |
Pr | -0.003 |
Morty | -0.003 |
Sn | -0.003 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
thia | +0.054 |
anne | +0.051 |
hy | +0.047 |
sed | +0.047 |
andra | +0.044 |
Neg logit contributions | |
one | -0.047 |
D | -0.045 |
if | -0.045 |
Pr | -0.042 |
First | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
hy | +0.107 |
anne | +0.103 |
thia | +0.100 |
rav | +0.099 |
grin | +0.097 |
Neg logit contributions | |
First | -0.077 |
One | -0.068 |
Pr | -0.066 |
D | -0.064 |
Stri | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
hy | +0.016 |
anne | +0.015 |
sed | +0.015 |
thia | +0.015 |
alo | +0.014 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Stri | -0.009 |
Morty | -0.009 |
Token | nurse |
Token ID | 15849 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
hy | +0.022 |
anne | +0.020 |
thia | +0.020 |
sed | +0.020 |
alo | +0.019 |
Neg logit contributions | |
First | -0.020 |
One | -0.017 |
Pr | -0.017 |
Morty | -0.017 |
Sn | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
hy | +0.027 |
anne | +0.025 |
thia | +0.025 |
sed | +0.025 |
alo | +0.024 |
Neg logit contributions | |
First | -0.042 |
One | -0.038 |
Morty | -0.038 |
Pr | -0.038 |
Stri | -0.037 |
Token | said |
Token ID | 531 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
hy | +0.018 |
anne | +0.016 |
thia | +0.016 |
alo | +0.016 |
sed | +0.016 |
Neg logit contributions | |
First | -0.016 |
Stri | -0.014 |
Pr | -0.014 |
stream | -0.014 |
Pr | -0.014 |
Token | couldn |
Token ID | 3521 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
First | +0.023 |
Morty | +0.021 |
One | +0.021 |
Stri | +0.021 |
Pr | +0.020 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.016 |
alo | -0.015 |
thia | -0.015 |
sed | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
hy | +0.022 |
anne | +0.021 |
sed | +0.021 |
thia | +0.020 |
alo | +0.020 |
Neg logit contributions | |
First | -0.017 |
One | -0.014 |
Morty | -0.014 |
Pr | -0.014 |
Sn | -0.014 |
Token | catch |
Token ID | 4929 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.012 |
thia | +0.011 |
alo | +0.011 |
sed | +0.011 |
Neg logit contributions | |
First | -0.016 |
Pr | -0.013 |
One | -0.013 |
Morty | -0.013 |
Sn | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
First | +0.005 |
Pr | +0.004 |
One | +0.004 |
Sn | +0.004 |
Morty | +0.004 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
sed | -0.004 |
alo | -0.004 |
thia | -0.004 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
hy | +0.011 |
sed | +0.010 |
anne | +0.010 |
thia | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
Sn | -0.009 |
Token | opl |
Token ID | 20106 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
hy | +0.067 |
sed | +0.066 |
anne | +0.063 |
alo | +0.063 |
cousins | +0.062 |
Neg logit contributions | |
First | -0.058 |
One | -0.054 |
Pr | -0.050 |
Stri | -0.049 |
Sn | -0.048 |
Token | ane |
Token ID | 1531 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
sed | +0.096 |
grin | +0.096 |
anne | +0.094 |
relief | +0.093 |
hy | +0.092 |
Neg logit contributions | |
First | -0.082 |
One | -0.077 |
Stri | -0.077 |
Pr | -0.075 |
bar | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
hy | +0.029 |
anne | +0.026 |
alo | +0.025 |
thia | +0.025 |
sed | +0.024 |
Neg logit contributions | |
First | -0.036 |
Pr | -0.031 |
One | -0.030 |
Morty | -0.030 |
Sn | -0.030 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
First | +0.000 |
Pr | +0.000 |
One | +0.000 |
Sn | +0.000 |
st | +0.000 |
Neg logit contributions | |
hy | -0.000 |
thia | -0.000 |
anne | -0.000 |
sed | -0.000 |
Katy | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
First | +0.020 |
Morty | +0.017 |
One | +0.017 |
Pr | +0.017 |
Stri | +0.017 |
Neg logit contributions | |
hy | -0.018 |
anne | -0.017 |
thia | -0.016 |
sed | -0.016 |
alo | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
hy | +0.008 |
anne | +0.007 |
sed | +0.007 |
thia | +0.007 |
alo | +0.007 |
Neg logit contributions | |
First | -0.006 |
One | -0.005 |
Pr | -0.005 |
Sn | -0.005 |
Morty | -0.005 |
Token | air |
Token ID | 1633 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
First | +0.012 |
One | +0.011 |
Pr | +0.011 |
Morty | +0.010 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.013 |
anne | -0.012 |
thia | -0.012 |
sed | -0.012 |
alo | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.13e-04 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
thia | +0.009 |
sed | +0.009 |
alo | +0.009 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
Stri | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
First | +0.000 |
Pr | +0.000 |
st | +0.000 |
Sn | +0.000 |
Morty | +0.000 |
Neg logit contributions | |
hy | -0.000 |
anne | -0.000 |
Katy | -0.000 |
thia | -0.000 |
sed | -0.000 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
First | +0.009 |
Pr | +0.008 |
One | +0.007 |
Morty | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
alo | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
hy | +0.029 |
anne | +0.027 |
thia | +0.026 |
sed | +0.026 |
alo | +0.026 |
Neg logit contributions | |
First | -0.028 |
One | -0.024 |
Pr | -0.024 |
Morty | -0.023 |
Sn | -0.023 |
Token | amaz |
Token ID | 40642 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
hy | +0.017 |
anne | +0.016 |
thia | +0.016 |
sed | +0.016 |
alo | +0.015 |
Neg logit contributions | |
First | -0.015 |
One | -0.013 |
Pr | -0.013 |
Morty | -0.012 |
Sn | -0.012 |
Token | ement |
Token ID | 972 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
hy | +0.094 |
sed | +0.091 |
cousins | +0.082 |
Jennifer | +0.082 |
thia | +0.081 |
Neg logit contributions | |
One | -0.083 |
First | -0.082 |
stal | -0.081 |
st | -0.076 |
bar | -0.075 |
Token | as |
Token ID | 355 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
hy | +0.029 |
anne | +0.027 |
thia | +0.027 |
sed | +0.026 |
alo | +0.026 |
Neg logit contributions | |
First | -0.029 |
One | -0.025 |
Morty | -0.025 |
Stri | -0.025 |
Pr | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
thia | +0.009 |
sed | +0.009 |
alo | +0.009 |
Neg logit contributions | |
First | -0.007 |
Pr | -0.006 |
One | -0.006 |
Morty | -0.006 |
Sn | -0.006 |
Token | z |
Token ID | 1976 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
hy | +0.021 |
anne | +0.020 |
thia | +0.019 |
sed | +0.019 |
alo | +0.019 |
Neg logit contributions | |
First | -0.024 |
One | -0.020 |
Pr | -0.020 |
Morty | -0.020 |
Sn | -0.020 |
Token | ig |
Token ID | 328 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
hy | +0.021 |
anne | +0.020 |
thia | +0.020 |
sed | +0.019 |
cousins | +0.019 |
Neg logit contributions | |
First | -0.015 |
One | -0.012 |
Morty | -0.012 |
Pr | -0.012 |
Stri | -0.012 |
Token | finally |
Token ID | 3443 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
hy | +0.012 |
sed | +0.012 |
anne | +0.011 |
alo | +0.011 |
thia | +0.011 |
Neg logit contributions | |
First | -0.012 |
stream | -0.011 |
Morty | -0.011 |
D | -0.010 |
One | -0.010 |
Token | arrived |
Token ID | 5284 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
hy | +0.004 |
sed | +0.004 |
thia | +0.004 |
cousins | +0.004 |
anne | +0.004 |
Neg logit contributions | |
First | -0.004 |
stream | -0.004 |
Fisher | -0.004 |
D | -0.004 |
Morty | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
First | +0.021 |
One | +0.018 |
Morty | +0.017 |
Pr | +0.017 |
Pr | +0.017 |
Neg logit contributions | |
hy | -0.024 |
anne | -0.022 |
sed | -0.021 |
thia | -0.021 |
alo | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
hy | +0.019 |
anne | +0.017 |
thia | +0.017 |
sed | +0.017 |
alo | +0.016 |
Neg logit contributions | |
First | -0.024 |
One | -0.021 |
Pr | -0.021 |
Morty | -0.020 |
Sn | -0.020 |
Token | waved |
Token ID | 26834 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
First | +0.002 |
Pr | +0.002 |
One | +0.002 |
Morty | +0.002 |
Sn | +0.002 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
thia | +0.054 |
anne | +0.051 |
hy | +0.049 |
sed | +0.047 |
alo | +0.046 |
Neg logit contributions | |
D | -0.044 |
one | -0.044 |
stream | -0.043 |
First | -0.043 |
if | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
hy | +0.109 |
anne | +0.103 |
thia | +0.103 |
Jennifer | +0.101 |
rav | +0.099 |
Neg logit contributions | |
First | -0.074 |
Pr | -0.062 |
stream | -0.061 |
One | -0.061 |
D | -0.060 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
hy | +0.021 |
anne | +0.019 |
sed | +0.019 |
alo | +0.019 |
thia | +0.019 |
Neg logit contributions | |
First | -0.014 |
One | -0.012 |
Morty | -0.012 |
Stri | -0.012 |
Pr | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
hy | +0.035 |
sed | +0.033 |
thia | +0.032 |
alo | +0.031 |
anne | +0.031 |
Neg logit contributions | |
First | -0.039 |
Morty | -0.034 |
One | -0.033 |
Finn | -0.033 |
Pr | -0.033 |
Token | drove |
Token ID | 10357 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
hy | +0.006 |
alo | +0.006 |
anne | +0.006 |
thia | +0.005 |
sed | +0.005 |
Neg logit contributions | |
First | -0.005 |
stream | -0.005 |
Stri | -0.005 |
Finn | -0.005 |
D | -0.005 |
Token | off |
Token ID | 572 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
hy | +0.019 |
thia | +0.019 |
sed | +0.019 |
anne | +0.018 |
alo | +0.018 |
Neg logit contributions | |
First | -0.014 |
One | -0.011 |
Morty | -0.011 |
Pr | -0.010 |
First | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
hy | +0.002 |
thia | +0.002 |
anne | +0.002 |
Katy | +0.001 |
sed | +0.001 |
Neg logit contributions | |
First | -0.003 |
bowl | -0.003 |
Pr | -0.003 |
Morty | -0.003 |
log | -0.003 |
Token | pick |
Token ID | 2298 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
First | +0.014 |
One | +0.012 |
Pr | +0.012 |
Morty | +0.012 |
Stri | +0.011 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.010 |
alo | -0.010 |
sed | -0.010 |
thia | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hy | +0.001 |
anne | +0.001 |
thia | +0.001 |
sed | +0.001 |
alo | +0.001 |
Neg logit contributions | |
First | -0.001 |
One | -0.001 |
Pr | -0.001 |
Morty | -0.001 |
Sn | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
hy | +0.028 |
anne | +0.027 |
thia | +0.026 |
sed | +0.026 |
alo | +0.025 |
Neg logit contributions | |
First | -0.025 |
One | -0.021 |
Pr | -0.021 |
Morty | -0.021 |
Sn | -0.021 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
hy | +0.017 |
sed | +0.015 |
anne | +0.015 |
alo | +0.014 |
thia | +0.014 |
Neg logit contributions | |
First | -0.019 |
Pr | -0.016 |
One | -0.016 |
Morty | -0.016 |
Sn | -0.015 |
Token | ay |
Token ID | 323 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
sed | +0.024 |
hy | +0.023 |
anne | +0.021 |
cousins | +0.020 |
witnessed | +0.019 |
Neg logit contributions | |
First | -0.060 |
One | -0.056 |
Pr | -0.055 |
Stri | -0.053 |
Sn | -0.053 |
Token | ons |
Token ID | 684 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
sed | +0.102 |
hy | +0.095 |
ote | +0.091 |
thia | +0.089 |
anne | +0.088 |
Neg logit contributions | |
First | -0.086 |
Pr | -0.078 |
One | -0.078 |
Pr | -0.075 |
st | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
hy | +0.009 |
anne | +0.008 |
alo | +0.008 |
thia | +0.008 |
sed | +0.008 |
Neg logit contributions | |
First | -0.012 |
Pr | -0.011 |
One | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
hy | +0.003 |
thia | +0.003 |
sed | +0.003 |
anne | +0.003 |
alo | +0.003 |
Neg logit contributions | |
First | -0.007 |
Pr | -0.006 |
bowl | -0.006 |
st | -0.006 |
Morty | -0.006 |
Token | draw |
Token ID | 3197 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
First | +0.016 |
One | +0.014 |
Pr | +0.014 |
Morty | +0.013 |
Stri | +0.013 |
Neg logit contributions | |
hy | -0.013 |
anne | -0.013 |
sed | -0.012 |
thia | -0.012 |
alo | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
anne | +0.021 |
hy | +0.020 |
sed | +0.020 |
thia | +0.019 |
rav | +0.018 |
Neg logit contributions | |
First | -0.016 |
One | -0.014 |
Stri | -0.014 |
Morty | -0.014 |
stream | -0.014 |
Token | closer |
Token ID | 5699 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Stri | +0.041 |
First | +0.040 |
Pr | +0.040 |
Sn | +0.037 |
Morty | +0.037 |
Neg logit contributions | |
ly | -0.032 |
hy | -0.027 |
relieved | -0.027 |
anne | -0.025 |
led | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.006 |
alo | +0.006 |
ly | +0.005 |
sed | +0.005 |
Neg logit contributions | |
First | -0.012 |
Pr | -0.011 |
Sn | -0.011 |
One | -0.010 |
Morty | -0.010 |
Token | watched |
Token ID | 7342 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
First | +0.015 |
One | +0.013 |
Pr | +0.013 |
Morty | +0.013 |
Sn | +0.013 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.010 |
sed | -0.009 |
thia | -0.009 |
alo | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +6.64e-04 |
Pos logit contributions | |
First | +0.002 |
One | +0.002 |
Pr | +0.002 |
Sn | +0.002 |
Morty | +0.002 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
sed | -0.002 |
thia | -0.002 |
alo | -0.002 |
Token | aer |
Token ID | 9551 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
First | +0.000 |
One | +0.000 |
Pr | +0.000 |
Morty | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
hy | -0.000 |
anne | -0.000 |
thia | -0.000 |
sed | -0.000 |
alo | -0.000 |
Token | opl |
Token ID | 20106 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
hy | +0.056 |
sed | +0.055 |
anne | +0.053 |
cousins | +0.052 |
alo | +0.052 |
Neg logit contributions | |
First | -0.052 |
One | -0.046 |
Pr | -0.045 |
Stri | -0.043 |
Sn | -0.043 |
Token | ane |
Token ID | 1531 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
relief | +0.101 |
sed | +0.101 |
grin | +0.100 |
anne | +0.098 |
Katy | +0.095 |
Neg logit contributions | |
First | -0.070 |
bar | -0.067 |
One | -0.065 |
Stri | -0.064 |
Pr | -0.063 |
Token | fly |
Token ID | 6129 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.012 |
thia | +0.011 |
alo | +0.011 |
sed | +0.011 |
Neg logit contributions | |
First | -0.016 |
Pr | -0.014 |
One | -0.014 |
Morty | -0.014 |
Sn | -0.014 |
Token | above |
Token ID | 2029 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.007 |
One | +0.007 |
Morty | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
hy | +0.019 |
anne | +0.018 |
thia | +0.018 |
sed | +0.017 |
alo | +0.017 |
Neg logit contributions | |
First | -0.018 |
Pr | -0.015 |
One | -0.015 |
Morty | -0.015 |
Sn | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
First | +0.002 |
Pr | +0.002 |
One | +0.002 |
Morty | +0.002 |
Sn | +0.002 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
thia | -0.002 |
sed | -0.002 |
alo | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
First | +0.063 |
Pr | +0.058 |
One | +0.057 |
Sn | +0.055 |
Ro | +0.055 |
Neg logit contributions | |
hy | -0.043 |
anne | -0.039 |
alo | -0.038 |
ly | -0.037 |
sed | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
First | +0.006 |
Pr | +0.005 |
bowl | +0.005 |
One | +0.005 |
Sn | +0.005 |
Neg logit contributions | |
hy | -0.004 |
sed | -0.004 |
thia | -0.004 |
anne | -0.004 |
alo | -0.003 |
Token | stir |
Token ID | 11240 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
First | +0.024 |
Pr | +0.021 |
One | +0.021 |
Morty | +0.020 |
Sn | +0.020 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.016 |
thia | -0.016 |
sed | -0.016 |
alo | -0.015 |
Token | s |
Token ID | 82 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
First | +0.056 |
One | +0.050 |
Pr | +0.049 |
Ro | +0.047 |
Sn | +0.046 |
Neg logit contributions | |
led | -0.032 |
ly | -0.031 |
ed | -0.031 |
anne | -0.031 |
hy | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
First | +0.029 |
One | +0.026 |
Pr | +0.025 |
Ro | +0.024 |
Sn | +0.023 |
Neg logit contributions | |
face | -0.019 |
hy | -0.018 |
faces | -0.018 |
alo | -0.017 |
anne | -0.017 |
Token | stir |
Token ID | 11240 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
First | +0.009 |
One | +0.008 |
Pr | +0.007 |
Morty | +0.007 |
Sn | +0.007 |
Neg logit contributions | |
hy | -0.010 |
sed | -0.009 |
thia | -0.009 |
anne | -0.009 |
grin | -0.009 |
Token | s |
Token ID | 82 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
First | +0.074 |
One | +0.066 |
Pr | +0.066 |
Ro | +0.064 |
bar | +0.062 |
Neg logit contributions | |
led | -0.040 |
ly | -0.039 |
ed | -0.037 |
anne | -0.037 |
hy | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
First | +0.041 |
One | +0.038 |
Ro | +0.037 |
Pr | +0.036 |
Stri | +0.035 |
Neg logit contributions | |
face | -0.024 |
faces | -0.023 |
back | -0.021 |
- | -0.021 |
anne | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
First | +0.003 |
bowl | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
One | +0.003 |
Neg logit contributions | |
hy | -0.003 |
sed | -0.003 |
thia | -0.003 |
anne | -0.002 |
alo | -0.002 |
Token | puts |
Token ID | 7584 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
First | +0.032 |
Pr | +0.028 |
One | +0.027 |
Morty | +0.026 |
Sn | +0.026 |
Neg logit contributions | |
hy | -0.022 |
thia | -0.021 |
sed | -0.021 |
anne | -0.020 |
alo | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
First | +0.014 |
Pr | +0.012 |
One | +0.012 |
bank | +0.012 |
Ro | +0.012 |
Neg logit contributions | |
hy | -0.012 |
alo | -0.010 |
Katy | -0.010 |
led | -0.010 |
anne | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
First | +0.042 |
Pr | +0.039 |
Sn | +0.038 |
Morty | +0.037 |
One | +0.037 |
Neg logit contributions | |
hy | -0.020 |
anne | -0.017 |
sed | -0.017 |
alo | -0.016 |
thia | -0.016 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
hy | +0.004 |
anne | +0.003 |
thia | +0.003 |
sed | +0.003 |
alo | +0.003 |
Neg logit contributions | |
First | -0.004 |
One | -0.004 |
Pr | -0.004 |
Morty | -0.004 |
Sn | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
First | +0.016 |
One | +0.014 |
Pr | +0.014 |
bank | +0.014 |
Ro | +0.014 |
Neg logit contributions | |
hy | -0.010 |
ed | -0.009 |
ly | -0.009 |
Katy | -0.009 |
sed | -0.009 |
Token | spoon |
Token ID | 24556 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
First | +0.001 |
Stri | +0.001 |
Pr | +0.001 |
Morty | +0.001 |
One | +0.001 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.001 |
alo | -0.001 |
thia | -0.001 |
grin | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
First | +0.044 |
One | +0.040 |
Pr | +0.039 |
Sn | +0.039 |
Ro | +0.038 |
Neg logit contributions | |
hy | -0.020 |
anne | -0.017 |
alo | -0.016 |
sed | -0.015 |
ly | -0.015 |
Token | started |
Token ID | 2067 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
First | +0.011 |
One | +0.009 |
Pr | +0.009 |
Morty | +0.009 |
Sn | +0.009 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.008 |
thia | -0.008 |
sed | -0.008 |
alo | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
First | +0.104 |
One | +0.096 |
Ro | +0.094 |
Pr | +0.093 |
Ant | +0.091 |
Neg logit contributions | |
hy | -0.026 |
appeared | -0.024 |
thia | -0.024 |
- | -0.024 |
alo | -0.024 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
First | +0.051 |
Pr | +0.048 |
One | +0.046 |
Morty | +0.045 |
Fish | +0.044 |
Neg logit contributions | |
hy | -0.040 |
grin | -0.040 |
thia | -0.039 |
face | -0.038 |
hugged | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
First | +0.058 |
Pr | +0.052 |
Ro | +0.052 |
One | +0.049 |
Br | +0.047 |
Neg logit contributions | |
back | -0.021 |
- | -0.020 |
ly | -0.020 |
under | -0.019 |
face | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
hy | +0.016 |
thia | +0.015 |
anne | +0.014 |
sed | +0.014 |
alo | +0.014 |
Neg logit contributions | |
First | -0.017 |
Pr | -0.015 |
One | -0.015 |
bowl | -0.014 |
Morty | -0.014 |
Token | loved |
Token ID | 6151 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
First | +0.021 |
Pr | +0.019 |
One | +0.019 |
Morty | +0.019 |
Sn | +0.018 |
Neg logit contributions | |
hy | -0.012 |
thia | -0.012 |
anne | -0.012 |
sed | -0.011 |
cousins | -0.010 |
Token | took |
Token ID | 1718 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
hy | +0.004 |
anne | +0.004 |
thia | +0.004 |
sed | +0.003 |
alo | +0.003 |
Neg logit contributions | |
First | -0.006 |
One | -0.006 |
Pr | -0.006 |
Morty | -0.005 |
Sn | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
First | +0.010 |
Morty | +0.008 |
Pr | +0.008 |
One | +0.008 |
Pr | +0.008 |
Neg logit contributions | |
hy | -0.017 |
sed | -0.016 |
alo | -0.015 |
thia | -0.015 |
anne | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
First | +0.004 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Pr | +0.003 |
Neg logit contributions | |
hy | -0.006 |
sed | -0.006 |
anne | -0.006 |
thia | -0.006 |
alo | -0.005 |
Token | bowl |
Token ID | 9396 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
thia | +0.009 |
sed | +0.009 |
alo | +0.008 |
Neg logit contributions | |
First | -0.009 |
One | -0.008 |
Pr | -0.008 |
Morty | -0.008 |
Sn | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
First | +0.029 |
One | +0.026 |
Pr | +0.026 |
Morty | +0.026 |
Sn | +0.025 |
Neg logit contributions | |
hy | -0.014 |
anne | -0.012 |
thia | -0.012 |
sed | -0.012 |
alo | -0.011 |
Token | spoon |
Token ID | 24556 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.002 |
alo | +0.002 |
sed | +0.002 |
thia | +0.002 |
Neg logit contributions | |
First | -0.002 |
Pr | -0.002 |
Morty | -0.002 |
One | -0.002 |
Stri | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
First | +0.078 |
One | +0.072 |
Pr | +0.070 |
Morty | +0.068 |
Ro | +0.067 |
Neg logit contributions | |
hy | -0.036 |
anne | -0.032 |
alo | -0.031 |
sed | -0.030 |
thia | -0.030 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
First | +0.012 |
One | +0.011 |
Pr | +0.011 |
Morty | +0.010 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.012 |
anne | -0.011 |
thia | -0.010 |
sed | -0.010 |
alo | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
First | +0.034 |
One | +0.029 |
Pr | +0.029 |
Morty | +0.028 |
Sn | +0.028 |
Neg logit contributions | |
hy | -0.039 |
sed | -0.035 |
anne | -0.035 |
thia | -0.034 |
alo | -0.034 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
First | +0.049 |
One | +0.043 |
Pr | +0.043 |
Morty | +0.042 |
Sn | +0.041 |
Neg logit contributions | |
hy | -0.039 |
anne | -0.035 |
thia | -0.034 |
sed | -0.034 |
alo | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
First | +0.032 |
Pr | +0.029 |
Morty | +0.029 |
One | +0.028 |
Stri | +0.028 |
Neg logit contributions | |
hy | -0.027 |
anne | -0.026 |
thia | -0.025 |
bell | -0.024 |
alo | -0.024 |
Token | we |
Token ID | 356 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
hy | +0.035 |
anne | +0.034 |
thia | +0.032 |
alo | +0.031 |
sed | +0.031 |
Neg logit contributions | |
First | -0.039 |
One | -0.036 |
Pr | -0.034 |
Sn | -0.033 |
Morty | -0.033 |
Token | be |
Token ID | 307 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
hy | +0.012 |
thia | +0.011 |
sed | +0.010 |
anne | +0.010 |
cousins | +0.010 |
Neg logit contributions | |
First | -0.017 |
Pr | -0.015 |
Morty | -0.015 |
Sn | -0.015 |
Stri | -0.014 |
Token | your |
Token ID | 534 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.011 |
thia | +0.010 |
sed | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.010 |
One | -0.008 |
Pr | -0.008 |
Morty | -0.008 |
Sn | -0.008 |
Token | friends |
Token ID | 2460 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
First | +0.004 |
Sn | +0.003 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Neg logit contributions | |
sed | -0.002 |
cousins | -0.002 |
hy | -0.002 |
rav | -0.002 |
alo | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
hy | +0.027 |
anne | +0.025 |
thia | +0.024 |
alo | +0.024 |
sed | +0.024 |
Neg logit contributions | |
First | -0.020 |
Pr | -0.017 |
Morty | -0.016 |
One | -0.016 |
Sn | -0.016 |
Token | snail |
Token ID | 47374 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
First | +0.040 |
Pr | +0.033 |
One | +0.033 |
Morty | +0.033 |
Sn | +0.032 |
Neg logit contributions | |
hy | -0.037 |
sed | -0.034 |
alo | -0.033 |
cousins | -0.033 |
thia | -0.033 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
First | +0.061 |
Pr | +0.052 |
Sn | +0.050 |
Morty | +0.049 |
One | +0.048 |
Neg logit contributions | |
hy | -0.053 |
anne | -0.049 |
sed | -0.047 |
cousins | -0.047 |
ly | -0.047 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
First | +0.029 |
bowl | +0.023 |
Sn | +0.023 |
Pr | +0.023 |
Morty | +0.023 |
Neg logit contributions | |
hy | -0.024 |
sed | -0.021 |
Katy | -0.021 |
thia | -0.021 |
anne | -0.020 |
Token | asks |
Token ID | 7893 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
First | +0.013 |
Pr | +0.012 |
Br | +0.011 |
bowl | +0.011 |
Sn | +0.011 |
Neg logit contributions | |
smiles | -0.009 |
Jennifer | -0.008 |
thia | -0.008 |
Jennifer | -0.008 |
cousins | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
First | +0.005 |
One | +0.004 |
Pr | +0.004 |
Morty | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
First | +0.008 |
bowl | +0.007 |
bank | +0.007 |
Pr | +0.007 |
Morty | +0.007 |
Neg logit contributions | |
hy | -0.006 |
sed | -0.006 |
alo | -0.006 |
relieved | -0.006 |
anne | -0.005 |
Token | fell |
Token ID | 3214 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
hy | +0.026 |
anne | +0.026 |
rav | +0.025 |
thia | +0.024 |
Katy | +0.024 |
Neg logit contributions | |
First | -0.034 |
One | -0.030 |
Stri | -0.030 |
Pr | -0.030 |
stream | -0.030 |
Token | on |
Token ID | 319 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
First | +0.028 |
One | +0.025 |
Pr | +0.025 |
Morty | +0.025 |
Sn | +0.024 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.015 |
sed | -0.015 |
alo | -0.014 |
thia | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
hy | +0.006 |
anne | +0.005 |
sed | +0.005 |
thia | +0.005 |
alo | +0.005 |
Neg logit contributions | |
First | -0.006 |
Pr | -0.005 |
One | -0.005 |
bowl | -0.005 |
Sn | -0.005 |
Token | floor |
Token ID | 4314 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rav | +0.026 |
anne | +0.026 |
hy | +0.026 |
thia | +0.025 |
andra | +0.025 |
Neg logit contributions | |
First | -0.016 |
stream | -0.014 |
Pr | -0.014 |
log | -0.014 |
Sn | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
First | +0.042 |
Pr | +0.038 |
Morty | +0.037 |
One | +0.037 |
Sn | +0.037 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.015 |
sed | -0.014 |
alo | -0.014 |
thia | -0.014 |
Token | broke |
Token ID | 6265 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
hy | +0.003 |
sed | +0.003 |
anne | +0.003 |
alo | +0.003 |
thia | +0.003 |
Neg logit contributions | |
First | -0.004 |
One | -0.004 |
Pr | -0.004 |
Morty | -0.004 |
Sn | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
First | +0.070 |
One | +0.061 |
Pr | +0.059 |
Morty | +0.058 |
Sn | +0.057 |
Neg logit contributions | |
hy | -0.053 |
anne | -0.049 |
sed | -0.048 |
alo | -0.047 |
thia | -0.047 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
First | +0.017 |
One | +0.014 |
Morty | +0.014 |
Sn | +0.014 |
Pr | +0.014 |
Neg logit contributions | |
hy | -0.017 |
cousins | -0.017 |
thia | -0.016 |
anne | -0.016 |
sed | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
First | +0.038 |
Pr | +0.034 |
Morty | +0.033 |
Sn | +0.033 |
Stri | +0.032 |
Neg logit contributions | |
hy | -0.027 |
anne | -0.024 |
alo | -0.023 |
ly | -0.022 |
thia | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
hy | +0.000 |
sed | +0.000 |
anne | +0.000 |
Katy | +0.000 |
thia | +0.000 |
Neg logit contributions | |
First | -0.001 |
One | -0.001 |
Pr | -0.001 |
bowl | -0.001 |
Sn | -0.001 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
First | +0.005 |
One | +0.004 |
Pr | +0.004 |
Morty | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.003 |
anne | -0.003 |
thia | -0.003 |
sed | -0.003 |
alo | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
hy | +0.023 |
anne | +0.020 |
thia | +0.020 |
cousins | +0.020 |
alo | +0.020 |
Neg logit contributions | |
First | -0.024 |
bowl | -0.020 |
Pr | -0.020 |
Morty | -0.020 |
One | -0.019 |
Token | long |
Token ID | 890 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
First | +0.019 |
Morty | +0.016 |
Pr | +0.016 |
Stri | +0.016 |
One | +0.016 |
Neg logit contributions | |
hy | -0.015 |
anne | -0.014 |
thia | -0.013 |
sed | -0.013 |
alo | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hy | +0.000 |
anne | +0.000 |
thia | +0.000 |
sed | +0.000 |
alo | +0.000 |
Neg logit contributions | |
First | -0.001 |
Pr | -0.000 |
Morty | -0.000 |
Sn | -0.000 |
One | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.005 |
alo | +0.005 |
cousins | +0.004 |
thia | +0.004 |
Neg logit contributions | |
First | -0.008 |
Pr | -0.007 |
Morty | -0.007 |
Sn | -0.007 |
Ro | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
First | +0.009 |
Pr | +0.009 |
One | +0.008 |
Sn | +0.008 |
bowl | +0.008 |
Neg logit contributions | |
hy | -0.008 |
thia | -0.008 |
anne | -0.008 |
sed | -0.008 |
Katy | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.009 |
alo | +0.009 |
thia | +0.009 |
sed | +0.009 |
Neg logit contributions | |
First | -0.017 |
One | -0.015 |
Morty | -0.015 |
Stri | -0.015 |
Pr | -0.015 |
Token | Ben |
Token ID | 3932 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
First | +0.009 |
One | +0.008 |
Pr | +0.008 |
Sn | +0.008 |
Ro | +0.008 |
Neg logit contributions | |
hy | -0.007 |
thia | -0.006 |
sed | -0.006 |
andra | -0.006 |
cousins | -0.006 |
Token | get |
Token ID | 651 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
First | +0.017 |
One | +0.015 |
Morty | +0.014 |
Pr | +0.014 |
Sn | +0.014 |
Neg logit contributions | |
hy | -0.015 |
anne | -0.014 |
alo | -0.014 |
sed | -0.014 |
thia | -0.014 |
Token | bored |
Token ID | 17533 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
First | +0.002 |
Pr | +0.002 |
One | +0.002 |
Morty | +0.002 |
Sn | +0.002 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
thia | -0.002 |
sed | -0.002 |
alo | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.003 |
thia | +0.003 |
sed | +0.003 |
alo | +0.003 |
Neg logit contributions | |
First | -0.004 |
One | -0.003 |
Pr | -0.003 |
Morty | -0.003 |
Sn | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
hy | +0.043 |
anne | +0.042 |
thia | +0.041 |
sed | +0.041 |
alo | +0.039 |
Neg logit contributions | |
First | -0.031 |
One | -0.026 |
Pr | -0.025 |
Morty | -0.025 |
Stri | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
hy | +0.009 |
alo | +0.009 |
anne | +0.009 |
sed | +0.009 |
thia | +0.009 |
Neg logit contributions | |
First | -0.013 |
Stri | -0.011 |
One | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | busy |
Token ID | 8179 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
First | +0.014 |
Pr | +0.013 |
Morty | +0.012 |
One | +0.012 |
Sn | +0.012 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
alo | -0.009 |
thia | -0.009 |
sed | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
First | +0.030 |
Pr | +0.028 |
One | +0.027 |
Morty | +0.026 |
Sn | +0.026 |
Neg logit contributions | |
hy | -0.017 |
alo | -0.015 |
anne | -0.014 |
sed | -0.014 |
cousins | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
hy | +0.006 |
alo | +0.005 |
anne | +0.005 |
cousins | +0.005 |
Katy | +0.005 |
Neg logit contributions | |
First | -0.007 |
Pr | -0.006 |
Sn | -0.006 |
bowl | -0.006 |
Morty | -0.006 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
hy | +0.030 |
anne | +0.029 |
sed | +0.028 |
alo | +0.028 |
thia | +0.028 |
Neg logit contributions | |
First | -0.026 |
One | -0.023 |
Pr | -0.021 |
Sn | -0.021 |
Morty | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
First | +0.030 |
Pr | +0.026 |
One | +0.026 |
Morty | +0.025 |
Sn | +0.025 |
Neg logit contributions | |
hy | -0.026 |
anne | -0.024 |
sed | -0.023 |
thia | -0.023 |
alo | -0.023 |
Token | Then |
Token ID | 3244 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
First | +0.001 |
Pr | +0.001 |
Morty | +0.001 |
Stri | +0.001 |
stream | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
Katy | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
First | +0.026 |
One | +0.023 |
Pr | +0.023 |
Morty | +0.023 |
Sn | +0.022 |
Neg logit contributions | |
hy | -0.022 |
anne | -0.020 |
thia | -0.019 |
sed | -0.019 |
alo | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
hy | +0.001 |
anne | +0.001 |
thia | +0.001 |
sed | +0.001 |
alo | +0.001 |
Neg logit contributions | |
First | -0.002 |
Pr | -0.001 |
One | -0.001 |
Morty | -0.001 |
Sn | -0.001 |
Token | sne |
Token ID | 10505 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
First | +0.002 |
One | +0.001 |
Sn | +0.001 |
Stri | +0.001 |
Morty | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
alo | -0.001 |
sed | -0.001 |
rav | -0.001 |
Token | aked |
Token ID | 4335 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.006 |
thia | +0.006 |
sed | +0.006 |
alo | +0.006 |
Neg logit contributions | |
First | -0.008 |
Pr | -0.008 |
Morty | -0.008 |
One | -0.007 |
Stri | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
hy | +0.022 |
anne | +0.021 |
sed | +0.020 |
thia | +0.020 |
alo | +0.020 |
Neg logit contributions | |
First | -0.024 |
Pr | -0.021 |
One | -0.020 |
Morty | -0.020 |
Sn | -0.020 |
Token | help |
Token ID | 1037 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
First | +0.001 |
One | +0.001 |
Morty | +0.001 |
Pr | +0.001 |
Stri | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
hy | +0.006 |
anne | +0.005 |
thia | +0.005 |
sed | +0.005 |
alo | +0.005 |
Neg logit contributions | |
First | -0.007 |
One | -0.006 |
Pr | -0.006 |
Morty | -0.006 |
Sn | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
First | +0.021 |
Pr | +0.019 |
One | +0.018 |
Morty | +0.018 |
Sn | +0.018 |
Neg logit contributions | |
hy | -0.016 |
thia | -0.015 |
anne | -0.015 |
cousins | -0.015 |
alo | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
hy | +0.006 |
anne | +0.006 |
thia | +0.005 |
cousins | +0.005 |
rav | +0.005 |
Neg logit contributions | |
First | -0.010 |
Pr | -0.009 |
bowl | -0.008 |
Morty | -0.008 |
One | -0.008 |
Token | 's |
Token ID | 338 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.010 |
thia | +0.010 |
sed | +0.010 |
alo | +0.009 |
Neg logit contributions | |
First | -0.018 |
Pr | -0.016 |
One | -0.016 |
Morty | -0.016 |
Sn | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
First | +0.005 |
Pr | +0.005 |
Morty | +0.004 |
One | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.003 |
sed | -0.003 |
thia | -0.003 |
cousins | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
sed | +0.009 |
thia | +0.009 |
alo | +0.008 |
Neg logit contributions | |
First | -0.013 |
Pr | -0.011 |
One | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | race |
Token ID | 3234 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
First | +0.024 |
Pr | +0.020 |
Morty | +0.020 |
Sn | +0.020 |
Stri | +0.019 |
Neg logit contributions | |
hy | -0.019 |
sed | -0.017 |
cousins | -0.016 |
anne | -0.016 |
alo | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.010 |
sed | +0.010 |
alo | +0.010 |
thia | +0.010 |
Neg logit contributions | |
First | -0.013 |
Pr | -0.012 |
One | -0.011 |
Morty | -0.011 |
Sn | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
First | +0.004 |
One | +0.003 |
Morty | +0.003 |
Stri | +0.003 |
Pr | +0.003 |
Neg logit contributions | |
hy | -0.005 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
alo | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
First | +0.026 |
Pr | +0.022 |
One | +0.022 |
Sn | +0.021 |
Morty | +0.021 |
Neg logit contributions | |
hy | -0.021 |
anne | -0.018 |
alo | -0.017 |
bell | -0.016 |
thia | -0.016 |
Token | Bob |
Token ID | 5811 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
First | +0.016 |
Pr | +0.015 |
One | +0.015 |
bowl | +0.014 |
ba | +0.014 |
Neg logit contributions | |
hy | -0.013 |
thia | -0.011 |
anne | -0.011 |
sed | -0.011 |
Katy | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.004 |
thia | +0.004 |
sed | +0.004 |
rav | +0.004 |
Neg logit contributions | |
First | -0.011 |
One | -0.009 |
Pr | -0.009 |
Morty | -0.009 |
Sn | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
hy | +0.007 |
anne | +0.006 |
thia | +0.005 |
sed | +0.005 |
alo | +0.005 |
Neg logit contributions | |
First | -0.017 |
One | -0.015 |
Pr | -0.015 |
Morty | -0.015 |
Sn | -0.015 |
Token | � |
Token ID | 6184 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
thia | +0.009 |
sed | +0.008 |
alo | +0.008 |
Neg logit contributions | |
First | -0.019 |
bowl | -0.017 |
One | -0.016 |
Pr | -0.016 |
Morty | -0.016 |
Token | � |
Token ID | 95 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.004 |
thia | +0.004 |
sed | +0.004 |
alo | +0.004 |
Neg logit contributions | |
First | -0.006 |
Pr | -0.005 |
One | -0.005 |
Morty | -0.005 |
Stri | -0.005 |
Token | € |
Token ID | 26391 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
First | +0.001 |
One | +0.001 |
Pr | +0.001 |
Morty | +0.001 |
Sn | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | � |
Token ID | 129 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
hy | +0.011 |
alo | +0.011 |
anne | +0.011 |
sed | +0.011 |
ly | +0.010 |
Neg logit contributions | |
First | -0.008 |
One | -0.007 |
Stri | -0.007 |
Morty | -0.007 |
Sn | -0.007 |
Token | � |
Token ID | 241 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
First | +0.003 |
Pr | +0.002 |
One | +0.002 |
Morty | +0.002 |
Sn | +0.002 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
thia | -0.002 |
sed | -0.002 |
alo | -0.001 |
Token | You |
Token ID | 1639 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.003 |
bowl | +0.003 |
stream | +0.003 |
Morty | +0.003 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
rav | -0.004 |
thia | -0.004 |
sed | -0.003 |
Token | did |
Token ID | 750 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
thia | +0.009 |
sed | +0.008 |
alo | +0.008 |
Neg logit contributions | |
First | -0.014 |
Pr | -0.012 |
One | -0.012 |
Morty | -0.012 |
Sn | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.011 |
thia | +0.011 |
sed | +0.011 |
alo | +0.010 |
Neg logit contributions | |
First | -0.014 |
One | -0.013 |
Pr | -0.013 |
Morty | -0.012 |
Stri | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
hy | +0.003 |
anne | +0.003 |
thia | +0.003 |
alo | +0.003 |
sed | +0.003 |
Neg logit contributions | |
First | -0.003 |
One | -0.003 |
Morty | -0.003 |
Pr | -0.003 |
Stri | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
First | +0.019 |
Pr | +0.016 |
One | +0.016 |
Sn | +0.016 |
Morty | +0.015 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.015 |
Katy | -0.015 |
cousins | -0.015 |
thia | -0.015 |
Token | animals |
Token ID | 4695 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
First | +0.038 |
Morty | +0.033 |
Finn | +0.033 |
Sn | +0.033 |
Stri | +0.032 |
Neg logit contributions | |
hy | -0.021 |
sed | -0.021 |
thia | -0.020 |
anne | -0.019 |
cousins | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
First | +0.001 |
One | +0.001 |
Pr | +0.001 |
Morty | +0.001 |
Stri | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.010 |
thia | +0.010 |
sed | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.008 |
One | -0.007 |
Pr | -0.007 |
Morty | -0.007 |
Sn | -0.006 |
Token | forest |
Token ID | 8222 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
First | +0.028 |
Sn | +0.025 |
Stri | +0.025 |
Morty | +0.025 |
Finn | +0.025 |
Neg logit contributions | |
hy | -0.021 |
thia | -0.020 |
mailbox | -0.020 |
anne | -0.020 |
Jennifer | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
First | +0.019 |
One | +0.016 |
bowl | +0.016 |
Stri | +0.016 |
Morty | +0.016 |
Neg logit contributions | |
hy | -0.014 |
alo | -0.013 |
anne | -0.013 |
sed | -0.013 |
thia | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.004 |
thia | +0.004 |
sed | +0.004 |
alo | +0.004 |
Neg logit contributions | |
First | -0.006 |
One | -0.005 |
Pr | -0.005 |
Morty | -0.005 |
Sn | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
First | +0.041 |
Pr | +0.035 |
Sn | +0.035 |
One | +0.035 |
Morty | +0.033 |
Neg logit contributions | |
hy | -0.032 |
happened | -0.031 |
cousins | -0.030 |
Katy | -0.030 |
sed | -0.030 |
Token | could |
Token ID | 714 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
First | +0.001 |
One | +0.001 |
bowl | +0.001 |
Morty | +0.001 |
Finn | +0.001 |
Neg logit contributions | |
hy | -0.001 |
alo | -0.001 |
sed | -0.001 |
thia | -0.001 |
anne | -0.001 |
Token | check |
Token ID | 2198 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
First | +0.014 |
One | +0.012 |
Pr | +0.011 |
Morty | +0.011 |
Sn | +0.011 |
Neg logit contributions | |
hy | -0.016 |
anne | -0.015 |
thia | -0.015 |
sed | -0.015 |
alo | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hy | +0.023 |
anne | +0.021 |
thia | +0.021 |
sed | +0.021 |
alo | +0.020 |
Neg logit contributions | |
First | -0.025 |
One | -0.021 |
Pr | -0.021 |
Morty | -0.021 |
Stri | -0.021 |
Token | their |
Token ID | 511 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
hy | +0.027 |
anne | +0.025 |
thia | +0.025 |
sed | +0.025 |
alo | +0.024 |
Neg logit contributions | |
First | -0.024 |
One | -0.021 |
Pr | -0.020 |
Morty | -0.020 |
Sn | -0.020 |
Token | luggage |
Token ID | 31488 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.010 |
thia | +0.010 |
alo | +0.010 |
rav | +0.009 |
Neg logit contributions | |
First | -0.011 |
One | -0.010 |
stream | -0.010 |
Morty | -0.009 |
Pr | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
hy | +0.020 |
anne | +0.018 |
thia | +0.018 |
sed | +0.018 |
alo | +0.017 |
Neg logit contributions | |
First | -0.018 |
One | -0.015 |
Pr | -0.015 |
Morty | -0.015 |
Sn | -0.014 |
Token | But |
Token ID | 887 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.012 |
thia | +0.011 |
alo | +0.011 |
sed | +0.011 |
Neg logit contributions | |
First | -0.010 |
One | -0.008 |
Morty | -0.008 |
Pr | -0.008 |
Sn | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
hy | +0.014 |
anne | +0.013 |
thia | +0.013 |
alo | +0.012 |
sed | +0.012 |
Neg logit contributions | |
First | -0.009 |
One | -0.008 |
Morty | -0.008 |
Pr | -0.007 |
Stri | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
First | +0.011 |
One | +0.009 |
Stri | +0.009 |
Morty | +0.009 |
Sn | +0.009 |
Neg logit contributions | |
hy | -0.009 |
alo | -0.008 |
anne | -0.008 |
rav | -0.008 |
sed | -0.007 |
Token | luggage |
Token ID | 31488 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
First | +0.011 |
One | +0.009 |
Morty | +0.009 |
Sn | +0.009 |
Pr | +0.009 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.009 |
thia | -0.008 |
alo | -0.008 |
rav | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
rav | +0.019 |
anne | +0.019 |
thia | +0.019 |
alo | +0.018 |
Jennifer | +0.018 |
Neg logit contributions | |
First | -0.018 |
Stri | -0.015 |
stream | -0.015 |
sometimes | -0.015 |
stal | -0.015 |
Token | too |
Token ID | 1165 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
First | +0.024 |
One | +0.021 |
Pr | +0.021 |
Morty | +0.021 |
Sn | +0.020 |
Neg logit contributions | |
hy | -0.018 |
anne | -0.017 |
thia | -0.016 |
sed | -0.016 |
alo | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
First | +0.013 |
One | +0.012 |
Pr | +0.010 |
Sn | +0.010 |
Morty | +0.010 |
Neg logit contributions | |
hy | -0.019 |
alo | -0.017 |
sed | -0.017 |
anne | -0.017 |
thia | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
hy | +0.018 |
anne | +0.016 |
thia | +0.016 |
sed | +0.016 |
alo | +0.016 |
Neg logit contributions | |
First | -0.020 |
One | -0.018 |
Morty | -0.017 |
Pr | -0.017 |
Finn | -0.016 |
Token | there |
Token ID | 612 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
First | +0.001 |
One | +0.001 |
Pr | +0.001 |
Morty | +0.001 |
Sn | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.002 |
thia | +0.002 |
sed | +0.002 |
alo | +0.002 |
Neg logit contributions | |
First | -0.003 |
One | -0.003 |
Morty | -0.003 |
Pr | -0.003 |
Sn | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
First | +0.005 |
One | +0.004 |
Pr | +0.004 |
Morty | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.005 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
alo | -0.005 |
Token | mechanic |
Token ID | 21600 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
First | +0.001 |
One | +0.000 |
Pr | +0.000 |
Morty | +0.000 |
Sn | +0.000 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | named |
Token ID | 3706 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.004 |
thia | +0.004 |
sed | +0.004 |
alo | +0.004 |
Neg logit contributions | |
First | -0.007 |
Pr | -0.006 |
Morty | -0.006 |
One | -0.006 |
Sn | -0.006 |
Token | John |
Token ID | 1757 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
First | +0.036 |
Pr | +0.033 |
One | +0.031 |
bowl | +0.031 |
Morty | +0.031 |
Neg logit contributions | |
hy | -0.024 |
thia | -0.020 |
cousins | -0.019 |
anne | -0.019 |
sed | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.011 |
thia | +0.011 |
cousins | +0.010 |
sed | +0.010 |
Neg logit contributions | |
First | -0.016 |
Morty | -0.013 |
Pr | -0.013 |
Sn | -0.013 |
Finn | -0.013 |
Token | John |
Token ID | 1757 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.004 |
sed | +0.004 |
alo | +0.004 |
thia | +0.004 |
Neg logit contributions | |
First | -0.011 |
One | -0.010 |
Morty | -0.009 |
Pr | -0.009 |
Stri | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
hy | +0.025 |
alo | +0.024 |
anne | +0.024 |
sed | +0.023 |
rav | +0.023 |
Neg logit contributions | |
First | -0.039 |
One | -0.036 |
Sn | -0.034 |
Stri | -0.034 |
bowl | -0.034 |
Token | pet |
Token ID | 4273 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
hy | +0.017 |
anne | +0.017 |
thia | +0.016 |
alo | +0.015 |
sed | +0.015 |
Neg logit contributions | |
First | -0.020 |
One | -0.017 |
Pr | -0.017 |
Morty | -0.016 |
Sn | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
First | +0.011 |
One | +0.010 |
Pr | +0.010 |
Morty | +0.010 |
Stri | +0.010 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.009 |
thia | -0.008 |
alo | -0.008 |
sed | -0.008 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
First | +0.011 |
Pr | +0.010 |
One | +0.010 |
Morty | +0.009 |
Sn | +0.009 |
Neg logit contributions | |
hy | -0.008 |
anne | -0.007 |
sed | -0.007 |
thia | -0.007 |
alo | -0.007 |
Token | exceptionally |
Token ID | 24822 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
First | +0.033 |
One | +0.028 |
Pr | +0.028 |
Stri | +0.027 |
Morty | +0.027 |
Neg logit contributions | |
hy | -0.027 |
anne | -0.024 |
sed | -0.023 |
thia | -0.023 |
alo | -0.023 |
Token | curious |
Token ID | 11040 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
First | +0.002 |
Morty | +0.002 |
One | +0.002 |
Pr | +0.002 |
Pr | +0.002 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
thia | -0.002 |
alo | -0.002 |
sed | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
First | +0.012 |
Pr | +0.010 |
One | +0.010 |
Morty | +0.010 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
thia | -0.009 |
sed | -0.009 |
alo | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
hy | +0.001 |
sed | +0.001 |
thia | +0.001 |
anne | +0.001 |
Katy | +0.001 |
Neg logit contributions | |
First | -0.001 |
Pr | -0.001 |
One | -0.001 |
ba | -0.001 |
Sn | -0.001 |
Token | began |
Token ID | 2540 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
First | +0.005 |
One | +0.004 |
Pr | +0.004 |
Morty | +0.004 |
Sn | +0.004 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
thia | -0.004 |
sed | -0.004 |
alo | -0.004 |
Token | sniff |
Token ID | 26300 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
First | +0.044 |
Sn | +0.039 |
Pr | +0.038 |
One | +0.038 |
Morty | +0.038 |
Neg logit contributions | |
hy | -0.018 |
anne | -0.017 |
thia | -0.017 |
sed | -0.017 |
cousins | -0.015 |
Token | ing |
Token ID | 278 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
First | +0.028 |
One | +0.024 |
Pr | +0.024 |
Morty | +0.024 |
Sn | +0.024 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.015 |
thia | -0.015 |
sed | -0.015 |
alo | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
First | +0.027 |
One | +0.024 |
Pr | +0.024 |
Sn | +0.023 |
Morty | +0.023 |
Neg logit contributions | |
hy | -0.016 |
anne | -0.014 |
sed | -0.013 |
thia | -0.013 |
alo | -0.013 |
Token | worth |
Token ID | 2861 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
First | +0.015 |
One | +0.013 |
Pr | +0.013 |
Sn | +0.013 |
Ro | +0.013 |
Neg logit contributions | |
hy | -0.008 |
cousins | -0.007 |
anne | -0.007 |
relieved | -0.007 |
sed | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
First | +0.008 |
Pr | +0.006 |
One | +0.006 |
Morty | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
thia | -0.006 |
sed | -0.006 |
alo | -0.006 |
Token | effort |
Token ID | 3626 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
hy | +0.000 |
sed | +0.000 |
anne | +0.000 |
cousins | +0.000 |
grin | +0.000 |
Neg logit contributions | |
First | -0.001 |
Morty | -0.000 |
Stri | -0.000 |
Pr | -0.000 |
bowl | -0.000 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
First | +0.020 |
One | +0.017 |
Pr | +0.017 |
Morty | +0.017 |
Sn | +0.017 |
Neg logit contributions | |
hy | -0.017 |
anne | -0.016 |
thia | -0.016 |
sed | -0.015 |
alo | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
First | +0.007 |
log | +0.007 |
Pr | +0.007 |
Fisher | +0.007 |
stalk | +0.007 |
Neg logit contributions | |
hy | -0.007 |
anne | -0.006 |
Katy | -0.006 |
Sarah | -0.006 |
thia | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
anne | +0.001 |
thia | +0.001 |
Jennifer | +0.001 |
hy | +0.001 |
rav | +0.001 |
Neg logit contributions | |
peas | -0.002 |
First | -0.002 |
cuc | -0.002 |
stalk | -0.002 |
Fisher | -0.002 |
Token | But |
Token ID | 1537 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Jennifer | +0.001 |
Sarah | +0.001 |
anne | +0.001 |
thia | +0.001 |
hy | +0.001 |
Neg logit contributions | |
peas | -0.002 |
Fisher | -0.002 |
minerals | -0.002 |
stalk | -0.002 |
cabbage | -0.002 |
Token | L |
Token ID | 406 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
hy | +0.012 |
anne | +0.011 |
sed | +0.011 |
cousins | +0.010 |
Katy | +0.010 |
Neg logit contributions | |
First | -0.013 |
Pr | -0.011 |
One | -0.010 |
Sn | -0.010 |
bowl | -0.010 |
Token | ill |
Token ID | 359 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
First | +0.002 |
Pr | +0.002 |
One | +0.002 |
Morty | +0.002 |
Sn | +0.002 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
thia | -0.002 |
alo | -0.002 |
sed | -0.002 |
Token | ie |
Token ID | 494 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
First | +0.021 |
Pr | +0.019 |
One | +0.018 |
Morty | +0.018 |
Sn | +0.018 |
Neg logit contributions | |
hy | -0.014 |
anne | -0.013 |
thia | -0.012 |
sed | -0.012 |
alo | -0.011 |
Token | still |
Token ID | 991 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
First | +0.013 |
One | +0.011 |
Pr | +0.011 |
Morty | +0.011 |
Sn | +0.011 |
Neg logit contributions | |
hy | -0.009 |
anne | -0.008 |
thia | -0.008 |
sed | -0.008 |
alo | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
First | +0.006 |
Pr | +0.006 |
Morty | +0.005 |
Sn | +0.005 |
Stri | +0.005 |
Neg logit contributions | |
hy | -0.004 |
sed | -0.003 |
anne | -0.003 |
alo | -0.003 |
cousins | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
First | +0.012 |
Fish | +0.010 |
bowl | +0.010 |
inn | +0.010 |
Sn | +0.010 |
Neg logit contributions | |
hy | -0.004 |
Katy | -0.003 |
eyes | -0.003 |
grandma | -0.003 |
Sarah | -0.003 |
Token | forest |
Token ID | 8222 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
First | +0.016 |
Morty | +0.014 |
Stri | +0.014 |
Pr | +0.013 |
First | +0.013 |
Neg logit contributions | |
hy | -0.013 |
thia | -0.011 |
back | -0.010 |
alo | -0.010 |
sed | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
First | +0.013 |
Pr | +0.011 |
Morty | +0.011 |
Sn | +0.011 |
Stri | +0.011 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
thia | -0.009 |
sed | -0.008 |
alo | -0.008 |
Token | One |
Token ID | 1881 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
hy | +0.004 |
thia | +0.004 |
anne | +0.004 |
Susan | +0.004 |
Katy | +0.004 |
Neg logit contributions | |
First | -0.006 |
ba | -0.006 |
Pr | -0.006 |
Morty | -0.006 |
b | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
First | +0.017 |
Morty | +0.013 |
Pr | +0.013 |
Stri | +0.013 |
One | +0.013 |
Neg logit contributions | |
hy | -0.026 |
anne | -0.025 |
thia | -0.024 |
sed | -0.024 |
alo | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
hy | +0.005 |
anne | +0.005 |
thia | +0.005 |
alo | +0.004 |
cousins | +0.004 |
Neg logit contributions | |
First | -0.005 |
One | -0.004 |
Morty | -0.004 |
Pr | -0.004 |
Finn | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
hy | +0.001 |
sed | +0.001 |
anne | +0.001 |
thia | +0.001 |
alo | +0.001 |
Neg logit contributions | |
First | -0.001 |
Pr | -0.001 |
One | -0.001 |
Morty | -0.001 |
Sn | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
First | +0.007 |
One | +0.006 |
Pr | +0.006 |
Morty | +0.006 |
Sn | +0.006 |
Neg logit contributions | |
hy | -0.006 |
anne | -0.006 |
thia | -0.006 |
sed | -0.005 |
alo | -0.005 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
First | +0.009 |
One | +0.008 |
Pr | +0.008 |
Morty | +0.008 |
Sn | +0.008 |
Neg logit contributions | |
hy | -0.007 |
sed | -0.007 |
anne | -0.007 |
alo | -0.006 |
thia | -0.006 |
Token | came |
Token ID | 1625 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hy | +0.046 |
alo | +0.045 |
ige | +0.044 |
ote | +0.044 |
thia | +0.044 |
Neg logit contributions | |
First | -0.027 |
D | -0.027 |
stream | -0.027 |
Pr | -0.026 |
st | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
First | +0.021 |
Pr | +0.020 |
Morty | +0.020 |
Sn | +0.019 |
One | +0.019 |
Neg logit contributions | |
hy | -0.010 |
anne | -0.009 |
sed | -0.008 |
cousins | -0.008 |
thia | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
First | +0.031 |
Pr | +0.027 |
Morty | +0.027 |
One | +0.026 |
Sn | +0.026 |
Neg logit contributions | |
hy | -0.023 |
sed | -0.020 |
thia | -0.019 |
anne | -0.019 |
alo | -0.019 |
Token | share |
Token ID | 2648 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
First | +0.004 |
Pr | +0.003 |
Morty | +0.003 |
bowl | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.003 |
thia | -0.003 |
anne | -0.003 |
sed | -0.003 |
cousins | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
First | +0.005 |
Pr | +0.004 |
Morty | +0.004 |
One | +0.004 |
Stri | +0.004 |
Neg logit contributions | |
hy | -0.004 |
anne | -0.004 |
thia | -0.004 |
alo | -0.004 |
cousins | -0.004 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hy | +0.018 |
sed | +0.016 |
cousins | +0.015 |
thia | +0.015 |
anne | +0.015 |
Neg logit contributions | |
First | -0.023 |
Pr | -0.020 |
Morty | -0.020 |
One | -0.020 |
Stri | -0.020 |
Token | ay |
Token ID | 323 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
hy | +0.014 |
sed | +0.012 |
anne | +0.011 |
thia | +0.011 |
alo | +0.010 |
Neg logit contributions | |
First | -0.047 |
One | -0.043 |
Pr | -0.043 |
Morty | -0.042 |
Sn | -0.042 |
Token | ons |
Token ID | 684 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
sed | +0.077 |
hy | +0.077 |
anne | +0.069 |
thia | +0.069 |
alo | +0.067 |
Neg logit contributions | |
First | -0.085 |
One | -0.077 |
Pr | -0.076 |
bowl | -0.073 |
Stri | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
hy | +0.010 |
anne | +0.009 |
alo | +0.009 |
thia | +0.009 |
cousins | +0.009 |
Neg logit contributions | |
First | -0.012 |
Pr | -0.011 |
Stri | -0.010 |
Morty | -0.010 |
One | -0.010 |
Token | You |
Token ID | 921 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
First | +0.004 |
stream | +0.004 |
log | +0.004 |
stalk | +0.004 |
Pr | +0.004 |
Neg logit contributions | |
hy | -0.002 |
thia | -0.002 |
cousins | -0.002 |
rav | -0.002 |
Katy | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
hy | +0.009 |
anne | +0.008 |
thia | +0.008 |
sed | +0.008 |
alo | +0.008 |
Neg logit contributions | |
First | -0.013 |
Pr | -0.012 |
One | -0.012 |
Morty | -0.012 |
Sn | -0.011 |
Token | show |
Token ID | 905 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
hy | +0.016 |
thia | +0.014 |
bell | +0.012 |
anne | +0.012 |
grin | +0.012 |
Neg logit contributions | |
First | -0.027 |
Pr | -0.024 |
Pr | -0.023 |
Morty | -0.023 |
Sn | -0.023 |
Token | field |
Token ID | 2214 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.012 |
thia | +0.012 |
sed | +0.012 |
alo | +0.012 |
Neg logit contributions | |
First | -0.010 |
One | -0.008 |
Pr | -0.008 |
Morty | -0.008 |
Sn | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
hy | +0.010 |
rav | +0.010 |
thia | +0.009 |
cousins | +0.009 |
icol | +0.009 |
Neg logit contributions | |
First | -0.008 |
stream | -0.008 |
stal | -0.007 |
log | -0.007 |
One | -0.007 |
Token | empty |
Token ID | 6565 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
hy | +0.001 |
anne | +0.001 |
thia | +0.001 |
sed | +0.001 |
alo | +0.001 |
Neg logit contributions | |
First | -0.001 |
One | -0.001 |
Pr | -0.001 |
Morty | -0.001 |
Sn | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
First | +0.004 |
One | +0.003 |
stream | +0.003 |
Morty | +0.003 |
Stri | +0.003 |
Neg logit contributions | |
hy | -0.003 |
thia | -0.003 |
anne | -0.003 |
rav | -0.003 |
sed | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
hy | +0.011 |
anne | +0.011 |
thia | +0.010 |
sed | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.012 |
One | -0.010 |
Pr | -0.010 |
Morty | -0.010 |
Sn | -0.010 |
Token | Where |
Token ID | 8496 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
hy | +0.024 |
anne | +0.022 |
thia | +0.022 |
alo | +0.021 |
cousins | +0.021 |
Neg logit contributions | |
First | -0.020 |
Morty | -0.018 |
Stri | -0.018 |
Finn | -0.017 |
Pr | -0.017 |
Token | did |
Token ID | 750 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
ote | +0.068 |
icol | +0.067 |
alo | +0.064 |
hy | +0.063 |
anne | +0.063 |
Neg logit contributions | |
First | -0.045 |
if | -0.045 |
One | -0.041 |
sometimes | -0.038 |
Sp | -0.037 |
Token | all |
Token ID | 477 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
hy | +0.028 |
anne | +0.028 |
sed | +0.028 |
thia | +0.027 |
alo | +0.027 |
Neg logit contributions | |
First | -0.017 |
One | -0.015 |
Pr | -0.015 |
Stri | -0.014 |
Morty | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
hy | +0.045 |
anne | +0.042 |
sed | +0.041 |
thia | +0.041 |
alo | +0.041 |
Neg logit contributions | |
First | -0.033 |
One | -0.027 |
Pr | -0.027 |
Morty | -0.027 |
Stri | -0.026 |
Token | wheat |
Token ID | 17135 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.012 |
sed | +0.012 |
alo | +0.012 |
thia | +0.012 |
Neg logit contributions | |
First | -0.009 |
One | -0.008 |
Pr | -0.008 |
Morty | -0.007 |
Sn | -0.007 |
Token | go |
Token ID | 467 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
First | +0.008 |
stream | +0.007 |
One | +0.007 |
bowl | +0.006 |
season | +0.006 |
Neg logit contributions | |
hy | -0.011 |
anne | -0.010 |
thia | -0.010 |
sed | -0.010 |
rav | -0.010 |
Token | with |
Token ID | 351 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
anne | +0.029 |
thia | +0.028 |
rav | +0.027 |
Jennifer | +0.026 |
ige | +0.026 |
Neg logit contributions | |
One | -0.022 |
First | -0.022 |
Stri | -0.021 |
stream | -0.021 |
Fisher | -0.021 |
Token | flashing |
Token ID | 25293 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hy | +0.028 |
anne | +0.027 |
thia | +0.026 |
sed | +0.025 |
alo | +0.025 |
Neg logit contributions | |
First | -0.026 |
One | -0.022 |
Pr | -0.022 |
Morty | -0.021 |
Stri | -0.021 |
Token | lights |
Token ID | 7588 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
anne | +0.035 |
Jennifer | +0.034 |
rav | +0.034 |
thia | +0.034 |
sed | +0.033 |
Neg logit contributions | |
stream | -0.021 |
First | -0.021 |
one | -0.021 |
wood | -0.021 |
One | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
anne | +0.049 |
rav | +0.048 |
thia | +0.048 |
Jennifer | +0.047 |
sed | +0.046 |
Neg logit contributions | |
First | -0.043 |
stream | -0.040 |
One | -0.039 |
Stri | -0.037 |
Fisher | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
hy | +0.005 |
sed | +0.005 |
anne | +0.005 |
thia | +0.005 |
alo | +0.005 |
Neg logit contributions | |
First | -0.010 |
One | -0.009 |
Pr | -0.009 |
Sn | -0.009 |
Morty | -0.009 |
Token | stopped |
Token ID | 5025 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
hy | +0.033 |
anne | +0.031 |
alo | +0.030 |
rav | +0.029 |
thia | +0.029 |
Neg logit contributions | |
First | -0.043 |
One | -0.040 |
Stri | -0.038 |
Sn | -0.038 |
Morty | -0.038 |
Token | near |
Token ID | 1474 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
hy | +0.055 |
anne | +0.052 |
thia | +0.050 |
sed | +0.049 |
alo | +0.048 |
Neg logit contributions | |
First | -0.062 |
One | -0.057 |
Pr | -0.056 |
Stri | -0.056 |
Morty | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
hy | +0.015 |
anne | +0.014 |
thia | +0.013 |
sed | +0.013 |
alo | +0.013 |
Neg logit contributions | |
First | -0.012 |
One | -0.011 |
Pr | -0.011 |
Morty | -0.010 |
Stri | -0.010 |
Token | tunnel |
Token ID | 13275 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
First | +0.004 |
stream | +0.003 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Neg logit contributions | |
anne | -0.006 |
hy | -0.005 |
thia | -0.005 |
alo | -0.005 |
andra | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
hy | +0.026 |
anne | +0.025 |
thia | +0.025 |
sed | +0.024 |
rav | +0.024 |
Neg logit contributions | |
First | -0.025 |
One | -0.022 |
Morty | -0.021 |
Pr | -0.021 |
Stri | -0.020 |
Token | Some |
Token ID | 2773 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
hy | +0.002 |
sed | +0.002 |
anne | +0.002 |
thia | +0.002 |
alo | +0.002 |
Neg logit contributions | |
First | -0.004 |
One | -0.004 |
Pr | -0.004 |
Sn | -0.004 |
Morty | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
hy | +0.015 |
anne | +0.014 |
thia | +0.013 |
sed | +0.013 |
alo | +0.013 |
Neg logit contributions | |
First | -0.023 |
One | -0.021 |
Pr | -0.020 |
Morty | -0.020 |
Sn | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
hy | +0.024 |
anne | +0.022 |
alo | +0.022 |
sed | +0.022 |
rav | +0.021 |
Neg logit contributions | |
First | -0.026 |
Stri | -0.023 |
Pr | -0.022 |
Pr | -0.022 |
One | -0.022 |
Token | expensive |
Token ID | 5789 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
hy | +0.017 |
sed | +0.015 |
thia | +0.015 |
anne | +0.015 |
cousins | +0.014 |
Neg logit contributions | |
First | -0.020 |
Morty | -0.017 |
Pr | -0.017 |
Sn | -0.016 |
Stri | -0.016 |
Token | ash |
Token ID | 12530 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
First | +0.004 |
One | +0.003 |
Pr | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.005 |
anne | -0.005 |
thia | -0.005 |
sed | -0.005 |
alo | -0.005 |
Token | tr |
Token ID | 2213 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
hy | +0.025 |
anne | +0.023 |
thia | +0.023 |
rav | +0.022 |
sed | +0.022 |
Neg logit contributions | |
First | -0.048 |
One | -0.043 |
Pr | -0.043 |
Stri | -0.042 |
Pr | -0.042 |
Token | ay |
Token ID | 323 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
ote | +0.053 |
anne | +0.052 |
thia | +0.052 |
hy | +0.051 |
sed | +0.050 |
Neg logit contributions | |
First | -0.104 |
bar | -0.101 |
One | -0.095 |
Stri | -0.093 |
O | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
hy | +0.050 |
anne | +0.047 |
thia | +0.047 |
sed | +0.047 |
alo | +0.046 |
Neg logit contributions | |
First | -0.060 |
One | -0.053 |
Stri | -0.052 |
Pr | -0.052 |
Morty | -0.052 |
Token | At |
Token ID | 1629 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
hy | +0.017 |
anne | +0.016 |
thia | +0.016 |
sed | +0.015 |
alo | +0.015 |
Neg logit contributions | |
First | -0.018 |
Pr | -0.016 |
Morty | -0.016 |
Sn | -0.016 |
One | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
hy | +0.016 |
anne | +0.014 |
alo | +0.014 |
sed | +0.013 |
Katy | +0.013 |
Neg logit contributions | |
First | -0.017 |
Pr | -0.015 |
bowl | -0.014 |
Sn | -0.014 |
Morty | -0.014 |
Token | end |
Token ID | 886 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
hy | +0.013 |
thia | +0.011 |
anne | +0.010 |
cousins | +0.010 |
andra | +0.010 |
Neg logit contributions | |
First | -0.023 |
Finn | -0.021 |
Morty | -0.021 |
Stri | -0.021 |
Pr | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
hy | +0.012 |
sed | +0.011 |
anne | +0.011 |
thia | +0.010 |
alo | +0.010 |
Neg logit contributions | |
First | -0.015 |
One | -0.013 |
Morty | -0.013 |
Pr | -0.013 |
Stri | -0.012 |
Token | further |
Token ID | 2252 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
First | +0.030 |
One | +0.025 |
Pr | +0.025 |
Morty | +0.024 |
Sn | +0.023 |
Neg logit contributions | |
hy | -0.047 |
anne | -0.045 |
thia | -0.044 |
sed | -0.043 |
alo | -0.043 |
Token | down |
Token ID | 866 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
First | +0.014 |
One | +0.012 |
Morty | +0.012 |
Pr | +0.012 |
Stri | +0.012 |
Neg logit contributions | |
hy | -0.016 |
thia | -0.016 |
anne | -0.015 |
sed | -0.015 |
alo | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
First | +0.029 |
Pr | +0.025 |
One | +0.024 |
Sn | +0.024 |
Morty | +0.024 |
Neg logit contributions | |
hy | -0.021 |
anne | -0.019 |
alo | -0.018 |
sed | -0.017 |
bell | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
hy | +0.013 |
anne | +0.012 |
thia | +0.012 |
sed | +0.012 |
alo | +0.012 |
Neg logit contributions | |
First | -0.009 |
One | -0.007 |
Pr | -0.007 |
Morty | -0.007 |
Sn | -0.007 |
Token | wondered |
Token ID | 14028 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
First | +0.003 |
One | +0.003 |
Stri | +0.003 |
Morty | +0.003 |
Sn | +0.003 |
Neg logit contributions | |
hy | -0.002 |
anne | -0.002 |
alo | -0.002 |
sed | -0.002 |
thia | -0.002 |
Token | what |
Token ID | 644 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
hy | +0.002 |
anne | +0.002 |
sed | +0.002 |
thia | +0.002 |
alo | +0.002 |
Neg logit contributions | |
First | -0.001 |
if | -0.001 |
One | -0.001 |
Pr | -0.001 |
Stri | -0.001 |
Token | else |
Token ID | 2073 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
hy | +0.075 |
sed | +0.071 |
alo | +0.070 |
thia | +0.068 |
anne | +0.068 |
Neg logit contributions | |
First | -0.051 |
One | -0.044 |
Pr | -0.041 |
Pr | -0.041 |
Sn | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
hy | +0.018 |
sed | +0.017 |
thia | +0.017 |
anne | +0.016 |
alo | +0.016 |
Neg logit contributions | |
First | -0.013 |
One | -0.011 |
Pr | -0.011 |
stream | -0.011 |
Morty | -0.010 |
Token | down |
Token ID | 866 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
First | +0.035 |
One | +0.032 |
Morty | +0.031 |
Pr | +0.031 |
Stri | +0.030 |
Neg logit contributions | |
hy | -0.026 |
anne | -0.024 |
thia | -0.024 |
sed | -0.023 |
alo | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
First | +0.002 |
Pr | +0.001 |
One | +0.001 |
Morty | +0.001 |
Sn | +0.001 |
Neg logit contributions | |
hy | -0.001 |
anne | -0.001 |
thia | -0.001 |
sed | -0.001 |
alo | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
First | +0.001 |
Sn | +0.001 |
Pr | +0.001 |
bowl | +0.001 |
Stri | +0.001 |
Neg logit contributions | |
hy | -0.001 |
Katy | -0.001 |
Jennifer | -0.001 |
Jennifer | -0.001 |
anne | -0.001 |