Token | and |
Token ID | 290 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ercise | +0.114 |
ams | +0.103 |
isdom | +0.102 |
ets | +0.101 |
reci | +0.097 |
Neg logit contributions | |
Ana | -0.113 |
El | -0.108 |
Pen | -0.106 |
Mir | -0.104 |
Fl | -0.101 |
Token | white |
Token ID | 2330 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ets | +0.124 |
ercise | +0.124 |
ock | +0.123 |
ams | +0.123 |
isdom | +0.114 |
Neg logit contributions | |
Ana | -0.099 |
Pen | -0.092 |
Mir | -0.091 |
El | -0.088 |
Mil | -0.084 |
Token | cloth |
Token ID | 16270 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ercise | +0.087 |
ams | +0.084 |
ets | +0.084 |
ock | +0.080 |
isdom | +0.076 |
Neg logit contributions | |
Ana | -0.116 |
Pen | -0.110 |
Mir | -0.108 |
El | -0.108 |
Megan | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
ets | +0.048 |
ercise | +0.047 |
ams | +0.047 |
ock | +0.044 |
isdom | +0.039 |
Neg logit contributions | |
Ana | -0.072 |
Pen | -0.069 |
Mir | -0.066 |
Megan | -0.065 |
El | -0.064 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ercise | +0.110 |
ets | +0.109 |
ams | +0.108 |
ock | +0.105 |
isdom | +0.097 |
Neg logit contributions | |
Ana | -0.099 |
Pen | -0.094 |
Mir | -0.090 |
El | -0.088 |
Megan | -0.087 |
Token | se |
Token ID | 384 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
ercise | +0.054 |
ets | +0.054 |
ams | +0.053 |
ock | +0.050 |
isdom | +0.047 |
Neg logit contributions | |
Ana | -0.049 |
Pen | -0.047 |
Megan | -0.044 |
Mir | -0.044 |
El | -0.043 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
weet | +0.137 |
jets | +0.132 |
since | +0.128 |
elling | +0.125 |
icated | +0.118 |
Neg logit contributions | |
Ana | -0.173 |
Megan | -0.170 |
plun | -0.169 |
Mir | -0.169 |
Mil | -0.165 |
Token | them |
Token ID | 606 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ercise | +0.064 |
ets | +0.063 |
ams | +0.063 |
ock | +0.059 |
isdom | +0.054 |
Neg logit contributions | |
Ana | -0.088 |
Pen | -0.085 |
Mir | -0.081 |
Megan | -0.080 |
El | -0.079 |
Token | together |
Token ID | 1978 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ets | +0.023 |
ercise | +0.022 |
ams | +0.022 |
ock | +0.021 |
isdom | +0.019 |
Neg logit contributions | |
Ana | -0.031 |
Pen | -0.030 |
Mir | -0.028 |
Megan | -0.028 |
El | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
ets | +0.048 |
ercise | +0.048 |
ams | +0.048 |
ock | +0.045 |
isdom | +0.040 |
Neg logit contributions | |
Ana | -0.065 |
Pen | -0.063 |
Mir | -0.060 |
Megan | -0.059 |
El | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ercise | +0.027 |
ets | +0.027 |
ams | +0.026 |
ock | +0.025 |
isdom | +0.023 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.025 |
Mir | -0.024 |
Megan | -0.024 |
El | -0.023 |
Token | own |
Token ID | 898 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ercise | +0.014 |
ets | +0.014 |
ams | +0.014 |
ock | +0.013 |
isdom | +0.012 |
Neg logit contributions | |
Ana | -0.013 |
Pen | -0.013 |
Mir | -0.012 |
Megan | -0.012 |
El | -0.012 |
Token | two |
Token ID | 734 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ets | +0.029 |
ercise | +0.028 |
ams | +0.028 |
ock | +0.027 |
isdom | +0.025 |
Neg logit contributions | |
Ana | -0.027 |
Pen | -0.026 |
plun | -0.024 |
El | -0.024 |
Ell | -0.024 |
Token | hands |
Token ID | 2832 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
ercise | +0.067 |
ets | +0.065 |
ams | +0.065 |
ock | +0.062 |
isdom | +0.060 |
Neg logit contributions | |
Ana | -0.066 |
Pen | -0.063 |
Megan | -0.059 |
El | -0.059 |
Mir | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ercise | +0.073 |
ets | +0.071 |
ams | +0.070 |
ock | +0.066 |
isdom | +0.062 |
Neg logit contributions | |
Ana | -0.098 |
Pen | -0.095 |
Megan | -0.090 |
Mir | -0.090 |
El | -0.089 |
Token | She |
Token ID | 1375 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ercise | +0.034 |
ams | +0.034 |
ets | +0.034 |
ock | +0.032 |
isdom | +0.030 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.038 |
plun | -0.036 |
gen | -0.036 |
Mir | -0.035 |
Token | se |
Token ID | 384 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
Ana | +0.009 |
Pen | +0.008 |
Mir | +0.008 |
Megan | +0.008 |
El | +0.008 |
Neg logit contributions | |
ercise | -0.010 |
ets | -0.010 |
ams | -0.010 |
ock | -0.009 |
isdom | -0.009 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ercise | +0.122 |
jets | +0.121 |
pads | +0.110 |
weet | +0.110 |
ully | +0.105 |
Neg logit contributions | |
Ana | -0.206 |
Megan | -0.201 |
gen | -0.196 |
illi | -0.191 |
Mir | -0.190 |
Token | it |
Token ID | 340 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
ercise | +0.074 |
ets | +0.074 |
ams | +0.072 |
ock | +0.067 |
isdom | +0.066 |
Neg logit contributions | |
Ana | -0.084 |
Pen | -0.080 |
Mir | -0.077 |
El | -0.076 |
Megan | -0.075 |
Token | with |
Token ID | 351 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ercise | +0.008 |
ets | +0.008 |
ams | +0.008 |
ock | +0.008 |
isdom | +0.007 |
Neg logit contributions | |
Ana | -0.011 |
Pen | -0.011 |
Mir | -0.010 |
Megan | -0.010 |
El | -0.010 |
Token | bright |
Token ID | 6016 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ets | +0.028 |
ercise | +0.028 |
ams | +0.028 |
ock | +0.026 |
isdom | +0.025 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.024 |
El | -0.023 |
Mir | -0.023 |
Ell | -0.023 |
Token | colors |
Token ID | 7577 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ercise | +0.108 |
ets | +0.100 |
isdom | +0.097 |
ams | +0.094 |
earned | +0.092 |
Neg logit contributions | |
Ana | -0.091 |
Ell | -0.090 |
El | -0.088 |
Mir | -0.084 |
Pen | -0.083 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ercise | +0.069 |
ams | +0.069 |
ets | +0.069 |
ock | +0.064 |
isdom | +0.061 |
Neg logit contributions | |
Ana | -0.078 |
Pen | -0.074 |
Mir | -0.070 |
El | -0.069 |
Megan | -0.069 |
Token | needle |
Token ID | 17598 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ercise | +0.044 |
ets | +0.043 |
ock | +0.042 |
ams | +0.041 |
weet | +0.038 |
Neg logit contributions | |
Ana | -0.043 |
Pen | -0.042 |
Mir | -0.040 |
Megan | -0.040 |
El | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ercise | +0.029 |
ams | +0.028 |
ets | +0.026 |
isdom | +0.024 |
ock | +0.024 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.039 |
El | -0.036 |
Mir | -0.036 |
stack | -0.036 |
Token | thread |
Token ID | 4704 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ets | +0.122 |
ams | +0.122 |
ercise | +0.120 |
ock | +0.115 |
isdom | +0.108 |
Neg logit contributions | |
Ana | -0.100 |
Pen | -0.096 |
Mir | -0.090 |
El | -0.088 |
plun | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ets | +0.048 |
ercise | +0.048 |
ams | +0.047 |
ock | +0.044 |
isdom | +0.039 |
Neg logit contributions | |
Ana | -0.084 |
Pen | -0.081 |
Mir | -0.077 |
Megan | -0.077 |
El | -0.076 |
Token | se |
Token ID | 384 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
ets | +0.110 |
ams | +0.110 |
ercise | +0.110 |
ock | +0.104 |
isdom | +0.098 |
Neg logit contributions | |
Ana | -0.094 |
Pen | -0.089 |
Mir | -0.084 |
El | -0.082 |
Megan | -0.082 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
jets | +0.129 |
weet | +0.126 |
since | +0.118 |
ercise | +0.113 |
ully | +0.112 |
Neg logit contributions | |
Ana | -0.174 |
Megan | -0.173 |
plun | -0.171 |
Mir | -0.163 |
Pen | -0.161 |
Token | Teddy |
Token ID | 29345 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ercise | +0.060 |
ets | +0.060 |
ams | +0.059 |
ock | +0.056 |
isdom | +0.050 |
Neg logit contributions | |
Ana | -0.080 |
Pen | -0.077 |
Megan | -0.073 |
Mir | -0.072 |
El | -0.071 |
Token | 's |
Token ID | 338 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ets | +0.037 |
ercise | +0.036 |
ams | +0.035 |
ock | +0.033 |
pads | +0.029 |
Neg logit contributions | |
Ana | -0.057 |
Pen | -0.055 |
Mir | -0.053 |
Megan | -0.053 |
El | -0.052 |
Token | eye |
Token ID | 4151 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
ercise | +0.010 |
ets | +0.010 |
ams | +0.010 |
ock | +0.009 |
isdom | +0.008 |
Neg logit contributions | |
Ana | -0.009 |
Pen | -0.008 |
Megan | -0.008 |
Mir | -0.008 |
El | -0.008 |
Token | back |
Token ID | 736 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ercise | +0.020 |
ams | +0.020 |
ets | +0.019 |
ock | +0.019 |
isdom | +0.018 |
Neg logit contributions | |
Ana | -0.019 |
Pen | -0.019 |
Mir | -0.018 |
El | -0.017 |
Megan | -0.017 |
Token | began |
Token ID | 2540 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
ets | +0.019 |
ams | +0.019 |
ercise | +0.019 |
ock | +0.017 |
ear | +0.016 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.019 |
stack | -0.018 |
Jenkins | -0.018 |
Megan | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ercise | +0.012 |
ets | +0.012 |
ams | +0.012 |
ock | +0.010 |
isdom | +0.009 |
Neg logit contributions | |
Ana | -0.029 |
Pen | -0.028 |
Megan | -0.027 |
Mir | -0.026 |
gen | -0.026 |
Token | sew |
Token ID | 34249 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Ana | +0.062 |
Pen | +0.060 |
Mir | +0.056 |
Megan | +0.055 |
El | +0.055 |
Neg logit contributions | |
ercise | -0.072 |
ets | -0.072 |
ams | -0.071 |
ock | -0.068 |
isdom | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ets | +0.038 |
ams | +0.036 |
ercise | +0.036 |
ock | +0.035 |
les | +0.031 |
Neg logit contributions | |
Ana | -0.060 |
Pen | -0.060 |
stack | -0.056 |
Megan | -0.056 |
gen | -0.056 |
Token | She |
Token ID | 1375 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
ercise | +0.035 |
ets | +0.035 |
ams | +0.034 |
ock | +0.032 |
ear | +0.030 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.037 |
gen | -0.036 |
plun | -0.036 |
Mir | -0.035 |
Token | se |
Token ID | 384 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
Ana | +0.013 |
Pen | +0.012 |
Megan | +0.011 |
Mir | +0.011 |
plun | +0.011 |
Neg logit contributions | |
ets | -0.014 |
ercise | -0.014 |
ams | -0.014 |
ock | -0.013 |
vious | -0.012 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
jets | +0.130 |
ercise | +0.123 |
pads | +0.119 |
weet | +0.116 |
motorcycles | +0.113 |
Neg logit contributions | |
Megan | -0.190 |
Ana | -0.188 |
illi | -0.178 |
Pen | -0.171 |
Ell | -0.169 |
Token | the |
Token ID | 262 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ercise | +0.066 |
ets | +0.064 |
ams | +0.064 |
ock | +0.059 |
isdom | +0.056 |
Neg logit contributions | |
Ana | -0.087 |
Pen | -0.083 |
Mir | -0.080 |
El | -0.079 |
Megan | -0.078 |
Token | piece |
Token ID | 3704 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ercise | +0.022 |
ets | +0.022 |
ams | +0.022 |
ock | +0.021 |
vious | +0.019 |
Neg logit contributions | |
Ana | -0.023 |
Pen | -0.022 |
Megan | -0.021 |
Mir | -0.021 |
El | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
ercise | +0.006 |
ams | +0.006 |
ets | +0.006 |
ock | +0.005 |
isdom | +0.005 |
Neg logit contributions | |
Ana | -0.009 |
Pen | -0.009 |
Mir | -0.009 |
Megan | -0.009 |
El | -0.009 |
Token | cloth |
Token ID | 16270 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
Mir | +0.019 |
El | +0.019 |
Megan | +0.019 |
Neg logit contributions | |
ets | -0.023 |
ercise | -0.023 |
ams | -0.023 |
ock | -0.022 |
vious | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ercise | +0.031 |
ets | +0.030 |
ams | +0.030 |
ock | +0.029 |
isdom | +0.027 |
Neg logit contributions | |
Ana | -0.029 |
Pen | -0.027 |
Mir | -0.026 |
Megan | -0.026 |
El | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ercise | +0.036 |
ets | +0.036 |
ams | +0.036 |
ock | +0.034 |
isdom | +0.032 |
Neg logit contributions | |
Ana | -0.033 |
Pen | -0.031 |
Mir | -0.029 |
Megan | -0.029 |
El | -0.029 |
Token | She |
Token ID | 3347 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
ams | +0.028 |
ets | +0.028 |
ercise | +0.028 |
ock | +0.026 |
isdom | +0.024 |
Neg logit contributions | |
Ana | -0.032 |
Pen | -0.031 |
Megan | -0.028 |
Mir | -0.028 |
El | -0.028 |
Token | cut |
Token ID | 2005 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
Megan | +0.019 |
Mir | +0.019 |
plun | +0.019 |
Neg logit contributions | |
ercise | -0.017 |
ets | -0.017 |
ams | -0.017 |
ock | -0.015 |
isdom | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
ets | +0.030 |
ams | +0.030 |
ercise | +0.030 |
ock | +0.028 |
vious | +0.025 |
Neg logit contributions | |
Ana | -0.040 |
Pen | -0.039 |
Megan | -0.037 |
gen | -0.036 |
Mir | -0.036 |
Token | se |
Token ID | 384 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
ercise | +0.103 |
ets | +0.102 |
ams | +0.102 |
ock | +0.096 |
isdom | +0.089 |
Neg logit contributions | |
Ana | -0.097 |
Pen | -0.093 |
Megan | -0.087 |
Mir | -0.086 |
El | -0.085 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
jets | +0.138 |
weet | +0.128 |
since | +0.121 |
pads | +0.120 |
sunset | +0.116 |
Neg logit contributions | |
Megan | -0.172 |
Ana | -0.169 |
illi | -0.161 |
plun | -0.159 |
Ann | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
ets | +0.049 |
ams | +0.048 |
ercise | +0.047 |
ock | +0.045 |
ear | +0.039 |
Neg logit contributions | |
Ana | -0.080 |
Pen | -0.078 |
Megan | -0.074 |
Mir | -0.073 |
gen | -0.072 |
Token | fabric |
Token ID | 9664 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ets | +0.012 |
ercise | +0.012 |
ams | +0.011 |
ock | +0.011 |
isdom | +0.010 |
Neg logit contributions | |
Ana | -0.013 |
Pen | -0.013 |
Mir | -0.012 |
Megan | -0.012 |
El | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
Ana | +0.005 |
Pen | +0.005 |
Mir | +0.004 |
Megan | +0.004 |
El | +0.004 |
Neg logit contributions | |
ets | -0.003 |
ercise | -0.003 |
ams | -0.003 |
ock | -0.003 |
isdom | -0.003 |
Token | put |
Token ID | 1234 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ets | +0.087 |
ams | +0.087 |
ercise | +0.086 |
ock | +0.079 |
isdom | +0.072 |
Neg logit contributions | |
Ana | -0.101 |
Pen | -0.099 |
Megan | -0.093 |
plun | -0.090 |
Mir | -0.090 |
Token | big |
Token ID | 1263 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ercise | +0.009 |
ets | +0.009 |
ams | +0.009 |
ock | +0.009 |
weet | +0.008 |
Neg logit contributions | |
Ana | -0.012 |
Pen | -0.011 |
Mir | -0.011 |
Megan | -0.011 |
El | -0.011 |
Token | hill |
Token ID | 12788 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ercise | +0.032 |
ets | +0.031 |
ams | +0.031 |
ock | +0.030 |
isdom | +0.028 |
Neg logit contributions | |
Ana | -0.029 |
Pen | -0.027 |
Mir | -0.026 |
Megan | -0.025 |
El | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
Ana | +0.048 |
Pen | +0.046 |
Mir | +0.044 |
Megan | +0.044 |
El | +0.043 |
Neg logit contributions | |
ercise | -0.039 |
ets | -0.038 |
ams | -0.038 |
ock | -0.036 |
isdom | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ercise | +0.020 |
ams | +0.020 |
ets | +0.020 |
ock | +0.019 |
isdom | +0.017 |
Neg logit contributions | |
Ana | -0.023 |
Pen | -0.022 |
Mir | -0.021 |
plun | -0.021 |
Megan | -0.021 |
Token | would |
Token ID | 561 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Ana | +0.011 |
Pen | +0.011 |
Mir | +0.010 |
Megan | +0.010 |
plun | +0.010 |
Neg logit contributions | |
ercise | -0.012 |
ets | -0.012 |
ams | -0.012 |
ock | -0.011 |
vious | -0.011 |
Token | even |
Token ID | 772 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
Ana | +0.007 |
Pen | +0.006 |
Mir | +0.006 |
Megan | +0.006 |
El | +0.006 |
Neg logit contributions | |
ercise | -0.008 |
ets | -0.008 |
ams | -0.008 |
ock | -0.007 |
isdom | -0.007 |
Token | pretend |
Token ID | 16614 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ams | +0.228 |
ets | +0.224 |
ercise | +0.223 |
ock | +0.210 |
isdom | +0.208 |
Neg logit contributions | |
Ana | -0.163 |
Pen | -0.155 |
Mir | -0.145 |
Megan | -0.141 |
El | -0.141 |
Token | to |
Token ID | 284 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ercise | +0.049 |
ets | +0.049 |
ams | +0.048 |
ock | +0.045 |
isdom | +0.041 |
Neg logit contributions | |
Ana | -0.071 |
Pen | -0.068 |
Mir | -0.065 |
Megan | -0.065 |
El | -0.064 |
Token | fly |
Token ID | 6129 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
Ana | +0.056 |
Pen | +0.053 |
Jenkins | +0.050 |
plun | +0.049 |
Megan | +0.049 |
Neg logit contributions | |
ercise | -0.062 |
ets | -0.061 |
ock | -0.059 |
ams | -0.059 |
isdom | -0.054 |
Token | with |
Token ID | 351 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ets | +0.079 |
ercise | +0.079 |
ams | +0.077 |
ock | +0.073 |
isdom | +0.065 |
Neg logit contributions | |
Ana | -0.112 |
Pen | -0.108 |
Mir | -0.103 |
Megan | -0.102 |
El | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ercise | +0.029 |
ets | +0.029 |
ams | +0.028 |
ock | +0.027 |
isdom | +0.024 |
Neg logit contributions | |
Ana | -0.037 |
Pen | -0.036 |
Mir | -0.034 |
Megan | -0.034 |
El | -0.033 |
Token | paint |
Token ID | 7521 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ets | +0.010 |
ercise | +0.010 |
ams | +0.010 |
ock | +0.009 |
vious | +0.008 |
Neg logit contributions | |
Ana | -0.010 |
Pen | -0.009 |
Mir | -0.009 |
Megan | -0.009 |
El | -0.009 |
Token | pot |
Token ID | 1787 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
ercise | +0.012 |
ams | +0.011 |
ets | +0.011 |
ock | +0.010 |
isdom | +0.010 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.014 |
Mir | -0.014 |
Megan | -0.013 |
El | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Ana | +0.029 |
Pen | +0.028 |
Mir | +0.027 |
El | +0.027 |
Megan | +0.026 |
Neg logit contributions | |
ercise | -0.023 |
ams | -0.021 |
ets | -0.021 |
ock | -0.020 |
isdom | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ercise | +0.039 |
ets | +0.038 |
ams | +0.038 |
ock | +0.036 |
isdom | +0.034 |
Neg logit contributions | |
Ana | -0.038 |
Pen | -0.037 |
Mir | -0.034 |
Megan | -0.034 |
El | -0.034 |
Token | would |
Token ID | 561 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
Ana | +0.019 |
Pen | +0.018 |
Mir | +0.017 |
Megan | +0.017 |
El | +0.017 |
Neg logit contributions | |
ercise | -0.017 |
ets | -0.017 |
ams | -0.017 |
ock | -0.016 |
isdom | -0.015 |
Token | even |
Token ID | 772 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
Ana | +0.015 |
Pen | +0.014 |
Mir | +0.013 |
El | +0.013 |
Megan | +0.013 |
Neg logit contributions | |
ercise | -0.021 |
ams | -0.021 |
ets | -0.021 |
ock | -0.020 |
isdom | -0.018 |
Token | mix |
Token ID | 5022 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ercise | +0.233 |
ams | +0.230 |
ets | +0.230 |
ock | +0.220 |
isdom | +0.211 |
Neg logit contributions | |
Ana | -0.155 |
Pen | -0.144 |
Mir | -0.137 |
Megan | -0.132 |
El | -0.131 |
Token | hot |
Token ID | 3024 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ercise | +0.081 |
ets | +0.079 |
ams | +0.078 |
ock | +0.074 |
isdom | +0.071 |
Neg logit contributions | |
Ana | -0.094 |
Pen | -0.089 |
Mir | -0.086 |
Megan | -0.085 |
El | -0.084 |
Token | chocolate |
Token ID | 11311 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
ercise | +0.014 |
ets | +0.013 |
ams | +0.013 |
ock | +0.013 |
isdom | +0.013 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.014 |
Mir | -0.014 |
El | -0.014 |
Megan | -0.013 |
Token | when |
Token ID | 618 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ets | +0.017 |
ams | +0.017 |
ercise | +0.017 |
ock | +0.016 |
ear | +0.014 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.025 |
Megan | -0.024 |
plun | -0.024 |
Mir | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Ana | +0.030 |
plun | +0.029 |
Pen | +0.028 |
gen | +0.028 |
Mir | +0.027 |
Neg logit contributions | |
ercise | -0.020 |
ams | -0.020 |
ock | -0.019 |
ets | -0.019 |
weet | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Ana | +0.022 |
Pen | +0.021 |
Megan | +0.020 |
Mir | +0.020 |
El | +0.020 |
Neg logit contributions | |
ercise | -0.018 |
ams | -0.018 |
ets | -0.018 |
ock | -0.017 |
vious | -0.016 |
Token | needle |
Token ID | 17598 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Ana | +0.009 |
Pen | +0.008 |
Megan | +0.008 |
El | +0.008 |
Mir | +0.008 |
Neg logit contributions | |
ercise | -0.007 |
ets | -0.007 |
ock | -0.006 |
ams | -0.006 |
isdom | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ercise | +0.000 |
ets | +0.000 |
ams | +0.000 |
ock | +0.000 |
isdom | +0.000 |
Neg logit contributions | |
Ana | -0.001 |
Pen | -0.001 |
Mir | -0.001 |
Megan | -0.001 |
El | -0.001 |
Token | thread |
Token ID | 4704 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ams | +0.100 |
ets | +0.100 |
ercise | +0.098 |
ock | +0.094 |
isdom | +0.087 |
Neg logit contributions | |
Ana | -0.080 |
Pen | -0.076 |
Mir | -0.074 |
plun | -0.071 |
gen | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ets | +0.035 |
ercise | +0.034 |
ams | +0.034 |
ock | +0.032 |
vious | +0.028 |
Neg logit contributions | |
Ana | -0.074 |
Pen | -0.071 |
Megan | -0.068 |
Mir | -0.067 |
El | -0.066 |
Token | se |
Token ID | 384 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
ets | +0.089 |
ams | +0.088 |
ercise | +0.088 |
ock | +0.084 |
isdom | +0.078 |
Neg logit contributions | |
Ana | -0.079 |
Pen | -0.076 |
Mir | -0.072 |
Megan | -0.070 |
El | -0.070 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
weet | +0.127 |
jets | +0.124 |
since | +0.116 |
sunset | +0.112 |
ock | +0.112 |
Neg logit contributions | |
plun | -0.168 |
Ana | -0.160 |
Megan | -0.160 |
Ann | -0.157 |
ocated | -0.156 |
Token | a |
Token ID | 257 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
ets | +0.051 |
ercise | +0.050 |
ams | +0.050 |
ock | +0.048 |
ear | +0.042 |
Neg logit contributions | |
Ana | -0.073 |
Pen | -0.071 |
Megan | -0.067 |
Mir | -0.066 |
gen | -0.066 |
Token | patch |
Token ID | 8529 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ets | +0.002 |
ercise | +0.002 |
ock | +0.002 |
ams | +0.002 |
ear | +0.002 |
Neg logit contributions | |
Ana | -0.002 |
Pen | -0.002 |
Megan | -0.002 |
El | -0.002 |
Mir | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.012 |
Mir | +0.011 |
Megan | +0.011 |
El | +0.011 |
Neg logit contributions | |
ercise | -0.006 |
ams | -0.006 |
ets | -0.006 |
ock | -0.005 |
isdom | -0.005 |
Token | Patch |
Token ID | 17106 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Ana | +0.050 |
Pen | +0.048 |
Megan | +0.046 |
gen | +0.045 |
Mir | +0.045 |
Neg logit contributions | |
ets | -0.038 |
ercise | -0.038 |
ams | -0.036 |
ock | -0.036 |
isdom | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
Ana | +0.062 |
Pen | +0.058 |
Mir | +0.055 |
El | +0.054 |
Megan | +0.054 |
Neg logit contributions | |
ercise | -0.071 |
ets | -0.070 |
ams | -0.069 |
ock | -0.064 |
isdom | -0.061 |
Token | needle |
Token ID | 17598 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
ercise | +0.020 |
ets | +0.019 |
ock | +0.018 |
ams | +0.017 |
isdom | +0.016 |
Neg logit contributions | |
Ana | -0.023 |
Pen | -0.022 |
Megan | -0.021 |
Mir | -0.021 |
Mil | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
ercise | +0.007 |
ams | +0.007 |
ets | +0.007 |
ock | +0.006 |
isdom | +0.006 |
Neg logit contributions | |
Ana | -0.013 |
Pen | -0.013 |
Mir | -0.012 |
El | -0.012 |
Megan | -0.012 |
Token | thread |
Token ID | 4704 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ercise | +0.107 |
ets | +0.104 |
ams | +0.103 |
ock | +0.098 |
isdom | +0.091 |
Neg logit contributions | |
Ana | -0.111 |
Pen | -0.107 |
Megan | -0.101 |
Mir | -0.099 |
El | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
ets | +0.039 |
ams | +0.038 |
ercise | +0.037 |
ock | +0.036 |
vious | +0.031 |
Neg logit contributions | |
Ana | -0.070 |
Pen | -0.067 |
Megan | -0.064 |
Mir | -0.064 |
El | -0.062 |
Token | se |
Token ID | 384 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
ercise | +0.090 |
ets | +0.087 |
ams | +0.087 |
ock | +0.083 |
isdom | +0.075 |
Neg logit contributions | |
Ana | -0.105 |
Pen | -0.102 |
Megan | -0.097 |
Jenkins | -0.094 |
Mir | -0.094 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
weet | +0.127 |
jets | +0.127 |
since | +0.112 |
ock | +0.112 |
ully | +0.112 |
Neg logit contributions | |
plun | -0.173 |
Ana | -0.172 |
Megan | -0.172 |
Mir | -0.166 |
Ann | -0.165 |
Token | the |
Token ID | 262 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
ets | +0.050 |
ercise | +0.049 |
ams | +0.049 |
ock | +0.047 |
ear | +0.041 |
Neg logit contributions | |
Ana | -0.070 |
Pen | -0.068 |
Megan | -0.064 |
Mir | -0.063 |
gen | -0.063 |
Token | t |
Token ID | 256 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
ercise | +0.002 |
ets | +0.002 |
ock | +0.002 |
ams | +0.002 |
les | +0.002 |
Neg logit contributions | |
Ana | -0.002 |
Megan | -0.001 |
Pen | -0.001 |
Mil | -0.001 |
Mir | -0.001 |
Token | eddy |
Token ID | 21874 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ercise | +0.014 |
ets | +0.014 |
ams | +0.013 |
ock | +0.012 |
isdom | +0.011 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.019 |
Mir | -0.018 |
Megan | -0.018 |
El | -0.018 |
Token | bear |
Token ID | 6842 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
Ana | +0.003 |
Pen | +0.003 |
Megan | +0.003 |
Mir | +0.003 |
Mil | +0.002 |
Neg logit contributions | |
ercise | -0.004 |
ets | -0.004 |
ams | -0.004 |
ock | -0.004 |
les | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ercise | +0.058 |
ams | +0.055 |
ets | +0.055 |
ock | +0.051 |
isdom | +0.051 |
Neg logit contributions | |
Ana | -0.077 |
Pen | -0.074 |
El | -0.071 |
Mir | -0.070 |
Megan | -0.070 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Ana | +0.061 |
Pen | +0.058 |
Megan | +0.055 |
Mir | +0.054 |
Jenkins | +0.054 |
Neg logit contributions | |
ercise | -0.057 |
ets | -0.057 |
ock | -0.054 |
ams | -0.054 |
isdom | -0.049 |
Token | up |
Token ID | 510 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ercise | +0.045 |
ets | +0.044 |
ams | +0.044 |
ock | +0.041 |
isdom | +0.038 |
Neg logit contributions | |
Ana | -0.054 |
Pen | -0.052 |
Mir | -0.049 |
Megan | -0.049 |
El | -0.049 |
Token | toys |
Token ID | 14958 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Ana | +0.005 |
Pen | +0.004 |
Mir | +0.004 |
Megan | +0.004 |
El | +0.004 |
Neg logit contributions | |
ercise | -0.004 |
ets | -0.004 |
ams | -0.004 |
ock | -0.004 |
isdom | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
ets | +0.037 |
ercise | +0.037 |
ams | +0.036 |
ock | +0.034 |
isdom | +0.029 |
Neg logit contributions | |
Ana | -0.069 |
Pen | -0.067 |
Mir | -0.064 |
Megan | -0.063 |
El | -0.063 |
Token | even |
Token ID | 772 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
ercise | +0.123 |
ets | +0.122 |
ams | +0.120 |
ock | +0.113 |
isdom | +0.106 |
Neg logit contributions | |
Ana | -0.119 |
Pen | -0.114 |
Mir | -0.107 |
Megan | -0.107 |
El | -0.105 |
Token | l |
Token ID | 300 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
ams | +0.202 |
ercise | +0.202 |
ets | +0.201 |
ock | +0.191 |
isdom | +0.182 |
Neg logit contributions | |
Ana | -0.181 |
Pen | -0.171 |
Mir | -0.162 |
Megan | -0.158 |
El | -0.158 |
Token | icked |
Token ID | 9484 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ets | +0.023 |
ercise | +0.022 |
ams | +0.022 |
ock | +0.021 |
vious | +0.019 |
Neg logit contributions | |
Ana | -0.027 |
Pen | -0.026 |
Mir | -0.025 |
Megan | -0.024 |
El | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ercise | +0.043 |
ets | +0.043 |
ams | +0.043 |
ock | +0.040 |
isdom | +0.037 |
Neg logit contributions | |
Ana | -0.050 |
Pen | -0.048 |
Mir | -0.045 |
Megan | -0.045 |
El | -0.045 |
Token | dust |
Token ID | 8977 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Ana | +0.006 |
Pen | +0.006 |
Mir | +0.006 |
Megan | +0.006 |
Mil | +0.005 |
Neg logit contributions | |
ets | -0.006 |
ercise | -0.006 |
ock | -0.006 |
ams | -0.006 |
elling | -0.005 |
Token | off |
Token ID | 572 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Ana | +0.095 |
Pen | +0.092 |
Mir | +0.087 |
Megan | +0.087 |
El | +0.086 |
Neg logit contributions | |
ets | -0.067 |
ams | -0.064 |
ercise | -0.064 |
ock | -0.062 |
vious | -0.054 |
Token | of |
Token ID | 286 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ercise | +0.135 |
isdom | +0.119 |
ully | +0.112 |
ams | +0.103 |
iper | +0.099 |
Neg logit contributions | |
Ana | -0.102 |
Megan | -0.098 |
El | -0.096 |
Ell | -0.095 |
Pen | -0.094 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Ana | +0.011 |
Pen | +0.011 |
Mir | +0.010 |
El | +0.010 |
Megan | +0.010 |
Neg logit contributions | |
ercise | -0.009 |
ets | -0.009 |
ams | -0.009 |
ock | -0.009 |
isdom | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ercise | +0.058 |
ets | +0.055 |
ams | +0.054 |
ock | +0.053 |
isdom | +0.053 |
Neg logit contributions | |
Ana | -0.045 |
Pen | -0.042 |
El | -0.041 |
Mir | -0.040 |
Megan | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ercise | +0.056 |
ets | +0.056 |
ams | +0.056 |
ock | +0.053 |
isdom | +0.049 |
Neg logit contributions | |
Ana | -0.052 |
Pen | -0.050 |
Mir | -0.047 |
Megan | -0.047 |
El | -0.046 |
Token | would |
Token ID | 561 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Ana | +0.013 |
Pen | +0.013 |
Mir | +0.012 |
Megan | +0.012 |
El | +0.012 |
Neg logit contributions | |
ercise | -0.015 |
ets | -0.015 |
ams | -0.015 |
ock | -0.014 |
isdom | -0.013 |
Token | even |
Token ID | 772 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
Ana | +0.007 |
Pen | +0.007 |
Mir | +0.006 |
Megan | +0.006 |
El | +0.006 |
Neg logit contributions | |
ercise | -0.009 |
ets | -0.009 |
ams | -0.009 |
ock | -0.009 |
isdom | -0.008 |
Token | try |
Token ID | 1949 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ams | +0.224 |
ercise | +0.222 |
ets | +0.218 |
isdom | +0.214 |
elling | +0.213 |
Neg logit contributions | |
Ana | -0.155 |
Pen | -0.143 |
Mir | -0.138 |
El | -0.133 |
Megan | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ams | +0.081 |
ercise | +0.081 |
ets | +0.080 |
vious | +0.073 |
ock | +0.073 |
Neg logit contributions | |
Ana | -0.093 |
Pen | -0.089 |
Mir | -0.087 |
El | -0.086 |
Mil | -0.082 |
Token | make |
Token ID | 787 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Ana | +0.058 |
Pen | +0.055 |
Mir | +0.052 |
Megan | +0.052 |
gen | +0.050 |
Neg logit contributions | |
ercise | -0.066 |
ets | -0.066 |
ams | -0.065 |
ock | -0.064 |
vious | -0.057 |
Token | up |
Token ID | 510 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
ercise | +0.068 |
ets | +0.067 |
ams | +0.067 |
ock | +0.063 |
isdom | +0.058 |
Neg logit contributions | |
Ana | -0.083 |
Pen | -0.080 |
Mir | -0.076 |
Megan | -0.075 |
El | -0.074 |
Token | silly |
Token ID | 14397 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ercise | +0.002 |
ets | +0.002 |
ams | +0.002 |
ock | +0.002 |
isdom | +0.002 |
Neg logit contributions | |
Ana | -0.003 |
Pen | -0.003 |
Mir | -0.003 |
Megan | -0.003 |
El | -0.003 |
Token | needle |
Token ID | 17598 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ercise | +0.010 |
ets | +0.009 |
ams | +0.009 |
ock | +0.008 |
isdom | +0.008 |
Neg logit contributions | |
Ana | -0.013 |
Pen | -0.012 |
Megan | -0.012 |
Mir | -0.011 |
El | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ercise | +0.031 |
ams | +0.030 |
ets | +0.030 |
ock | +0.028 |
isdom | +0.026 |
Neg logit contributions | |
Ana | -0.042 |
Pen | -0.041 |
Mir | -0.039 |
El | -0.038 |
Megan | -0.038 |
Token | thread |
Token ID | 4704 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ercise | +0.087 |
ets | +0.086 |
ams | +0.086 |
ock | +0.081 |
isdom | +0.075 |
Neg logit contributions | |
Ana | -0.087 |
Pen | -0.083 |
Mir | -0.079 |
Megan | -0.078 |
El | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ercise | +0.061 |
ets | +0.060 |
ams | +0.060 |
ock | +0.057 |
isdom | +0.052 |
Neg logit contributions | |
Ana | -0.076 |
Pen | -0.073 |
Mir | -0.069 |
Megan | -0.069 |
El | -0.069 |
Token | She |
Token ID | 1375 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ercise | +0.005 |
ets | +0.005 |
ams | +0.005 |
ock | +0.004 |
vious | +0.004 |
Neg logit contributions | |
Ana | -0.007 |
Pen | -0.007 |
gen | -0.007 |
plun | -0.007 |
Megan | -0.007 |
Token | se |
Token ID | 384 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
Ana | +0.028 |
Pen | +0.027 |
Megan | +0.025 |
Mir | +0.025 |
El | +0.025 |
Neg logit contributions | |
ercise | -0.025 |
ets | -0.025 |
ams | -0.025 |
ock | -0.023 |
isdom | -0.022 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ercise | +0.117 |
since | +0.115 |
weet | +0.111 |
pads | +0.110 |
jets | +0.108 |
Neg logit contributions | |
Megan | -0.172 |
Ana | -0.166 |
illi | -0.160 |
Ann | -0.157 |
Mir | -0.155 |
Token | a |
Token ID | 257 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ercise | +0.064 |
ets | +0.063 |
ams | +0.061 |
ock | +0.057 |
isdom | +0.056 |
Neg logit contributions | |
Ana | -0.070 |
Pen | -0.067 |
Mir | -0.065 |
El | -0.064 |
Ell | -0.063 |
Token | hole |
Token ID | 7604 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ercise | +0.009 |
ets | +0.009 |
ams | +0.009 |
ock | +0.009 |
isdom | +0.008 |
Neg logit contributions | |
Ana | -0.009 |
Pen | -0.008 |
Mir | -0.008 |
Megan | -0.008 |
El | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Ana | +0.068 |
Pen | +0.064 |
Megan | +0.061 |
Mir | +0.061 |
El | +0.061 |
Neg logit contributions | |
ercise | -0.074 |
ams | -0.070 |
ets | -0.069 |
ock | -0.067 |
isdom | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
Ana | +0.079 |
Pen | +0.075 |
Megan | +0.071 |
Mir | +0.070 |
gen | +0.070 |
Neg logit contributions | |
ams | -0.048 |
ock | -0.047 |
ets | -0.046 |
ercise | -0.046 |
ear | -0.040 |
Token | blue |
Token ID | 4171 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ercise | +0.006 |
ets | +0.006 |
isdom | +0.006 |
ams | +0.005 |
ear | +0.005 |
Neg logit contributions | |
Ana | -0.005 |
Ell | -0.005 |
Pen | -0.004 |
El | -0.004 |
Megan | -0.004 |
Token | berries |
Token ID | 20853 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
ercise | +0.112 |
ets | +0.108 |
isdom | +0.105 |
ear | +0.101 |
aling | +0.100 |
Neg logit contributions | |
Ana | -0.061 |
Ell | -0.059 |
El | -0.056 |
Fl | -0.056 |
Pen | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ercise | +0.085 |
ets | +0.081 |
ams | +0.080 |
ock | +0.076 |
isdom | +0.076 |
Neg logit contributions | |
Ana | -0.081 |
Pen | -0.078 |
El | -0.074 |
Megan | -0.073 |
Mir | -0.073 |
Token | She |
Token ID | 1375 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ercise | +0.046 |
ets | +0.045 |
ams | +0.044 |
ock | +0.043 |
isdom | +0.039 |
Neg logit contributions | |
Ana | -0.056 |
Pen | -0.053 |
plun | -0.051 |
gen | -0.051 |
Mir | -0.051 |
Token | would |
Token ID | 561 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Ana | +0.013 |
Pen | +0.012 |
plun | +0.012 |
Mir | +0.012 |
Megan | +0.012 |
Neg logit contributions | |
ercise | -0.009 |
ets | -0.009 |
ams | -0.009 |
ock | -0.008 |
isdom | -0.008 |
Token | even |
Token ID | 772 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
Ana | +0.009 |
Pen | +0.009 |
El | +0.008 |
Mir | +0.008 |
Megan | +0.008 |
Neg logit contributions | |
ams | -0.011 |
ercise | -0.011 |
ets | -0.011 |
ock | -0.011 |
vious | -0.010 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ercise | +0.217 |
ets | +0.215 |
ams | +0.214 |
ock | +0.210 |
isdom | +0.203 |
Neg logit contributions | |
Ana | -0.162 |
Pen | -0.151 |
Mir | -0.146 |
Megan | -0.141 |
El | -0.136 |
Token | them |
Token ID | 606 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ercise | +0.027 |
ets | +0.027 |
ams | +0.026 |
ock | +0.024 |
isdom | +0.023 |
Neg logit contributions | |
Ana | -0.033 |
Pen | -0.032 |
Mir | -0.030 |
Megan | -0.030 |
El | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ercise | +0.030 |
ets | +0.029 |
ams | +0.028 |
ock | +0.027 |
isdom | +0.025 |
Neg logit contributions | |
Ana | -0.054 |
Pen | -0.052 |
El | -0.050 |
Megan | -0.050 |
Mir | -0.049 |
Token | breakfast |
Token ID | 12607 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
Mir | +0.019 |
Megan | +0.019 |
El | +0.018 |
Neg logit contributions | |
ercise | -0.018 |
ets | -0.018 |
ams | -0.018 |
ock | -0.017 |
vious | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ets | +0.008 |
ams | +0.008 |
ercise | +0.008 |
ock | +0.008 |
isdom | +0.007 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.014 |
Mir | -0.014 |
Megan | -0.014 |
El | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ercise | +0.063 |
ams | +0.063 |
ets | +0.062 |
ock | +0.059 |
isdom | +0.057 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.037 |
Mir | -0.034 |
Megan | -0.034 |
El | -0.033 |
Token | t |
Token ID | 256 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ercise | +0.009 |
ock | +0.009 |
ets | +0.009 |
ams | +0.009 |
vious | +0.008 |
Neg logit contributions | |
Ana | -0.005 |
Pen | -0.005 |
Megan | -0.005 |
Mir | -0.005 |
Mil | -0.005 |
Token | eddy |
Token ID | 21874 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ercise | +0.005 |
ets | +0.005 |
ams | +0.005 |
isdom | +0.004 |
vious | +0.004 |
Neg logit contributions | |
Ana | -0.006 |
Pen | -0.006 |
gen | -0.005 |
Mir | -0.005 |
Sn | -0.005 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Ana | +0.004 |
Pen | +0.004 |
Mir | +0.004 |
El | +0.004 |
Megan | +0.004 |
Neg logit contributions | |
ets | -0.010 |
ercise | -0.010 |
ams | -0.010 |
ock | -0.010 |
isdom | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
Ana | +0.004 |
Pen | +0.004 |
Mir | +0.003 |
El | +0.003 |
plun | +0.003 |
Neg logit contributions | |
ercise | -0.003 |
ams | -0.003 |
ets | -0.003 |
ock | -0.003 |
isdom | -0.002 |
Token | se |
Token ID | 384 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
ercise | +0.094 |
ams | +0.089 |
ets | +0.089 |
ock | +0.085 |
isdom | +0.078 |
Neg logit contributions | |
Ana | -0.105 |
Pen | -0.102 |
Megan | -0.097 |
Mir | -0.094 |
Jenkins | -0.094 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
jets | +0.127 |
weet | +0.126 |
ets | +0.112 |
ully | +0.112 |
ercise | +0.112 |
Neg logit contributions | |
Megan | -0.182 |
Ana | -0.180 |
plun | -0.172 |
Ann | -0.171 |
Fl | -0.167 |
Token | up |
Token ID | 510 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ercise | +0.049 |
ets | +0.049 |
ams | +0.048 |
ock | +0.046 |
ear | +0.041 |
Neg logit contributions | |
Ana | -0.064 |
Pen | -0.062 |
Mir | -0.059 |
Megan | -0.058 |
El | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
ercise | +0.009 |
ets | +0.009 |
ams | +0.009 |
ock | +0.009 |
isdom | +0.008 |
Neg logit contributions | |
Ana | -0.011 |
Pen | -0.011 |
Mir | -0.010 |
Megan | -0.010 |
El | -0.010 |
Token | hole |
Token ID | 7604 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
ercise | +0.026 |
ets | +0.026 |
ams | +0.025 |
ock | +0.025 |
vious | +0.023 |
Neg logit contributions | |
Ana | -0.018 |
Pen | -0.017 |
Megan | -0.016 |
Mir | -0.016 |
El | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Ana | +0.121 |
Pen | +0.117 |
Mir | +0.111 |
Megan | +0.110 |
El | +0.109 |
Neg logit contributions | |
ets | -0.088 |
ams | -0.086 |
ercise | -0.086 |
ock | -0.081 |
vious | -0.073 |
Token | healthy |
Token ID | 5448 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.043 |
Megan | +0.040 |
Mir | +0.040 |
El | +0.040 |
Neg logit contributions | |
ercise | -0.035 |
ets | -0.035 |
ams | -0.034 |
ock | -0.032 |
isdom | -0.030 |
Token | things |
Token ID | 1243 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ercise | +0.013 |
ets | +0.013 |
ams | +0.013 |
ock | +0.012 |
isdom | +0.011 |
Neg logit contributions | |
Ana | -0.016 |
Pen | -0.016 |
Megan | -0.015 |
Mir | -0.015 |
El | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Ana | +0.001 |
Pen | +0.001 |
El | +0.001 |
Megan | +0.001 |
Ell | +0.001 |
Neg logit contributions | |
ercise | -0.001 |
ams | -0.001 |
ets | -0.001 |
ock | -0.001 |
isdom | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
ercise | +0.046 |
ets | +0.046 |
ock | +0.045 |
ams | +0.045 |
elling | +0.041 |
Neg logit contributions | |
Ana | -0.029 |
Pen | -0.028 |
Megan | -0.028 |
Mir | -0.027 |
El | -0.025 |
Token | would |
Token ID | 561 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
Ana | +0.029 |
Pen | +0.028 |
Mir | +0.027 |
Megan | +0.027 |
plun | +0.026 |
Neg logit contributions | |
ets | -0.023 |
ercise | -0.023 |
ams | -0.023 |
ock | -0.021 |
isdom | -0.019 |
Token | even |
Token ID | 772 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
Ana | +0.013 |
Pen | +0.012 |
Mir | +0.011 |
Megan | +0.011 |
El | +0.011 |
Neg logit contributions | |
ercise | -0.012 |
ets | -0.012 |
ams | -0.012 |
ock | -0.011 |
isdom | -0.010 |
Token | share |
Token ID | 2648 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ercise | +0.211 |
ams | +0.209 |
ets | +0.209 |
ock | +0.203 |
isdom | +0.191 |
Neg logit contributions | |
Ana | -0.167 |
Pen | -0.157 |
Mir | -0.150 |
Megan | -0.146 |
El | -0.143 |
Token | these |
Token ID | 777 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ercise | +0.069 |
ets | +0.068 |
ams | +0.064 |
ock | +0.063 |
vious | +0.063 |
Neg logit contributions | |
Ana | -0.071 |
Pen | -0.066 |
Megan | -0.064 |
Mir | -0.063 |
Ell | -0.063 |
Token | snacks |
Token ID | 28487 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ercise | +0.033 |
ets | +0.032 |
ams | +0.032 |
ock | +0.031 |
isdom | +0.029 |
Neg logit contributions | |
Ana | -0.038 |
Pen | -0.036 |
Megan | -0.035 |
El | -0.034 |
Mir | -0.034 |
Token | with |
Token ID | 351 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ercise | +0.008 |
ets | +0.008 |
ams | +0.008 |
ock | +0.008 |
isdom | +0.007 |
Neg logit contributions | |
Ana | -0.007 |
Pen | -0.007 |
Megan | -0.007 |
Mir | -0.007 |
El | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ets | +0.025 |
ercise | +0.025 |
ams | +0.023 |
ock | +0.023 |
vious | +0.022 |
Neg logit contributions | |
Ana | -0.030 |
Pen | -0.028 |
Megan | -0.028 |
Mir | -0.027 |
El | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ercise | +0.012 |
ets | +0.012 |
ams | +0.012 |
ock | +0.011 |
isdom | +0.010 |
Neg logit contributions | |
Ana | -0.018 |
Pen | -0.017 |
Mir | -0.017 |
Megan | -0.016 |
El | -0.016 |
Token | some |
Token ID | 617 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
ams | +0.077 |
ercise | +0.076 |
ets | +0.076 |
ock | +0.073 |
isdom | +0.068 |
Neg logit contributions | |
Ana | -0.078 |
Pen | -0.074 |
Mir | -0.071 |
El | -0.069 |
Megan | -0.069 |
Token | buttons |
Token ID | 12163 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ercise | +0.023 |
ams | +0.023 |
ets | +0.023 |
ock | +0.021 |
isdom | +0.020 |
Neg logit contributions | |
Ana | -0.024 |
Pen | -0.023 |
Mir | -0.022 |
Megan | -0.021 |
El | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
ercise | +0.059 |
ams | +0.056 |
ets | +0.054 |
isdom | +0.052 |
ock | +0.052 |
Neg logit contributions | |
Ana | -0.067 |
Pen | -0.064 |
Mir | -0.063 |
El | -0.062 |
Megan | -0.061 |
Token | I |
Token ID | 314 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.011 |
Mir | +0.011 |
Megan | +0.010 |
El | +0.010 |
Neg logit contributions | |
ercise | -0.012 |
ets | -0.012 |
ams | -0.012 |
ock | -0.011 |
isdom | -0.010 |
Token | se |
Token ID | 384 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
ets | +0.007 |
ercise | +0.007 |
ams | +0.007 |
ock | +0.006 |
vious | +0.006 |
Neg logit contributions | |
Ana | -0.007 |
Pen | -0.007 |
Megan | -0.006 |
Mir | -0.006 |
Jenkins | -0.006 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
jets | +0.121 |
ully | +0.118 |
since | +0.111 |
ercise | +0.110 |
weet | +0.109 |
Neg logit contributions | |
Ana | -0.190 |
Megan | -0.184 |
Mir | -0.180 |
illi | -0.178 |
Mil | -0.173 |
Token | them |
Token ID | 606 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ercise | +0.070 |
ets | +0.069 |
ams | +0.069 |
ock | +0.064 |
isdom | +0.063 |
Neg logit contributions | |
Ana | -0.076 |
Pen | -0.072 |
Mir | -0.070 |
El | -0.068 |
Megan | -0.067 |
Token | together |
Token ID | 1978 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ercise | +0.011 |
ets | +0.011 |
ams | +0.011 |
ock | +0.010 |
isdom | +0.009 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.015 |
Mir | -0.014 |
Megan | -0.014 |
El | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ercise | +0.023 |
ams | +0.023 |
ets | +0.023 |
ock | +0.021 |
isdom | +0.019 |
Neg logit contributions | |
Ana | -0.038 |
Pen | -0.037 |
Mir | -0.035 |
Megan | -0.035 |
El | -0.035 |
Token | stuffed |
Token ID | 22259 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ercise | +0.078 |
ets | +0.078 |
ams | +0.077 |
ock | +0.072 |
isdom | +0.067 |
Neg logit contributions | |
Ana | -0.090 |
Pen | -0.088 |
Mir | -0.082 |
Megan | -0.082 |
plun | -0.081 |
Token | this |
Token ID | 428 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
ercise | +0.036 |
ets | +0.036 |
ams | +0.036 |
ock | +0.034 |
isdom | +0.031 |
Neg logit contributions | |
Ana | -0.045 |
Pen | -0.043 |
Mir | -0.040 |
Megan | -0.040 |
El | -0.040 |
Token | show |
Token ID | 905 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ets | +0.012 |
ercise | +0.012 |
ams | +0.012 |
ock | +0.012 |
isdom | +0.011 |
Neg logit contributions | |
Ana | -0.014 |
Pen | -0.013 |
Mir | -0.013 |
Megan | -0.013 |
El | -0.012 |
Token | ? |
Token ID | 30 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
ercise | +0.080 |
ets | +0.079 |
ams | +0.079 |
ock | +0.074 |
isdom | +0.068 |
Neg logit contributions | |
Ana | -0.106 |
Pen | -0.102 |
Mir | -0.096 |
Megan | -0.096 |
El | -0.095 |
Token | You |
Token ID | 921 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ercise | +0.014 |
ams | +0.013 |
ets | +0.013 |
ock | +0.012 |
ear | +0.012 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.015 |
plun | -0.014 |
gen | -0.014 |
Mir | -0.014 |
Token | can |
Token ID | 460 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
ets | +0.063 |
ercise | +0.062 |
ams | +0.060 |
ock | +0.058 |
vious | +0.054 |
Neg logit contributions | |
Ana | -0.063 |
Pen | -0.060 |
Mir | -0.057 |
Megan | -0.057 |
plun | -0.055 |
Token | even |
Token ID | 772 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
Ana | +0.014 |
Pen | +0.013 |
Mir | +0.013 |
Megan | +0.012 |
El | +0.012 |
Neg logit contributions | |
ercise | -0.017 |
ets | -0.017 |
ams | -0.017 |
ock | -0.016 |
isdom | -0.015 |
Token | perform |
Token ID | 1620 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
ercise | +0.204 |
ams | +0.203 |
ets | +0.203 |
ock | +0.192 |
isdom | +0.179 |
Neg logit contributions | |
Ana | -0.174 |
Pen | -0.166 |
Mir | -0.155 |
Megan | -0.153 |
El | -0.152 |
Token | in |
Token ID | 287 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ercise | +0.055 |
ams | +0.054 |
ets | +0.054 |
ock | +0.051 |
isdom | +0.047 |
Neg logit contributions | |
Ana | -0.069 |
Pen | -0.066 |
Mir | -0.062 |
Megan | -0.062 |
El | -0.062 |
Token | front |
Token ID | 2166 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Ana | +0.049 |
Pen | +0.048 |
Mir | +0.045 |
Megan | +0.045 |
El | +0.044 |
Neg logit contributions | |
ercise | -0.033 |
ets | -0.033 |
ams | -0.033 |
ock | -0.031 |
isdom | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
ercise | +0.029 |
ams | +0.026 |
ets | +0.024 |
ully | +0.024 |
isdom | +0.023 |
Neg logit contributions | |
Ana | -0.048 |
Pen | -0.046 |
Megan | -0.045 |
El | -0.045 |
Mir | -0.044 |
Token | all |
Token ID | 477 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
Ana | +0.025 |
Pen | +0.025 |
Mir | +0.023 |
Megan | +0.023 |
El | +0.023 |
Neg logit contributions | |
ercise | -0.017 |
ets | -0.017 |
ams | -0.017 |
ock | -0.016 |
isdom | -0.014 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Ana | +0.008 |
Pen | +0.008 |
Mir | +0.007 |
El | +0.007 |
Megan | +0.007 |
Neg logit contributions | |
ercise | -0.008 |
ets | -0.008 |
ams | -0.008 |
ock | -0.007 |
isdom | -0.007 |
Token | taking |
Token ID | 2263 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ercise | +0.053 |
ets | +0.053 |
ams | +0.053 |
ock | +0.050 |
isdom | +0.046 |
Neg logit contributions | |
Ana | -0.061 |
Pen | -0.058 |
Mir | -0.055 |
Megan | -0.055 |
El | -0.054 |
Token | baths |
Token ID | 49076 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
ercise | +0.059 |
ams | +0.059 |
ets | +0.058 |
ock | +0.054 |
isdom | +0.051 |
Neg logit contributions | |
Ana | -0.085 |
Pen | -0.082 |
Mir | -0.077 |
Megan | -0.077 |
El | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ets | +0.014 |
ercise | +0.014 |
ams | +0.014 |
ock | +0.013 |
vious | +0.012 |
Neg logit contributions | |
Ana | -0.022 |
Pen | -0.022 |
Mir | -0.021 |
Megan | -0.021 |
gen | -0.020 |
Token | would |
Token ID | 561 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
ercise | +0.094 |
ets | +0.093 |
ams | +0.093 |
ock | +0.088 |
isdom | +0.081 |
Neg logit contributions | |
Ana | -0.089 |
Pen | -0.086 |
Mir | -0.080 |
Megan | -0.080 |
El | -0.079 |
Token | even |
Token ID | 772 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
Ana | +0.020 |
Pen | +0.020 |
Mir | +0.019 |
Megan | +0.018 |
El | +0.018 |
Neg logit contributions | |
ercise | -0.015 |
ets | -0.015 |
ams | -0.015 |
ock | -0.014 |
isdom | -0.013 |
Token | ask |
Token ID | 1265 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ams | +0.211 |
ercise | +0.208 |
ets | +0.206 |
isdom | +0.194 |
ock | +0.193 |
Neg logit contributions | |
Ana | -0.165 |
Pen | -0.155 |
Mir | -0.146 |
El | -0.144 |
Megan | -0.143 |
Token | her |
Token ID | 607 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Ana | +0.010 |
Pen | +0.010 |
Megan | +0.009 |
Mir | +0.009 |
gen | +0.009 |
Neg logit contributions | |
ets | -0.006 |
ercise | -0.006 |
ams | -0.006 |
ock | -0.005 |
isdom | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Ana | +0.020 |
Pen | +0.019 |
Megan | +0.018 |
Mir | +0.018 |
El | +0.017 |
Neg logit contributions | |
ercise | -0.021 |
ets | -0.021 |
ams | -0.021 |
ock | -0.020 |
isdom | -0.019 |
Token | my |
Token ID | 1820 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ercise | +0.044 |
ets | +0.043 |
ams | +0.042 |
ock | +0.039 |
vious | +0.037 |
Neg logit contributions | |
Ana | -0.068 |
Pen | -0.066 |
Mir | -0.062 |
El | -0.062 |
Megan | -0.062 |
Token | if |
Token ID | 611 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ercise | +0.055 |
ets | +0.054 |
ams | +0.054 |
ock | +0.050 |
isdom | +0.045 |
Neg logit contributions | |
Ana | -0.095 |
Pen | -0.092 |
Mir | -0.088 |
Megan | -0.087 |
El | -0.087 |
Token | needle |
Token ID | 17598 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ercise | +0.022 |
ets | +0.022 |
ock | +0.021 |
ams | +0.020 |
ag | +0.019 |
Neg logit contributions | |
Ana | -0.025 |
Pen | -0.024 |
Megan | -0.023 |
Mir | -0.023 |
Mil | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ercise | +0.008 |
ets | +0.008 |
ams | +0.008 |
ock | +0.007 |
isdom | +0.007 |
Neg logit contributions | |
Ana | -0.016 |
Pen | -0.016 |
Mir | -0.015 |
Megan | -0.015 |
El | -0.015 |
Token | thread |
Token ID | 4704 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ercise | +0.104 |
ets | +0.103 |
ams | +0.102 |
ock | +0.097 |
isdom | +0.090 |
Neg logit contributions | |
Ana | -0.097 |
Pen | -0.093 |
Mir | -0.087 |
Megan | -0.086 |
El | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ets | +0.036 |
ercise | +0.035 |
ams | +0.035 |
ock | +0.033 |
vious | +0.029 |
Neg logit contributions | |
Ana | -0.067 |
Pen | -0.064 |
Megan | -0.061 |
Mir | -0.061 |
El | -0.060 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ercise | +0.093 |
ets | +0.093 |
ams | +0.092 |
ock | +0.087 |
isdom | +0.081 |
Neg logit contributions | |
Ana | -0.090 |
Pen | -0.086 |
Megan | -0.080 |
Mir | -0.080 |
El | -0.079 |
Token | se |
Token ID | 384 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
ets | +0.045 |
ercise | +0.045 |
ams | +0.044 |
ock | +0.041 |
isdom | +0.039 |
Neg logit contributions | |
Ana | -0.048 |
Pen | -0.045 |
Megan | -0.043 |
Mir | -0.041 |
Jenkins | -0.041 |
Token | wed |
Token ID | 19103 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
jets | +0.120 |
weet | +0.118 |
since | +0.108 |
ully | +0.106 |
sunset | +0.104 |
Neg logit contributions | |
Ana | -0.170 |
Mir | -0.170 |
plun | -0.169 |
Megan | -0.169 |
Ann | -0.160 |
Token | Mr |
Token ID | 1770 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
ets | +0.052 |
ams | +0.052 |
ercise | +0.051 |
ock | +0.049 |
ear | +0.043 |
Neg logit contributions | |
Ana | -0.076 |
Pen | -0.073 |
Megan | -0.069 |
gen | -0.068 |
Mir | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Ana | +0.094 |
Pen | +0.088 |
Megan | +0.087 |
El | +0.086 |
plun | +0.086 |
Neg logit contributions | |
ets | -0.046 |
ams | -0.044 |
ock | -0.042 |
ercise | -0.042 |
isdom | -0.039 |
Token | Fl |
Token ID | 1610 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Ana | +0.051 |
Megan | +0.048 |
Pen | +0.044 |
Mil | +0.044 |
El | +0.043 |
Neg logit contributions | |
ercise | -0.065 |
isdom | -0.064 |
ams | -0.061 |
weet | -0.061 |
pads | -0.061 |
Token | uffy |
Token ID | 15352 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Ana | +0.041 |
Pen | +0.038 |
stack | +0.037 |
Megan | +0.037 |
Mir | +0.037 |
Neg logit contributions | |
ams | -0.056 |
ets | -0.055 |
ercise | -0.055 |
isdom | -0.054 |
ock | -0.051 |
Token | forg |
Token ID | 5784 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
Ana | +0.020 |
Pen | +0.019 |
Mir | +0.018 |
Megan | +0.018 |
El | +0.018 |
Neg logit contributions | |
ercise | -0.021 |
ets | -0.021 |
ams | -0.020 |
ock | -0.019 |
isdom | -0.018 |
Token | ave |
Token ID | 1015 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ercise | +0.110 |
ams | +0.102 |
isdom | +0.089 |
opl | +0.089 |
ock | +0.088 |
Neg logit contributions | |
Ana | -0.144 |
plun | -0.135 |
Ell | -0.133 |
El | -0.133 |
Pen | -0.130 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ercise | +0.033 |
ets | +0.033 |
ams | +0.033 |
ock | +0.030 |
vious | +0.028 |
Neg logit contributions | |
Ana | -0.036 |
Pen | -0.035 |
Mir | -0.033 |
Megan | -0.033 |
El | -0.032 |
Token | my |
Token ID | 1820 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ercise | +0.033 |
ets | +0.030 |
ams | +0.028 |
isdom | +0.025 |
ear | +0.025 |
Neg logit contributions | |
Ana | -0.042 |
Pen | -0.040 |
Mir | -0.039 |
Fl | -0.039 |
Jenkins | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
ercise | +0.042 |
ets | +0.039 |
ams | +0.039 |
ock | +0.038 |
vious | +0.035 |
Neg logit contributions | |
Ana | -0.052 |
Pen | -0.049 |
Mir | -0.047 |
El | -0.047 |
Ell | -0.045 |
Token | even |
Token ID | 772 |
Feature activation | +7.10e+00 |
Pos logit contributions | |
ercise | +0.091 |
ams | +0.090 |
ets | +0.088 |
ock | +0.083 |
isdom | +0.078 |
Neg logit contributions | |
Ana | -0.115 |
Pen | -0.111 |
Megan | -0.105 |
plun | -0.104 |
Mir | -0.103 |
Token | gave |
Token ID | 2921 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ercise | +0.190 |
ets | +0.189 |
ams | +0.188 |
ock | +0.180 |
elling | +0.166 |
Neg logit contributions | |
Ana | -0.183 |
Pen | -0.171 |
Mir | -0.165 |
El | -0.160 |
gen | -0.160 |
Token | him |
Token ID | 683 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ets | +0.059 |
ercise | +0.058 |
ams | +0.057 |
ock | +0.052 |
vious | +0.049 |
Neg logit contributions | |
Ana | -0.084 |
Pen | -0.080 |
Mir | -0.077 |
Megan | -0.077 |
El | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Ana | +0.006 |
Pen | +0.006 |
El | +0.005 |
Fl | +0.005 |
Megan | +0.005 |
Neg logit contributions | |
ets | -0.009 |
ams | -0.009 |
ercise | -0.008 |
ock | -0.008 |
elling | -0.008 |
Token | reward |
Token ID | 6721 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
Ana | +0.001 |
Pen | +0.001 |
plun | +0.001 |
Mir | +0.001 |
gen | +0.001 |
Neg logit contributions | |
ams | -0.001 |
ets | -0.001 |
ercise | -0.001 |
ock | -0.001 |
isdom | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Ana | +0.001 |
Pen | +0.001 |
Mir | +0.001 |
Megan | +0.001 |
El | +0.001 |
Neg logit contributions | |
ercise | -0.001 |
ets | -0.001 |
ams | -0.001 |
ock | -0.001 |
vious | -0.001 |
Token | around |
Token ID | 1088 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ets | +0.013 |
ercise | +0.013 |
ams | +0.013 |
ock | +0.012 |
vious | +0.011 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.019 |
Mir | -0.018 |
Megan | -0.018 |
El | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Ana | +0.038 |
Pen | +0.037 |
Megan | +0.036 |
Mei | +0.036 |
illi | +0.035 |
Neg logit contributions | |
ets | -0.014 |
ock | -0.013 |
ams | -0.012 |
ear | -0.011 |
ercise | -0.011 |
Token | hallway |
Token ID | 23959 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
Ana | +0.031 |
Pen | +0.029 |
El | +0.029 |
Megan | +0.028 |
Mir | +0.028 |
Neg logit contributions | |
ets | -0.036 |
ams | -0.034 |
ercise | -0.033 |
ock | -0.032 |
off | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Ana | +0.170 |
Pen | +0.166 |
Mir | +0.155 |
plun | +0.154 |
Megan | +0.154 |
Neg logit contributions | |
ets | -0.102 |
ams | -0.097 |
ercise | -0.089 |
ock | -0.088 |
ear | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Ana | +0.035 |
Pen | +0.034 |
Megan | +0.032 |
Mir | +0.030 |
Jenkins | +0.030 |
Neg logit contributions | |
ets | -0.036 |
ercise | -0.035 |
ams | -0.034 |
ock | -0.032 |
ear | -0.030 |
Token | dining |
Token ID | 17423 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.042 |
El | +0.040 |
Megan | +0.040 |
Mir | +0.040 |
Neg logit contributions | |
ets | -0.052 |
ercise | -0.051 |
ams | -0.049 |
ock | -0.048 |
vious | -0.045 |
Token | room |
Token ID | 2119 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
Ana | +0.166 |
Pen | +0.165 |
El | +0.159 |
Sn | +0.156 |
plun | +0.156 |
Neg logit contributions | |
ets | -0.211 |
ams | -0.205 |
ock | -0.175 |
ercise | -0.175 |
les | -0.174 |
Token | and |
Token ID | 290 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Ana | +0.123 |
Pen | +0.120 |
Mir | +0.111 |
Mei | +0.109 |
Megan | +0.108 |
Neg logit contributions | |
ets | -0.104 |
ams | -0.096 |
ock | -0.089 |
ercise | -0.088 |
vious | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ams | +0.053 |
ercise | +0.052 |
ets | +0.050 |
ock | +0.049 |
pads | +0.041 |
Neg logit contributions | |
Ana | -0.083 |
Pen | -0.081 |
Mir | -0.075 |
plun | -0.074 |
Mei | -0.074 |
Token | bedroom |
Token ID | 14043 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
Ana | +0.035 |
Pen | +0.033 |
Mir | +0.032 |
El | +0.032 |
Mil | +0.031 |
Neg logit contributions | |
ercise | -0.039 |
ets | -0.038 |
ams | -0.037 |
ock | -0.036 |
vious | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Ana | +0.131 |
Pen | +0.131 |
Mei | +0.120 |
Mir | +0.119 |
Flor | +0.117 |
Neg logit contributions | |
ets | -0.113 |
ams | -0.099 |
ock | -0.087 |
ly | -0.086 |
les | -0.084 |
Token | loud |
Token ID | 7812 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Pen | +0.053 |
Megan | +0.052 |
Ana | +0.051 |
Mir | +0.050 |
Mil | +0.049 |
Neg logit contributions | |
ock | -0.025 |
ercise | -0.025 |
ay | -0.023 |
arrow | -0.022 |
weet | -0.022 |
Token | laugh |
Token ID | 6487 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Ana | +0.026 |
Pen | +0.025 |
Megan | +0.024 |
illi | +0.024 |
Mil | +0.023 |
Neg logit contributions | |
ock | -0.026 |
ets | -0.024 |
ercise | -0.024 |
weet | -0.023 |
ag | -0.022 |
Token | echoed |
Token ID | 22211 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ets | +0.010 |
ercise | +0.010 |
ams | +0.010 |
ock | +0.010 |
vious | +0.009 |
Neg logit contributions | |
Ana | -0.010 |
Pen | -0.010 |
Mir | -0.009 |
Megan | -0.009 |
El | -0.009 |
Token | around |
Token ID | 1088 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Ana | +0.054 |
Pen | +0.053 |
Mir | +0.051 |
Megan | +0.050 |
plun | +0.049 |
Neg logit contributions | |
ets | -0.035 |
ams | -0.033 |
ock | -0.033 |
ercise | -0.032 |
ear | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Ana | +0.086 |
Pen | +0.085 |
gen | +0.085 |
Mir | +0.084 |
Megan | +0.082 |
Neg logit contributions | |
ets | -0.045 |
ock | -0.039 |
ercise | -0.038 |
ams | -0.037 |
les | -0.034 |
Token | chamber |
Token ID | 11847 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
Ana | +0.025 |
Pen | +0.025 |
Mir | +0.024 |
plun | +0.022 |
Megan | +0.022 |
Neg logit contributions | |
ets | -0.042 |
ercise | -0.040 |
ams | -0.039 |
ock | -0.038 |
ear | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Pen | +0.258 |
Ana | +0.257 |
Mir | +0.245 |
Megan | +0.242 |
plun | +0.241 |
Neg logit contributions | |
ets | -0.122 |
ams | -0.094 |
ock | -0.092 |
ear | -0.083 |
vious | -0.082 |
Token | " |
Token ID | 366 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Ana | +0.006 |
Pen | +0.006 |
gen | +0.006 |
Mir | +0.006 |
Megan | +0.006 |
Neg logit contributions | |
ets | -0.005 |
ercise | -0.005 |
ams | -0.005 |
ock | -0.005 |
isdom | -0.004 |
Token | Welcome |
Token ID | 14618 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Ana | +0.040 |
Pen | +0.038 |
Mir | +0.036 |
Megan | +0.035 |
El | +0.035 |
Neg logit contributions | |
ercise | -0.050 |
ets | -0.049 |
ams | -0.049 |
ock | -0.047 |
vious | -0.044 |
Token | visitors |
Token ID | 9692 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
ercise | +0.009 |
ets | +0.008 |
ams | +0.008 |
ock | +0.008 |
ear | +0.007 |
Neg logit contributions | |
Ana | -0.016 |
Pen | -0.015 |
Mir | -0.015 |
plun | -0.014 |
Megan | -0.014 |
Token | ," |
Token ID | 553 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ets | +0.019 |
ercise | +0.018 |
ams | +0.018 |
ock | +0.017 |
vious | +0.015 |
Neg logit contributions | |
Ana | -0.030 |
Pen | -0.029 |
Mir | -0.028 |
plun | -0.028 |
Megan | -0.027 |
Token | came |
Token ID | 1625 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Ana | +0.002 |
Pen | +0.002 |
plun | +0.002 |
Megan | +0.002 |
Mir | +0.002 |
Neg logit contributions | |
ets | -0.002 |
ercise | -0.002 |
ock | -0.002 |
ams | -0.002 |
vious | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Ana | +0.092 |
Pen | +0.088 |
Megan | +0.085 |
plun | +0.083 |
Mir | +0.083 |
Neg logit contributions | |
ets | -0.067 |
ock | -0.066 |
ams | -0.065 |
ercise | -0.065 |
ear | -0.059 |
Token | deep |
Token ID | 2769 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Ana | +0.128 |
Pen | +0.122 |
Mir | +0.115 |
Megan | +0.115 |
plun | +0.112 |
Neg logit contributions | |
ercise | -0.116 |
ets | -0.115 |
ams | -0.111 |
ock | -0.109 |
isdom | -0.100 |
Token | inside |
Token ID | 2641 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
Ana | +0.038 |
Pen | +0.037 |
Mir | +0.035 |
El | +0.034 |
Megan | +0.034 |
Neg logit contributions | |
ercise | -0.031 |
ets | -0.030 |
ams | -0.030 |
ock | -0.028 |
isdom | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Ana | +0.177 |
Pen | +0.171 |
plun | +0.168 |
Mir | +0.165 |
Lopez | +0.163 |
Neg logit contributions | |
ock | -0.072 |
ets | -0.071 |
ams | -0.065 |
ear | -0.060 |
weet | -0.059 |
Token | chamber |
Token ID | 11847 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
Ana | +0.028 |
Pen | +0.028 |
Mir | +0.027 |
Mil | +0.027 |
Megan | +0.026 |
Neg logit contributions | |
ets | -0.050 |
ercise | -0.049 |
ock | -0.046 |
ams | -0.045 |
elling | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
Ana | +0.243 |
Pen | +0.241 |
plun | +0.236 |
Mir | +0.229 |
Sn | +0.228 |
Neg logit contributions | |
ets | -0.104 |
ams | -0.089 |
ock | -0.085 |
ercise | -0.078 |
ear | -0.078 |
Token | Max |
Token ID | 5436 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Ana | +0.019 |
Megan | +0.019 |
Pen | +0.019 |
Mil | +0.018 |
Mir | +0.018 |
Neg logit contributions | |
ercise | -0.014 |
ets | -0.013 |
isdom | -0.012 |
ock | -0.011 |
ear | -0.011 |
Token | jumped |
Token ID | 11687 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Ana | +0.018 |
plun | +0.018 |
stack | +0.018 |
Megan | +0.018 |
Pen | +0.018 |
Neg logit contributions | |
ets | -0.014 |
ercise | -0.014 |
ly | -0.013 |
les | -0.013 |
pads | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ets | +0.002 |
ercise | +0.002 |
ams | +0.002 |
ock | +0.002 |
ear | +0.002 |
Neg logit contributions | |
Ana | -0.004 |
Pen | -0.004 |
Mir | -0.004 |
Megan | -0.003 |
gen | -0.003 |
Token | fright |
Token ID | 12773 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Ana | +0.006 |
Pen | +0.006 |
Mir | +0.006 |
Megan | +0.006 |
El | +0.006 |
Neg logit contributions | |
ercise | -0.005 |
ets | -0.005 |
ams | -0.005 |
ock | -0.005 |
isdom | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
Ana | +0.003 |
Pen | +0.003 |
Mir | +0.003 |
Megan | +0.003 |
El | +0.002 |
Neg logit contributions | |
ercise | -0.002 |
ets | -0.002 |
ams | -0.002 |
ock | -0.002 |
vious | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Ana | +0.134 |
ider | +0.131 |
Pen | +0.128 |
comb | +0.127 |
gen | +0.127 |
Neg logit contributions | |
ock | -0.046 |
ercise | -0.041 |
ams | -0.036 |
ag | -0.035 |
ear | -0.034 |
Token | edge |
Token ID | 5743 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Ana | +0.015 |
Pen | +0.014 |
Mir | +0.013 |
illi | +0.013 |
Megan | +0.012 |
Neg logit contributions | |
ercise | -0.013 |
ets | -0.013 |
ams | -0.012 |
vious | -0.012 |
ock | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Ana | +0.101 |
Pen | +0.098 |
Mir | +0.096 |
Megan | +0.096 |
Mil | +0.092 |
Neg logit contributions | |
ercise | -0.053 |
ets | -0.046 |
ams | -0.044 |
isdom | -0.041 |
ock | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Ana | +0.089 |
Pen | +0.086 |
igor | +0.084 |
Jenkins | +0.083 |
gen | +0.081 |
Neg logit contributions | |
ock | -0.037 |
ams | -0.035 |
ercise | -0.032 |
ets | -0.031 |
weet | -0.029 |
Token | pit |
Token ID | 6028 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
Ana | +0.024 |
Pen | +0.023 |
Mir | +0.020 |
Megan | +0.020 |
El | +0.019 |
Neg logit contributions | |
ets | -0.035 |
ercise | -0.034 |
ams | -0.033 |
ock | -0.033 |
vious | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Ana | +0.251 |
Pen | +0.244 |
Mir | +0.229 |
Megan | +0.229 |
El | +0.228 |
Neg logit contributions | |
ets | -0.116 |
ams | -0.114 |
ercise | -0.108 |
ock | -0.103 |
vious | -0.089 |
Token | leaned |
Token ID | 23831 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ercise | +0.072 |
ets | +0.071 |
ams | +0.069 |
vious | +0.063 |
ock | +0.059 |
Neg logit contributions | |
Ana | -0.078 |
Pen | -0.075 |
Jenkins | -0.074 |
plun | -0.072 |
Lopez | -0.072 |
Token | over |
Token ID | 625 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Ana | +0.004 |
Pen | +0.004 |
Mir | +0.003 |
Megan | +0.003 |
El | +0.003 |
Neg logit contributions | |
ercise | -0.003 |
ams | -0.003 |
ets | -0.002 |
ock | -0.002 |
vious | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Ana | +0.100 |
Pen | +0.097 |
gen | +0.093 |
plun | +0.091 |
Mir | +0.091 |
Neg logit contributions | |
ercise | -0.052 |
ams | -0.051 |
ets | -0.051 |
ock | -0.049 |
ear | -0.044 |
Token | examine |
Token ID | 10716 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Ana | +0.110 |
Pen | +0.106 |
Jenkins | +0.105 |
Lopez | +0.102 |
gen | +0.101 |
Neg logit contributions | |
ercise | -0.079 |
ock | -0.077 |
ets | -0.073 |
ams | -0.068 |
ear | -0.067 |
Token | strange |
Token ID | 6283 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Pen | +0.002 |
Megan | +0.002 |
Ana | +0.002 |
stack | +0.002 |
Mir | +0.002 |
Neg logit contributions | |
ock | -0.002 |
ercise | -0.001 |
ets | -0.001 |
weet | -0.001 |
ag | -0.001 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ets | +0.015 |
ock | +0.015 |
ercise | +0.015 |
ams | +0.014 |
isdom | +0.013 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.015 |
Megan | -0.014 |
Mir | -0.014 |
Mil | -0.013 |
Token | coming |
Token ID | 2406 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Ana | +0.075 |
Pen | +0.072 |
Mir | +0.069 |
Megan | +0.068 |
El | +0.067 |
Neg logit contributions | |
ets | -0.056 |
ercise | -0.054 |
ams | -0.054 |
ock | -0.053 |
vious | -0.047 |
Token | from |
Token ID | 422 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
Ana | +0.139 |
Pen | +0.133 |
Megan | +0.128 |
gen | +0.126 |
plun | +0.125 |
Neg logit contributions | |
ock | -0.092 |
ets | -0.089 |
ams | -0.084 |
ercise | -0.082 |
ear | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Ana | +0.138 |
Pen | +0.132 |
Mir | +0.126 |
Megan | +0.125 |
plun | +0.123 |
Neg logit contributions | |
ets | -0.098 |
ercise | -0.098 |
ams | -0.094 |
ock | -0.093 |
ear | -0.083 |
Token | living |
Token ID | 2877 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
Ana | +0.036 |
Pen | +0.034 |
Mir | +0.033 |
Megan | +0.033 |
Mil | +0.032 |
Neg logit contributions | |
ock | -0.043 |
ets | -0.043 |
ercise | -0.041 |
vious | -0.038 |
ams | -0.037 |
Token | room |
Token ID | 2119 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Ana | +0.168 |
Pen | +0.167 |
Stev | +0.155 |
El | +0.154 |
Megan | +0.153 |
Neg logit contributions | |
ams | -0.176 |
ets | -0.175 |
ock | -0.160 |
les | -0.156 |
off | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
Ana | +0.163 |
Pen | +0.158 |
Mir | +0.152 |
El | +0.148 |
Megan | +0.148 |
Neg logit contributions | |
ets | -0.100 |
ams | -0.095 |
ock | -0.090 |
ercise | -0.089 |
vious | -0.080 |
Token | She |
Token ID | 1375 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ets | +0.002 |
ercise | +0.002 |
ams | +0.002 |
ear | +0.002 |
isdom | +0.002 |
Neg logit contributions | |
Ana | -0.003 |
Pen | -0.003 |
gen | -0.003 |
Mir | -0.003 |
plun | -0.003 |
Token | got |
Token ID | 1392 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
Ana | +0.032 |
Pen | +0.032 |
stack | +0.031 |
plun | +0.030 |
Megan | +0.030 |
Neg logit contributions | |
ets | -0.033 |
ercise | -0.033 |
ams | -0.032 |
ock | -0.031 |
ear | -0.029 |
Token | scared |
Token ID | 12008 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
Ana | +0.027 |
Pen | +0.027 |
stack | +0.026 |
Megan | +0.026 |
Mir | +0.025 |
Neg logit contributions | |
ercise | -0.019 |
ams | -0.019 |
ets | -0.018 |
vious | -0.018 |
ock | -0.017 |
Token | loud |
Token ID | 7812 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Pen | +0.049 |
Ana | +0.049 |
Megan | +0.048 |
Mir | +0.048 |
stack | +0.047 |
Neg logit contributions | |
ercise | -0.032 |
ock | -0.030 |
ams | -0.030 |
ets | -0.028 |
weet | -0.027 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Ana | +0.020 |
Pen | +0.019 |
Megan | +0.018 |
illi | +0.018 |
plun | +0.017 |
Neg logit contributions | |
ock | -0.021 |
ercise | -0.020 |
ets | -0.020 |
ams | -0.019 |
weet | -0.019 |
Token | came |
Token ID | 1625 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Ana | +0.065 |
Pen | +0.062 |
Mir | +0.059 |
Megan | +0.058 |
Mil | +0.056 |
Neg logit contributions | |
ets | -0.060 |
ock | -0.059 |
ercise | -0.058 |
ams | -0.057 |
les | -0.052 |
Token | from |
Token ID | 422 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
Ana | +0.103 |
Pen | +0.097 |
Megan | +0.094 |
Mir | +0.092 |
gen | +0.092 |
Neg logit contributions | |
ets | -0.068 |
ock | -0.068 |
ams | -0.066 |
ercise | -0.066 |
ear | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Ana | +0.139 |
Pen | +0.132 |
Mir | +0.126 |
Megan | +0.125 |
Mil | +0.122 |
Neg logit contributions | |
ercise | -0.104 |
ets | -0.102 |
ams | -0.100 |
ock | -0.098 |
isdom | -0.087 |
Token | living |
Token ID | 2877 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
Ana | +0.034 |
Pen | +0.032 |
Mir | +0.031 |
El | +0.030 |
Megan | +0.030 |
Neg logit contributions | |
ets | -0.040 |
ercise | -0.040 |
ams | -0.039 |
ock | -0.039 |
vious | -0.037 |
Token | room |
Token ID | 2119 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Ana | +0.157 |
Pen | +0.154 |
Mir | +0.142 |
Megan | +0.141 |
Stev | +0.140 |
Neg logit contributions | |
ams | -0.194 |
ets | -0.187 |
les | -0.170 |
ock | -0.170 |
ercise | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Ana | +0.165 |
Pen | +0.159 |
Mir | +0.153 |
Megan | +0.148 |
El | +0.148 |
Neg logit contributions | |
ets | -0.085 |
ams | -0.079 |
ock | -0.072 |
ercise | -0.070 |
vious | -0.063 |
Token | Billy |
Token ID | 15890 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Ana | +0.015 |
gen | +0.015 |
Pen | +0.014 |
plun | +0.014 |
teaspoon | +0.014 |
Neg logit contributions | |
ercise | -0.007 |
ets | -0.007 |
ams | -0.007 |
isdom | -0.006 |
ock | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ets | +0.021 |
ercise | +0.020 |
ams | +0.020 |
ock | +0.019 |
les | +0.019 |
Neg logit contributions | |
Ana | -0.025 |
Mir | -0.023 |
gen | -0.023 |
Pen | -0.023 |
Megan | -0.023 |
Token | scared |
Token ID | 12008 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Ana | +0.058 |
stack | +0.056 |
gen | +0.055 |
Mir | +0.055 |
Pen | +0.054 |
Neg logit contributions | |
about | -0.040 |
vious | -0.037 |
ets | -0.036 |
ams | -0.035 |
ag | -0.035 |
Token | 's |
Token ID | 338 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.021 |
Megan | +0.020 |
gen | +0.020 |
Mir | +0.020 |
Neg logit contributions | |
ets | -0.011 |
ams | -0.010 |
ock | -0.010 |
ercise | -0.010 |
ear | -0.009 |
Token | voice |
Token ID | 3809 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Pen | +0.008 |
Ana | +0.008 |
stack | +0.007 |
plun | +0.007 |
Megan | +0.007 |
Neg logit contributions | |
ets | -0.011 |
ams | -0.011 |
ock | -0.011 |
ercise | -0.010 |
ag | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.012 |
Mir | +0.011 |
Megan | +0.011 |
El | +0.011 |
Neg logit contributions | |
ets | -0.007 |
ams | -0.007 |
ercise | -0.007 |
ock | -0.006 |
vious | -0.006 |
Token | inside |
Token ID | 2641 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
Ana | +0.118 |
Pen | +0.113 |
Mir | +0.105 |
gen | +0.104 |
plun | +0.104 |
Neg logit contributions | |
ets | -0.114 |
ercise | -0.112 |
ock | -0.108 |
ams | -0.106 |
ear | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Ana | +0.142 |
gen | +0.137 |
Pen | +0.137 |
plun | +0.132 |
Mir | +0.131 |
Neg logit contributions | |
ets | -0.073 |
ock | -0.070 |
ams | -0.068 |
ercise | -0.061 |
ear | -0.057 |
Token | cabinet |
Token ID | 13447 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.021 |
El | +0.019 |
Mir | +0.019 |
Megan | +0.019 |
Neg logit contributions | |
ets | -0.032 |
ercise | -0.031 |
ock | -0.029 |
ams | -0.029 |
vious | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Ana | +0.228 |
Pen | +0.221 |
Mir | +0.208 |
Megan | +0.208 |
El | +0.208 |
Neg logit contributions | |
ets | -0.129 |
ams | -0.122 |
ercise | -0.112 |
ock | -0.112 |
vious | -0.102 |
Token | He |
Token ID | 679 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
illi | +0.078 |
gen | +0.077 |
plun | +0.076 |
teaspoon | +0.075 |
ocated | +0.075 |
Neg logit contributions | |
ercise | -0.017 |
ets | -0.015 |
vious | -0.014 |
ear | -0.014 |
aw | -0.012 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
stack | +0.061 |
Ana | +0.060 |
Pen | +0.059 |
Lopez | +0.058 |
Jenkins | +0.057 |
Neg logit contributions | |
ercise | -0.047 |
ets | -0.046 |
ams | -0.044 |
aw | -0.042 |
les | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
ercise | +0.019 |
ets | +0.019 |
ock | +0.017 |
ams | +0.017 |
ear | +0.013 |
Neg logit contributions | |
Ana | -0.062 |
Pen | -0.061 |
plun | -0.061 |
stack | -0.060 |
gen | -0.059 |
Token | surprise |
Token ID | 5975 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Ana | +0.099 |
Pen | +0.097 |
Mir | +0.092 |
plun | +0.091 |
Jenkins | +0.090 |
Neg logit contributions | |
ercise | -0.073 |
ets | -0.072 |
ock | -0.071 |
ear | -0.066 |
ams | -0.065 |
Token | loud |
Token ID | 7812 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Pen | +0.034 |
Ana | +0.033 |
Megan | +0.033 |
stack | +0.033 |
Mir | +0.033 |
Neg logit contributions | |
ercise | -0.020 |
ock | -0.019 |
ay | -0.018 |
ams | -0.017 |
ets | -0.017 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Ana | +0.018 |
Pen | +0.017 |
Megan | +0.017 |
illi | +0.016 |
El | +0.016 |
Neg logit contributions | |
ock | -0.020 |
ercise | -0.019 |
ets | -0.019 |
ams | -0.018 |
weet | -0.018 |
Token | came |
Token ID | 1625 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Ana | +0.052 |
Pen | +0.050 |
Mir | +0.047 |
Megan | +0.047 |
Mil | +0.045 |
Neg logit contributions | |
ets | -0.052 |
ercise | -0.051 |
ock | -0.051 |
ams | -0.050 |
vious | -0.046 |
Token | from |
Token ID | 422 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
Ana | +0.091 |
Pen | +0.087 |
Megan | +0.084 |
gen | +0.083 |
Mir | +0.082 |
Neg logit contributions | |
ock | -0.054 |
ets | -0.054 |
ams | -0.053 |
ercise | -0.051 |
ear | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Ana | +0.142 |
Pen | +0.135 |
Mir | +0.129 |
gen | +0.128 |
Megan | +0.128 |
Neg logit contributions | |
ercise | -0.095 |
ets | -0.092 |
ams | -0.088 |
ock | -0.088 |
isdom | -0.078 |
Token | living |
Token ID | 2877 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
Ana | +0.027 |
Pen | +0.025 |
Megan | +0.025 |
Mir | +0.024 |
El | +0.024 |
Neg logit contributions | |
ercise | -0.035 |
ets | -0.035 |
ock | -0.034 |
ams | -0.033 |
vious | -0.033 |
Token | room |
Token ID | 2119 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
Ana | +0.164 |
Pen | +0.161 |
comb | +0.154 |
stack | +0.154 |
Stev | +0.154 |
Neg logit contributions | |
ams | -0.182 |
ets | -0.175 |
les | -0.159 |
off | -0.152 |
vious | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Ana | +0.166 |
Pen | +0.162 |
Mir | +0.154 |
Flor | +0.152 |
El | +0.151 |
Neg logit contributions | |
ets | -0.082 |
ams | -0.073 |
ock | -0.066 |
ercise | -0.062 |
vious | -0.061 |
Token | It |
Token ID | 632 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Ana | +0.012 |
stack | +0.012 |
Pen | +0.011 |
plun | +0.011 |
gen | +0.011 |
Neg logit contributions | |
ercise | -0.007 |
ams | -0.006 |
ets | -0.006 |
elling | -0.006 |
isdom | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Ana | +0.003 |
Pen | +0.003 |
Flor | +0.003 |
Mir | +0.003 |
stack | +0.003 |
Neg logit contributions | |
ercise | -0.003 |
ets | -0.003 |
ock | -0.003 |
les | -0.003 |
vious | -0.003 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Ana | +0.082 |
Pen | +0.077 |
stack | +0.074 |
Megan | +0.073 |
El | +0.073 |
Neg logit contributions | |
ock | -0.044 |
ercise | -0.044 |
ams | -0.043 |
ets | -0.042 |
weet | -0.040 |
Token | at |
Token ID | 379 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Ana | +0.094 |
Pen | +0.090 |
Mir | +0.085 |
Megan | +0.084 |
El | +0.083 |
Neg logit contributions | |
ercise | -0.091 |
ams | -0.090 |
ets | -0.090 |
ock | -0.085 |
vious | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Ana | +0.096 |
Pen | +0.090 |
Megan | +0.086 |
gen | +0.085 |
plun | +0.085 |
Neg logit contributions | |
ercise | -0.056 |
ock | -0.055 |
ets | -0.054 |
ams | -0.054 |
weet | -0.046 |
Token | edge |
Token ID | 5743 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Ana | +0.003 |
Pen | +0.003 |
Megan | +0.003 |
El | +0.003 |
Mir | +0.003 |
Neg logit contributions | |
ets | -0.004 |
ercise | -0.004 |
ock | -0.004 |
ams | -0.004 |
vious | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Ana | +0.112 |
Pen | +0.108 |
Megan | +0.106 |
Mir | +0.105 |
El | +0.102 |
Neg logit contributions | |
ercise | -0.073 |
ets | -0.064 |
ams | -0.062 |
isdom | -0.060 |
ock | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Ana | +0.089 |
Pen | +0.084 |
Megan | +0.080 |
El | +0.079 |
Jenkins | +0.079 |
Neg logit contributions | |
ock | -0.053 |
ercise | -0.052 |
ams | -0.052 |
ets | -0.050 |
weet | -0.046 |
Token | pit |
Token ID | 6028 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
Ana | +0.016 |
Pen | +0.015 |
Mir | +0.013 |
Megan | +0.013 |
El | +0.013 |
Neg logit contributions | |
ets | -0.035 |
ercise | -0.034 |
ams | -0.034 |
ock | -0.033 |
vious | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Ana | +0.210 |
Pen | +0.204 |
Mir | +0.191 |
Megan | +0.190 |
El | +0.188 |
Neg logit contributions | |
ets | -0.147 |
ams | -0.145 |
ercise | -0.141 |
ock | -0.134 |
vious | -0.122 |
Token | The |
Token ID | 383 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
ercise | +0.003 |
ets | +0.003 |
ams | +0.003 |
isdom | +0.002 |
ock | +0.002 |
Neg logit contributions | |
Ana | -0.005 |
Pen | -0.005 |
Mir | -0.004 |
El | -0.004 |
Megan | -0.004 |
Token | lion |
Token ID | 18744 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Ana | +0.016 |
Pen | +0.016 |
Mir | +0.015 |
Megan | +0.015 |
El | +0.015 |
Neg logit contributions | |
ercise | -0.015 |
ets | -0.015 |
ams | -0.015 |
ock | -0.014 |
isdom | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Ana | +0.033 |
Pen | +0.032 |
plun | +0.030 |
Megan | +0.030 |
Mir | +0.030 |
Neg logit contributions | |
ams | -0.035 |
ercise | -0.035 |
ets | -0.035 |
ock | -0.032 |
isdom | -0.031 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Ana | +0.068 |
Pen | +0.064 |
Megan | +0.060 |
plun | +0.059 |
El | +0.059 |
Neg logit contributions | |
ams | -0.069 |
ercise | -0.067 |
ets | -0.066 |
ock | -0.064 |
weet | -0.062 |
Token | balance |
Token ID | 5236 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Ana | +0.031 |
Pen | +0.030 |
Mir | +0.028 |
Megan | +0.028 |
El | +0.027 |
Neg logit contributions | |
ercise | -0.034 |
ets | -0.033 |
ams | -0.033 |
ock | -0.031 |
isdom | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ercise | +0.004 |
ams | +0.003 |
ets | +0.003 |
isdom | +0.003 |
elling | +0.003 |
Neg logit contributions | |
Ana | -0.004 |
Pen | -0.004 |
plun | -0.004 |
Mir | -0.004 |
Megan | -0.004 |
Token | fell |
Token ID | 3214 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ercise | +0.067 |
ets | +0.067 |
ams | +0.064 |
ock | +0.061 |
pads | +0.058 |
Neg logit contributions | |
Ana | -0.070 |
Pen | -0.065 |
Lopez | -0.061 |
Jenkins | -0.061 |
Megan | -0.061 |
Token | into |
Token ID | 656 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
ets | +0.014 |
ams | +0.013 |
ercise | +0.013 |
ock | +0.013 |
vious | +0.011 |
Neg logit contributions | |
Ana | -0.023 |
Pen | -0.022 |
Megan | -0.021 |
Mir | -0.021 |
gen | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
stack | +0.174 |
ider | +0.173 |
igor | +0.172 |
Ana | +0.171 |
Pen | +0.167 |
Neg logit contributions | |
ock | -0.043 |
ams | -0.036 |
weet | -0.032 |
ear | -0.028 |
vious | -0.027 |
Token | pit |
Token ID | 6028 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
Ana | +0.026 |
Pen | +0.025 |
Mir | +0.022 |
El | +0.021 |
Megan | +0.021 |
Neg logit contributions | |
ets | -0.047 |
ercise | -0.046 |
ams | -0.046 |
ock | -0.044 |
vious | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Ana | +0.225 |
Pen | +0.218 |
Mir | +0.205 |
El | +0.204 |
Megan | +0.203 |
Neg logit contributions | |
ets | -0.133 |
ams | -0.125 |
ock | -0.120 |
ercise | -0.115 |
vious | -0.107 |
Token | He |
Token ID | 679 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Ana | +0.039 |
Pen | +0.037 |
gen | +0.036 |
El | +0.036 |
plun | +0.035 |
Neg logit contributions | |
ams | -0.019 |
ets | -0.019 |
ercise | -0.019 |
ock | -0.018 |
ear | -0.017 |
Token | screamed |
Token ID | 25421 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Ana | +0.051 |
Pen | +0.048 |
Megan | +0.045 |
Mir | +0.045 |
El | +0.045 |
Neg logit contributions | |
ets | -0.061 |
ercise | -0.059 |
ams | -0.059 |
ock | -0.056 |
vious | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Ana | +0.050 |
Pen | +0.049 |
Megan | +0.047 |
Mir | +0.046 |
El | +0.046 |
Neg logit contributions | |
ets | -0.019 |
ercise | -0.018 |
ams | -0.017 |
ock | -0.016 |
ear | -0.014 |
Token | cried |
Token ID | 16896 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ets | +0.049 |
ercise | +0.047 |
ams | +0.046 |
ock | +0.043 |
vious | +0.042 |
Neg logit contributions | |
Ana | -0.045 |
Pen | -0.042 |
Jenkins | -0.041 |
Lopez | -0.041 |
Megan | -0.040 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Ana | +0.092 |
Pen | +0.088 |
Megan | +0.086 |
gen | +0.085 |
El | +0.083 |
Neg logit contributions | |
ercise | -0.066 |
ets | -0.066 |
ams | -0.064 |
ock | -0.056 |
isdom | -0.055 |
Token | ran |
Token ID | 4966 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
Ana | +0.034 |
Pen | +0.034 |
Mir | +0.032 |
Megan | +0.031 |
El | +0.031 |
Neg logit contributions | |
ets | -0.025 |
ercise | -0.024 |
ams | -0.024 |
ock | -0.022 |
vious | -0.022 |
Token | out |
Token ID | 503 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ercise | +0.001 |
ets | +0.001 |
ams | +0.001 |
ock | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
Ana | -0.002 |
Pen | -0.002 |
Mir | -0.002 |
Megan | -0.002 |
El | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Ana | +0.152 |
Pen | +0.149 |
Megan | +0.142 |
Mir | +0.142 |
El | +0.141 |
Neg logit contributions | |
ets | -0.039 |
ams | -0.038 |
ercise | -0.036 |
ock | -0.035 |
vious | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Ana | +0.038 |
Pen | +0.037 |
Megan | +0.035 |
Mir | +0.035 |
El | +0.035 |
Neg logit contributions | |
ams | -0.023 |
ercise | -0.023 |
ock | -0.023 |
ets | -0.023 |
weet | -0.020 |
Token | chamber |
Token ID | 11847 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
Ana | +0.019 |
Pen | +0.018 |
Mir | +0.017 |
plun | +0.016 |
gen | +0.016 |
Neg logit contributions | |
ercise | -0.042 |
ets | -0.042 |
ams | -0.042 |
ock | -0.040 |
isdom | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Ana | +0.251 |
Pen | +0.249 |
Mir | +0.236 |
El | +0.236 |
Megan | +0.235 |
Neg logit contributions | |
ets | -0.102 |
ams | -0.086 |
ock | -0.076 |
ercise | -0.074 |
ear | -0.068 |
Token | back |
Token ID | 736 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
ets | +0.069 |
ercise | +0.068 |
ams | +0.067 |
pads | +0.057 |
ock | +0.055 |
Neg logit contributions | |
Ana | -0.082 |
Pen | -0.080 |
gen | -0.075 |
El | -0.074 |
Mir | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
gen | +0.020 |
Ana | +0.020 |
Pen | +0.019 |
plun | +0.019 |
Maur | +0.018 |
Neg logit contributions | |
ets | -0.005 |
ams | -0.004 |
ercise | -0.004 |
ear | -0.003 |
off | -0.003 |
Token | their |
Token ID | 511 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Ana | +0.116 |
Pen | +0.114 |
gen | +0.112 |
plun | +0.110 |
comb | +0.107 |
Neg logit contributions | |
ercise | -0.051 |
ets | -0.047 |
ams | -0.046 |
isdom | -0.043 |
ock | -0.042 |
Token | room |
Token ID | 2119 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Ana | +0.034 |
Pen | +0.034 |
Mir | +0.032 |
El | +0.031 |
Megan | +0.031 |
Neg logit contributions | |
ets | -0.034 |
ercise | -0.033 |
ams | -0.033 |
ock | -0.029 |
off | -0.029 |
Token | loud |
Token ID | 7812 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Megan | +0.006 |
Pen | +0.006 |
stack | +0.006 |
Ana | +0.006 |
Mil | +0.006 |
Neg logit contributions | |
ock | -0.003 |
ercise | -0.003 |
ets | -0.003 |
weet | -0.003 |
ly | -0.003 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Ana | +0.009 |
Pen | +0.009 |
Megan | +0.009 |
Lopez | +0.008 |
Jenkins | +0.008 |
Neg logit contributions | |
ock | -0.010 |
ets | -0.009 |
ercise | -0.009 |
weet | -0.009 |
ag | -0.008 |
Token | coming |
Token ID | 2406 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
Ana | +0.077 |
Pen | +0.074 |
Mir | +0.071 |
Megan | +0.070 |
El | +0.069 |
Neg logit contributions | |
ercise | -0.058 |
ets | -0.058 |
ams | -0.057 |
ock | -0.054 |
isdom | -0.049 |
Token | from |
Token ID | 422 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Ana | +0.145 |
Pen | +0.138 |
Megan | +0.133 |
gen | +0.130 |
Mir | +0.129 |
Neg logit contributions | |
ets | -0.101 |
ock | -0.100 |
ams | -0.095 |
ercise | -0.095 |
ear | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Ana | +0.136 |
Pen | +0.130 |
Megan | +0.124 |
Mir | +0.123 |
gen | +0.121 |
Neg logit contributions | |
ercise | -0.098 |
ets | -0.098 |
ock | -0.093 |
ams | -0.093 |
ear | -0.081 |
Token | living |
Token ID | 2877 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
Ana | +0.030 |
Megan | +0.028 |
Pen | +0.028 |
Mir | +0.028 |
El | +0.028 |
Neg logit contributions | |
ock | -0.038 |
ets | -0.037 |
ercise | -0.036 |
vious | -0.033 |
off | -0.033 |
Token | room |
Token ID | 2119 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
Ana | +0.162 |
Pen | +0.160 |
stack | +0.154 |
comb | +0.153 |
El | +0.152 |
Neg logit contributions | |
ams | -0.169 |
ets | -0.167 |
ock | -0.152 |
les | -0.150 |
off | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Ana | +0.166 |
Pen | +0.162 |
Mir | +0.154 |
El | +0.151 |
Megan | +0.150 |
Neg logit contributions | |
ets | -0.088 |
ams | -0.079 |
ock | -0.074 |
ercise | -0.068 |
vious | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
gen | +0.011 |
Pen | +0.011 |
Ana | +0.010 |
stack | +0.010 |
Mir | +0.010 |
Neg logit contributions | |
ets | -0.008 |
ercise | -0.007 |
ams | -0.007 |
ly | -0.006 |
ear | -0.006 |
Token | went |
Token ID | 1816 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ets | +0.005 |
ercise | +0.005 |
ock | +0.005 |
ams | +0.005 |
ully | +0.005 |
Neg logit contributions | |
Ana | -0.006 |
Pen | -0.006 |
Megan | -0.005 |
plun | -0.005 |
Mir | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
Ana | +0.026 |
Pen | +0.025 |
gen | +0.024 |
Mir | +0.024 |
Megan | +0.024 |
Neg logit contributions | |
ets | -0.009 |
ercise | -0.008 |
ock | -0.007 |
ams | -0.007 |
ag | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
Ana | +0.017 |
Pen | +0.016 |
Mir | +0.016 |
plun | +0.015 |
Megan | +0.015 |
Neg logit contributions | |
ets | -0.016 |
ercise | -0.016 |
ams | -0.016 |
ock | -0.015 |
vious | -0.014 |
Token | see |
Token ID | 766 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
Ana | +0.020 |
Pen | +0.019 |
Jenkins | +0.018 |
Mir | +0.018 |
plun | +0.018 |
Neg logit contributions | |
ets | -0.018 |
ercise | -0.018 |
ock | -0.018 |
ams | -0.017 |
vious | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ets | +0.021 |
ams | +0.021 |
ercise | +0.020 |
ock | +0.020 |
les | +0.018 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.020 |
Mir | -0.018 |
plun | -0.018 |
Megan | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Ana | +0.054 |
Pen | +0.051 |
Mir | +0.048 |
Megan | +0.047 |
Jenkins | +0.047 |
Neg logit contributions | |
ets | -0.039 |
ercise | -0.038 |
ams | -0.038 |
ock | -0.036 |
vious | -0.034 |
Token | deep |
Token ID | 2769 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
Ana | +0.046 |
Pen | +0.044 |
Mir | +0.042 |
Megan | +0.042 |
El | +0.040 |
Neg logit contributions | |
ets | -0.039 |
ercise | -0.039 |
ock | -0.039 |
ams | -0.038 |
vious | -0.035 |
Token | pit |
Token ID | 6028 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
Ana | +0.091 |
Pen | +0.087 |
Mir | +0.081 |
Megan | +0.080 |
El | +0.078 |
Neg logit contributions | |
ets | -0.102 |
ercise | -0.101 |
ams | -0.101 |
ock | -0.096 |
vious | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
Ana | +0.213 |
Pen | +0.206 |
Mir | +0.195 |
Megan | +0.192 |
El | +0.189 |
Neg logit contributions | |
ets | -0.140 |
ams | -0.137 |
ercise | -0.134 |
ock | -0.129 |
vious | -0.115 |
Token | |
Token ID | 220 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
ams | +0.018 |
ercise | +0.017 |
ets | +0.017 |
ear | +0.015 |
ock | +0.015 |
Neg logit contributions | |
Ana | -0.027 |
gen | -0.026 |
Pen | -0.025 |
plun | -0.025 |
teaspoon | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ams | +0.018 |
ets | +0.018 |
ercise | +0.018 |
ock | +0.017 |
ear | +0.016 |
Neg logit contributions | |
Ana | -0.025 |
Pen | -0.024 |
gen | -0.024 |
plun | -0.022 |
Megan | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
ams | +0.023 |
ock | +0.022 |
ercise | +0.022 |
ets | +0.021 |
ear | +0.021 |
Neg logit contributions | |
Ana | -0.035 |
Pen | -0.033 |
gen | -0.033 |
stack | -0.032 |
plun | -0.032 |
Token | Mike |
Token ID | 16073 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ams | +0.026 |
ercise | +0.025 |
ets | +0.024 |
ock | +0.024 |
ear | +0.022 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.024 |
gen | -0.023 |
Mir | -0.023 |
plun | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ams | +0.001 |
ercise | +0.001 |
ets | +0.001 |
ock | +0.001 |
vious | +0.001 |
Neg logit contributions | |
Ana | -0.001 |
Pen | -0.001 |
El | -0.001 |
plun | -0.001 |
stack | -0.001 |
Token | loud |
Token ID | 7812 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
stack | +0.023 |
Megan | +0.022 |
Pen | +0.022 |
Jenkins | +0.022 |
Ana | +0.022 |
Neg logit contributions | |
ock | -0.016 |
ets | -0.014 |
ercise | -0.014 |
ag | -0.013 |
ly | -0.013 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
Ana | +0.010 |
Pen | +0.009 |
Megan | +0.009 |
Jenkins | +0.009 |
Lopez | +0.009 |
Neg logit contributions | |
ock | -0.011 |
ets | -0.011 |
ercise | -0.011 |
ams | -0.010 |
ag | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
Ana | +0.093 |
Pen | +0.090 |
Mir | +0.085 |
Megan | +0.085 |
El | +0.084 |
Neg logit contributions | |
ercise | -0.056 |
ets | -0.055 |
ams | -0.055 |
ock | -0.051 |
isdom | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
Ana | +0.146 |
Pen | +0.139 |
Megan | +0.131 |
Mir | +0.130 |
gen | +0.130 |
Neg logit contributions | |
ercise | -0.106 |
ets | -0.106 |
ock | -0.103 |
ams | -0.102 |
vious | -0.089 |
Token | living |
Token ID | 2877 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
Ana | +0.042 |
Pen | +0.039 |
Megan | +0.038 |
Mil | +0.038 |
El | +0.038 |
Neg logit contributions | |
ets | -0.039 |
ercise | -0.039 |
ock | -0.038 |
ams | -0.035 |
weet | -0.035 |
Token | room |
Token ID | 2119 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Ana | +0.171 |
Pen | +0.168 |
comb | +0.167 |
Stev | +0.162 |
El | +0.160 |
Neg logit contributions | |
ams | -0.159 |
ets | -0.154 |
les | -0.135 |
ock | -0.133 |
off | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Ana | +0.174 |
Pen | +0.167 |
El | +0.158 |
Mir | +0.157 |
Megan | +0.156 |
Neg logit contributions | |
ets | -0.085 |
ams | -0.078 |
ock | -0.073 |
ercise | -0.065 |
vious | -0.061 |
Token | He |
Token ID | 679 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Ana | +0.073 |
Pen | +0.071 |
El | +0.069 |
gen | +0.067 |
teaspoon | +0.067 |
Neg logit contributions | |
ets | -0.020 |
ams | -0.020 |
ercise | -0.019 |
ear | -0.018 |
isdom | -0.016 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Ana | +0.061 |
stack | +0.060 |
Pen | +0.060 |
Lopez | +0.057 |
Jenkins | +0.057 |
Neg logit contributions | |
ets | -0.052 |
ams | -0.051 |
ercise | -0.051 |
ock | -0.047 |
aw | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
ets | +0.005 |
ercise | +0.005 |
ams | +0.005 |
ock | +0.004 |
ear | +0.004 |
Neg logit contributions | |
Ana | -0.012 |
Pen | -0.011 |
Mir | -0.011 |
gen | -0.011 |
Megan | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
ets | +0.033 |
ercise | +0.033 |
ams | +0.032 |
ock | +0.030 |
vious | +0.027 |
Neg logit contributions | |
Ana | -0.054 |
Pen | -0.052 |
Mir | -0.050 |
Megan | -0.049 |
gen | -0.049 |
Token | gro |
Token ID | 7128 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ercise | +0.060 |
ets | +0.057 |
ams | +0.056 |
ock | +0.053 |
pads | +0.051 |
Neg logit contributions | |
Ana | -0.068 |
gen | -0.068 |
Pen | -0.067 |
plun | -0.066 |
Mir | -0.064 |
Token | oving |
Token ID | 5165 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Ana | +0.004 |
Pen | +0.004 |
Mir | +0.004 |
Megan | +0.004 |
El | +0.004 |
Neg logit contributions | |
ercise | -0.003 |
ets | -0.003 |
ams | -0.003 |
ock | -0.003 |
isdom | -0.003 |
Token | around |
Token ID | 1088 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ets | +0.014 |
ercise | +0.014 |
ams | +0.014 |
ock | +0.013 |
ear | +0.011 |
Neg logit contributions | |
Ana | -0.024 |
Pen | -0.023 |
gen | -0.022 |
Mir | -0.022 |
plun | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Ana | +0.076 |
gen | +0.076 |
Pen | +0.074 |
Mir | +0.073 |
plun | +0.072 |
Neg logit contributions | |
ets | -0.037 |
ock | -0.032 |
ams | -0.032 |
ercise | -0.031 |
ear | -0.028 |
Token | living |
Token ID | 2877 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
Ana | +0.048 |
Pen | +0.045 |
Mir | +0.045 |
Megan | +0.044 |
El | +0.043 |
Neg logit contributions | |
ets | -0.056 |
ercise | -0.055 |
ams | -0.054 |
ock | -0.053 |
vious | -0.049 |
Token | room |
Token ID | 2119 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
Ana | +0.160 |
Pen | +0.159 |
Mir | +0.152 |
Stev | +0.147 |
gen | +0.146 |
Neg logit contributions | |
ams | -0.186 |
ets | -0.185 |
les | -0.162 |
ercise | -0.158 |
ock | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
Ana | +0.167 |
Pen | +0.164 |
Mir | +0.158 |
gen | +0.154 |
plun | +0.152 |
Neg logit contributions | |
ets | -0.095 |
ams | -0.083 |
ock | -0.076 |
ercise | -0.074 |
vious | -0.068 |
Token | And |
Token ID | 843 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ets | +0.006 |
ercise | +0.006 |
ams | +0.006 |
ock | +0.006 |
isdom | +0.006 |
Neg logit contributions | |
Ana | -0.009 |
gen | -0.009 |
Pen | -0.008 |
plun | -0.008 |
Mir | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
ets | +0.031 |
ams | +0.030 |
ercise | +0.030 |
ock | +0.028 |
ear | +0.025 |
Neg logit contributions | |
Ana | -0.041 |
Pen | -0.040 |
plun | -0.038 |
Mir | -0.038 |
gen | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ets | +0.023 |
ercise | +0.022 |
ams | +0.022 |
ock | +0.021 |
vious | +0.019 |
Neg logit contributions | |
Ana | -0.027 |
Pen | -0.026 |
Mir | -0.025 |
plun | -0.025 |
gen | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
Ana | +0.054 |
Pen | +0.051 |
Megan | +0.048 |
Jenkins | +0.048 |
El | +0.048 |
Neg logit contributions | |
ets | -0.034 |
ercise | -0.034 |
ams | -0.032 |
ock | -0.030 |
ear | -0.027 |
Token | big |
Token ID | 1263 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Ana | +0.087 |
Pen | +0.086 |
El | +0.084 |
Megan | +0.083 |
Mir | +0.079 |
Neg logit contributions | |
ercise | -0.059 |
ets | -0.056 |
ock | -0.052 |
poems | -0.050 |
ams | -0.050 |
Token | box |
Token ID | 3091 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Ana | +0.046 |
Pen | +0.044 |
Megan | +0.042 |
El | +0.041 |
Mir | +0.040 |
Neg logit contributions | |
ets | -0.051 |
ercise | -0.051 |
ams | -0.049 |
ock | -0.048 |
isdom | -0.046 |
Token | in |
Token ID | 287 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
Ana | +0.094 |
Pen | +0.090 |
Mir | +0.086 |
Megan | +0.085 |
El | +0.085 |
Neg logit contributions | |
ets | -0.066 |
ams | -0.064 |
ercise | -0.064 |
ock | -0.061 |
vious | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Ana | +0.130 |
Pen | +0.125 |
plun | +0.118 |
Megan | +0.117 |
El | +0.117 |
Neg logit contributions | |
ams | -0.086 |
ercise | -0.083 |
ets | -0.083 |
ock | -0.082 |
ear | -0.072 |
Token | living |
Token ID | 2877 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
Ana | +0.027 |
Pen | +0.026 |
El | +0.024 |
Megan | +0.024 |
Mir | +0.023 |
Neg logit contributions | |
ets | -0.036 |
ercise | -0.036 |
ams | -0.035 |
ock | -0.033 |
off | -0.031 |
Token | room |
Token ID | 2119 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Ana | +0.150 |
Pen | +0.147 |
Megan | +0.136 |
El | +0.135 |
stack | +0.129 |
Neg logit contributions | |
ams | -0.200 |
ets | -0.196 |
ercise | -0.181 |
ock | -0.176 |
off | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Ana | +0.147 |
Pen | +0.141 |
plun | +0.134 |
Mir | +0.134 |
El | +0.134 |
Neg logit contributions | |
ets | -0.091 |
ams | -0.088 |
ercise | -0.080 |
ock | -0.078 |
ear | -0.072 |
Token | It |
Token ID | 632 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.042 |
Megan | +0.040 |
plun | +0.040 |
gen | +0.039 |
Neg logit contributions | |
ercise | -0.041 |
ets | -0.040 |
ams | -0.040 |
ock | -0.037 |
ear | -0.036 |
Token | has |
Token ID | 468 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Ana | +0.027 |
Jenkins | +0.026 |
Pen | +0.026 |
Megan | +0.026 |
Lopez | +0.025 |
Neg logit contributions | |
ets | -0.021 |
ercise | -0.019 |
ams | -0.018 |
elling | -0.017 |
ock | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
ets | +0.013 |
ercise | +0.013 |
ams | +0.013 |
ock | +0.012 |
isdom | +0.011 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.014 |
Megan | -0.013 |
Mir | -0.013 |
El | -0.013 |
Token | ice |
Token ID | 4771 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Ana | +0.032 |
Pen | +0.029 |
Mir | +0.028 |
Megan | +0.028 |
El | +0.028 |
Neg logit contributions | |
ercise | -0.037 |
ets | -0.036 |
ams | -0.036 |
ock | -0.035 |
vious | -0.032 |
Token | cream |
Token ID | 8566 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
Ana | +0.065 |
Pen | +0.062 |
Mir | +0.059 |
El | +0.058 |
Megan | +0.058 |
Neg logit contributions | |
ams | -0.054 |
ets | -0.053 |
ercise | -0.053 |
ock | -0.050 |
vious | -0.045 |
Token | out |
Token ID | 503 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
Ana | +0.113 |
Pen | +0.107 |
Mir | +0.102 |
El | +0.102 |
Megan | +0.100 |
Neg logit contributions | |
ets | -0.086 |
ams | -0.086 |
ercise | -0.084 |
ock | -0.081 |
vious | -0.073 |
Token | of |
Token ID | 286 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
Ana | +0.172 |
Pen | +0.165 |
Mir | +0.157 |
Megan | +0.157 |
El | +0.155 |
Neg logit contributions | |
ercise | -0.113 |
ets | -0.108 |
ams | -0.108 |
ock | -0.101 |
isdom | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Ana | +0.081 |
Pen | +0.077 |
El | +0.072 |
Mir | +0.071 |
plun | +0.071 |
Neg logit contributions | |
ams | -0.052 |
ercise | -0.049 |
ets | -0.048 |
ock | -0.047 |
isdom | -0.041 |
Token | freezer |
Token ID | 30967 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
Ana | +0.033 |
Pen | +0.030 |
Mir | +0.028 |
El | +0.028 |
Megan | +0.028 |
Neg logit contributions | |
ams | -0.046 |
ets | -0.046 |
ercise | -0.045 |
ock | -0.043 |
vious | -0.040 |
Token | again |
Token ID | 757 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
Ana | +0.225 |
Pen | +0.217 |
El | +0.206 |
Mir | +0.204 |
Megan | +0.199 |
Neg logit contributions | |
ets | -0.128 |
ams | -0.126 |
ock | -0.110 |
ercise | -0.109 |
vious | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
Ana | +0.027 |
Pen | +0.026 |
Mir | +0.025 |
Megan | +0.024 |
El | +0.024 |
Neg logit contributions | |
ercise | -0.022 |
ets | -0.022 |
ams | -0.022 |
ock | -0.021 |
isdom | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Ana | +0.025 |
Pen | +0.024 |
plun | +0.024 |
gen | +0.023 |
Megan | +0.023 |
Neg logit contributions | |
ets | -0.020 |
ams | -0.020 |
ercise | -0.019 |
ock | -0.018 |
ear | -0.017 |
Token | also |
Token ID | 635 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.012 |
Mir | +0.011 |
plun | +0.011 |
Megan | +0.011 |
Neg logit contributions | |
ets | -0.009 |
ercise | -0.009 |
ams | -0.009 |
ock | -0.008 |
vious | -0.008 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ets | +0.062 |
ercise | +0.062 |
ams | +0.060 |
ock | +0.055 |
vious | +0.052 |
Neg logit contributions | |
Ana | -0.097 |
Pen | -0.093 |
Megan | -0.088 |
Mir | -0.088 |
El | -0.087 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Ana | +0.022 |
Pen | +0.021 |
Mir | +0.019 |
Megan | +0.019 |
El | +0.019 |
Neg logit contributions | |
ercise | -0.021 |
ets | -0.021 |
ams | -0.021 |
ock | -0.020 |
isdom | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Ana | +0.008 |
Pen | +0.008 |
Mir | +0.007 |
Megan | +0.007 |
El | +0.007 |
Neg logit contributions | |
ets | -0.007 |
ercise | -0.007 |
ams | -0.007 |
ock | -0.006 |
vious | -0.006 |
Token | came |
Token ID | 1625 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
ock | +0.036 |
ets | +0.034 |
ams | +0.032 |
ly | +0.031 |
ercise | +0.031 |
Neg logit contributions | |
stack | -0.058 |
comb | -0.055 |
fire | -0.053 |
Lopez | -0.052 |
Jenkins | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
Ana | +0.103 |
gen | +0.103 |
Pen | +0.100 |
stack | +0.099 |
Megan | +0.096 |
Neg logit contributions | |
ets | -0.040 |
ock | -0.039 |
ams | -0.039 |
ercise | -0.036 |
ear | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
stack | +0.160 |
Ana | +0.157 |
comb | +0.152 |
ider | +0.150 |
Pen | +0.149 |
Neg logit contributions | |
ock | -0.068 |
ercise | -0.068 |
ear | -0.063 |
ets | -0.061 |
off | -0.060 |
Token | living |
Token ID | 2877 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
Ana | +0.052 |
Pen | +0.048 |
El | +0.048 |
Megan | +0.048 |
Mil | +0.047 |
Neg logit contributions | |
ercise | -0.052 |
ets | -0.051 |
ock | -0.050 |
off | -0.048 |
vious | -0.046 |
Token | room |
Token ID | 2119 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
comb | +0.170 |
Pen | +0.167 |
stack | +0.167 |
Ana | +0.166 |
El | +0.161 |
Neg logit contributions | |
ams | -0.156 |
ets | -0.148 |
off | -0.137 |
les | -0.136 |
ock | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
Ana | +0.174 |
Pen | +0.170 |
El | +0.162 |
Mir | +0.162 |
gen | +0.158 |
Neg logit contributions | |
ets | -0.079 |
ams | -0.071 |
ock | -0.065 |
ercise | -0.058 |
vious | -0.057 |
Token | She |
Token ID | 1375 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Ana | +0.067 |
gen | +0.065 |
Pen | +0.065 |
El | +0.062 |
plun | +0.060 |
Neg logit contributions | |
ercise | -0.035 |
ets | -0.035 |
ams | -0.031 |
vious | -0.031 |
elling | -0.031 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Ana | +0.065 |
Pen | +0.064 |
stack | +0.064 |
comb | +0.063 |
Lopez | +0.062 |
Neg logit contributions | |
ams | -0.039 |
ercise | -0.039 |
ets | -0.038 |
ock | -0.036 |
les | -0.033 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Ana | +0.030 |
Pen | +0.030 |
El | +0.027 |
Megan | +0.027 |
Mir | +0.027 |
Neg logit contributions | |
ets | -0.023 |
ams | -0.023 |
ercise | -0.023 |
ock | -0.023 |
vious | -0.021 |
Token | ily |
Token ID | 813 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Ana | +0.033 |
Pen | +0.032 |
Mir | +0.029 |
El | +0.029 |
Megan | +0.029 |
Neg logit contributions | |
ets | -0.036 |
ercise | -0.035 |
ams | -0.035 |
ock | -0.034 |
vious | -0.031 |
Token | ran |
Token ID | 4966 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
Ana | +0.036 |
Pen | +0.035 |
stack | +0.034 |
plun | +0.034 |
Mir | +0.034 |
Neg logit contributions | |
ercise | -0.027 |
ets | -0.027 |
ams | -0.026 |
vious | -0.024 |
ock | -0.024 |
Token | back |
Token ID | 736 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ets | +0.001 |
ercise | +0.001 |
ams | +0.001 |
ock | +0.001 |
ear | +0.001 |
Neg logit contributions | |
Ana | -0.002 |
Pen | -0.002 |
Mir | -0.002 |
gen | -0.002 |
El | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
Ana | +0.045 |
gen | +0.045 |
Pen | +0.044 |
plun | +0.043 |
stack | +0.043 |
Neg logit contributions | |
ets | -0.012 |
ams | -0.012 |
ercise | -0.011 |
ock | -0.010 |
ear | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
gen | +0.147 |
fire | +0.146 |
igor | +0.142 |
ider | +0.139 |
comb | +0.138 |
Neg logit contributions | |
ock | -0.039 |
ercise | -0.035 |
yours | -0.035 |
isdom | -0.034 |
ossible | -0.034 |
Token | cabinet |
Token ID | 13447 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
Ana | +0.030 |
Pen | +0.029 |
El | +0.029 |
Mir | +0.028 |
Mil | +0.028 |
Neg logit contributions | |
ercise | -0.031 |
ets | -0.030 |
off | -0.027 |
ock | -0.027 |
vious | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
Ana | +0.256 |
Pen | +0.249 |
El | +0.238 |
Mir | +0.238 |
Megan | +0.238 |
Neg logit contributions | |
ets | -0.090 |
ams | -0.084 |
ercise | -0.078 |
ock | -0.075 |
vious | -0.067 |
Token | looked |
Token ID | 3114 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
ets | +0.065 |
ercise | +0.064 |
ams | +0.060 |
pads | +0.053 |
vious | +0.052 |
Neg logit contributions | |
Pen | -0.083 |
Ana | -0.083 |
Jenkins | -0.082 |
Lopez | -0.080 |
plun | -0.080 |
Token | again |
Token ID | 757 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Ana | +0.003 |
Pen | +0.003 |
Megan | +0.003 |
Mir | +0.003 |
El | +0.003 |
Neg logit contributions | |
ercise | -0.002 |
ams | -0.002 |
ets | -0.001 |
ock | -0.001 |
isdom | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ercise | +0.004 |
ets | +0.004 |
ams | +0.004 |
ock | +0.003 |
vious | +0.003 |
Neg logit contributions | |
Ana | -0.004 |
Pen | -0.004 |
Mir | -0.004 |
Megan | -0.004 |
El | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
gen | +0.046 |
Pen | +0.045 |
Ana | +0.045 |
stack | +0.043 |
plun | +0.042 |
Neg logit contributions | |
ets | -0.030 |
ercise | -0.029 |
ear | -0.027 |
isdom | -0.026 |
ams | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Ana | +0.017 |
Pen | +0.017 |
gen | +0.016 |
Megan | +0.016 |
Mir | +0.016 |
Neg logit contributions | |
ets | -0.007 |
ams | -0.006 |
ock | -0.006 |
ercise | -0.006 |
ear | -0.005 |
Token | found |
Token ID | 1043 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ets | +0.060 |
ams | +0.056 |
ercise | +0.055 |
ock | +0.049 |
vious | +0.045 |
Neg logit contributions | |
stack | -0.092 |
Pen | -0.092 |
Jenkins | -0.090 |
Ana | -0.089 |
Lopez | -0.088 |
Token | them |
Token ID | 606 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
ets | +0.002 |
ercise | +0.002 |
ock | +0.002 |
ams | +0.002 |
elling | +0.002 |
Neg logit contributions | |
Ana | -0.004 |
Pen | -0.004 |
Jenkins | -0.004 |
Megan | -0.004 |
stack | -0.004 |
Token | behind |
Token ID | 2157 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Ana | +0.013 |
Pen | +0.013 |
Mir | +0.013 |
Mil | +0.012 |
gen | +0.012 |
Neg logit contributions | |
ets | -0.008 |
ams | -0.007 |
ercise | -0.007 |
ock | -0.007 |
ag | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Ana | +0.055 |
Pen | +0.052 |
Mir | +0.051 |
gen | +0.051 |
Mil | +0.049 |
Neg logit contributions | |
ets | -0.026 |
ock | -0.024 |
ams | -0.024 |
ercise | -0.023 |
les | -0.020 |
Token | cabinet |
Token ID | 13447 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
Pen | +0.032 |
Ana | +0.032 |
Megan | +0.030 |
Mir | +0.030 |
El | +0.029 |
Neg logit contributions | |
ets | -0.044 |
ock | -0.043 |
les | -0.038 |
ercise | -0.038 |
ams | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Ana | +0.255 |
Pen | +0.253 |
Mei | +0.239 |
El | +0.239 |
Stev | +0.238 |
Neg logit contributions | |
ets | -0.089 |
ams | -0.070 |
ock | -0.055 |
vious | -0.054 |
aw | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Ana | +0.052 |
Pen | +0.051 |
gen | +0.050 |
Megan | +0.048 |
El | +0.047 |
Neg logit contributions | |
ets | -0.044 |
ercise | -0.043 |
ams | -0.041 |
ock | -0.038 |
vious | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Pen | +0.063 |
stack | +0.063 |
Ana | +0.062 |
Lopez | +0.061 |
drown | +0.060 |
Neg logit contributions | |
ams | -0.044 |
ets | -0.042 |
ercise | -0.042 |
ock | -0.039 |
les | -0.037 |
Token | not |
Token ID | 407 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Ana | +0.055 |
stack | +0.052 |
El | +0.052 |
Pen | +0.051 |
plun | +0.050 |
Neg logit contributions | |
ams | -0.039 |
ag | -0.037 |
about | -0.037 |
ets | -0.036 |
ercise | -0.036 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ams | +0.004 |
ets | +0.003 |
ock | +0.003 |
ag | +0.003 |
weet | +0.003 |
Neg logit contributions | |
stack | -0.006 |
Ana | -0.006 |
Pen | -0.006 |
El | -0.006 |
Me | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ercise | +0.077 |
ams | +0.075 |
ets | +0.074 |
ock | +0.072 |
isdom | +0.067 |
Neg logit contributions | |
Ana | -0.093 |
Pen | -0.090 |
Mir | -0.085 |
El | -0.083 |
Megan | -0.083 |
Token | She |
Token ID | 1375 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ercise | +0.017 |
ets | +0.017 |
ams | +0.016 |
ock | +0.015 |
isdom | +0.015 |
Neg logit contributions | |
Ana | -0.018 |
Pen | -0.018 |
gen | -0.017 |
Mir | -0.017 |
plun | -0.017 |
Token | gathered |
Token ID | 9272 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.012 |
Megan | +0.011 |
Mir | +0.011 |
plun | +0.011 |
Neg logit contributions | |
ercise | -0.011 |
ets | -0.011 |
ams | -0.011 |
ock | -0.010 |
isdom | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
ercise | +0.051 |
ets | +0.051 |
ams | +0.051 |
ock | +0.048 |
isdom | +0.044 |
Neg logit contributions | |
Ana | -0.068 |
Pen | -0.065 |
Mir | -0.062 |
Megan | -0.062 |
El | -0.061 |
Token | hammer |
Token ID | 15554 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ercise | +0.014 |
ets | +0.014 |
ams | +0.013 |
ock | +0.013 |
isdom | +0.012 |
Neg logit contributions | |
Ana | -0.014 |
Pen | -0.014 |
Megan | -0.013 |
Mir | -0.013 |
El | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
ercise | +0.026 |
ams | +0.025 |
ets | +0.024 |
ock | +0.022 |
isdom | +0.022 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.038 |
Mir | -0.037 |
El | -0.037 |
Megan | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ets | +0.122 |
ercise | +0.122 |
ams | +0.121 |
ock | +0.116 |
isdom | +0.107 |
Neg logit contributions | |
Ana | -0.115 |
Pen | -0.110 |
Mir | -0.104 |
El | -0.101 |
Megan | -0.101 |
Token | toy |
Token ID | 13373 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Ana | +0.004 |
Pen | +0.004 |
Megan | +0.003 |
Mir | +0.003 |
gen | +0.003 |
Neg logit contributions | |
ercise | -0.004 |
ams | -0.004 |
ets | -0.004 |
isdom | -0.004 |
ock | -0.004 |
Token | tool |
Token ID | 2891 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
ercise | +0.012 |
ets | +0.012 |
ams | +0.011 |
ock | +0.011 |
ully | +0.010 |
Neg logit contributions | |
Ana | -0.012 |
Pen | -0.011 |
Megan | -0.011 |
Mir | -0.010 |
Mei | -0.010 |
Token | box |
Token ID | 3524 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.012 |
Megan | +0.011 |
Mir | +0.011 |
Mei | +0.011 |
Neg logit contributions | |
ets | -0.009 |
ercise | -0.009 |
ams | -0.009 |
ock | -0.008 |
pads | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Ana | +0.022 |
Pen | +0.022 |
Mir | +0.021 |
Megan | +0.020 |
Mei | +0.020 |
Neg logit contributions | |
ets | -0.013 |
ams | -0.013 |
ercise | -0.012 |
ock | -0.011 |
isdom | -0.010 |
Token | Christmas |
Token ID | 6786 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ercise | +0.035 |
ets | +0.033 |
ams | +0.033 |
ock | +0.029 |
isdom | +0.029 |
Neg logit contributions | |
Ana | -0.054 |
Pen | -0.053 |
Megan | -0.050 |
Mir | -0.050 |
gen | -0.050 |
Token | ever |
Token ID | 1683 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Ana | +0.011 |
Pen | +0.011 |
Mir | +0.010 |
Megan | +0.010 |
El | +0.010 |
Neg logit contributions | |
ets | -0.008 |
ercise | -0.008 |
ams | -0.008 |
ock | -0.008 |
isdom | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
ercise | +0.097 |
ams | +0.084 |
isdom | +0.084 |
ock | +0.081 |
ully | +0.081 |
Neg logit contributions | |
Ana | -0.057 |
Pen | -0.056 |
Megan | -0.053 |
Ell | -0.052 |
Mir | -0.051 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
plun | +0.020 |
Megan | +0.019 |
gen | +0.019 |
Neg logit contributions | |
ets | -0.020 |
ercise | -0.020 |
ams | -0.020 |
ock | -0.018 |
isdom | -0.017 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Ana | +0.048 |
Pen | +0.044 |
Mir | +0.044 |
stack | +0.044 |
gen | +0.044 |
Neg logit contributions | |
ock | -0.045 |
ets | -0.045 |
ams | -0.045 |
ercise | -0.044 |
les | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
ercise | +0.026 |
ets | +0.026 |
ams | +0.025 |
ock | +0.024 |
isdom | +0.022 |
Neg logit contributions | |
Ana | -0.041 |
Pen | -0.040 |
Mir | -0.038 |
Megan | -0.038 |
El | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ets | +0.135 |
ercise | +0.129 |
ams | +0.125 |
ock | +0.125 |
elling | +0.115 |
Neg logit contributions | |
Ana | -0.121 |
Pen | -0.119 |
Mir | -0.113 |
Megan | -0.111 |
El | -0.109 |
Token | were |
Token ID | 547 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ets | +0.049 |
ercise | +0.049 |
ams | +0.049 |
ock | +0.046 |
vious | +0.042 |
Neg logit contributions | |
Ana | -0.055 |
Pen | -0.052 |
Mir | -0.050 |
Megan | -0.049 |
plun | -0.049 |
Token | having |
Token ID | 1719 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ercise | +0.011 |
ets | +0.010 |
ams | +0.010 |
ock | +0.010 |
isdom | +0.009 |
Neg logit contributions | |
Ana | -0.009 |
Pen | -0.009 |
Mir | -0.008 |
Megan | -0.008 |
El | -0.008 |
Token | lunch |
Token ID | 9965 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ercise | +0.059 |
ets | +0.058 |
ams | +0.057 |
ock | +0.055 |
isdom | +0.052 |
Neg logit contributions | |
Ana | -0.052 |
Pen | -0.050 |
Mir | -0.047 |
Megan | -0.047 |
El | -0.046 |
Token | with |
Token ID | 351 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Ana | +0.023 |
Pen | +0.022 |
Mir | +0.021 |
Megan | +0.020 |
El | +0.020 |
Neg logit contributions | |
ets | -0.017 |
ercise | -0.017 |
ams | -0.017 |
ock | -0.016 |
isdom | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Ana | +0.049 |
Pen | +0.047 |
plun | +0.045 |
Mir | +0.044 |
El | +0.044 |
Neg logit contributions | |
ets | -0.037 |
ams | -0.036 |
ercise | -0.036 |
ock | -0.034 |
ear | -0.031 |
Token | all |
Token ID | 477 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Ana | +0.062 |
Pen | +0.059 |
Mir | +0.057 |
Megan | +0.056 |
El | +0.056 |
Neg logit contributions | |
ercise | -0.041 |
ets | -0.041 |
ams | -0.040 |
ock | -0.038 |
isdom | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ercise | +0.090 |
ams | +0.086 |
ets | +0.084 |
ock | +0.081 |
isdom | +0.077 |
Neg logit contributions | |
Ana | -0.084 |
Pen | -0.082 |
Megan | -0.077 |
Mir | -0.076 |
El | -0.074 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Ana | +0.013 |
Pen | +0.013 |
Mir | +0.012 |
Megan | +0.012 |
El | +0.012 |
Neg logit contributions | |
ercise | -0.015 |
ets | -0.015 |
ams | -0.015 |
ock | -0.014 |
isdom | -0.013 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.041 |
Mir | +0.040 |
Megan | +0.039 |
gen | +0.039 |
Neg logit contributions | |
ets | -0.050 |
ock | -0.049 |
ercise | -0.049 |
ams | -0.049 |
vious | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
ercise | +0.046 |
ets | +0.045 |
ams | +0.045 |
ock | +0.043 |
isdom | +0.040 |
Neg logit contributions | |
Ana | -0.040 |
Pen | -0.039 |
Mir | -0.037 |
Megan | -0.036 |
El | -0.035 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ets | +0.166 |
ercise | +0.156 |
ams | +0.155 |
ock | +0.155 |
elling | +0.144 |
Neg logit contributions | |
Ana | -0.111 |
Pen | -0.110 |
Mir | -0.103 |
Megan | -0.103 |
Ell | -0.103 |
Token | are |
Token ID | 389 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ercise | +0.065 |
ams | +0.065 |
ets | +0.064 |
ock | +0.062 |
isdom | +0.059 |
Neg logit contributions | |
Ana | -0.057 |
Pen | -0.055 |
El | -0.052 |
Megan | -0.051 |
Mir | -0.051 |
Token | young |
Token ID | 1862 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ercise | +0.001 |
ets | +0.001 |
ock | +0.001 |
ams | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
Ana | -0.001 |
Pen | -0.001 |
Mir | -0.001 |
Megan | -0.001 |
Ell | -0.001 |
Token | twins |
Token ID | 20345 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
ams | +0.003 |
ets | +0.002 |
ercise | +0.002 |
ock | +0.002 |
isdom | +0.002 |
Neg logit contributions | |
Ana | -0.006 |
Pen | -0.005 |
plun | -0.005 |
Mir | -0.005 |
Megan | -0.005 |
Token | who |
Token ID | 508 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ets | +0.007 |
ams | +0.007 |
ercise | +0.007 |
ock | +0.006 |
isdom | +0.006 |
Neg logit contributions | |
Ana | -0.011 |
Pen | -0.010 |
Mir | -0.010 |
plun | -0.010 |
Megan | -0.010 |
Token | forg |
Token ID | 5784 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
ercise | +0.004 |
ets | +0.004 |
ams | +0.004 |
ock | +0.003 |
vious | +0.003 |
Neg logit contributions | |
Ana | -0.005 |
Pen | -0.005 |
Mir | -0.005 |
Megan | -0.004 |
El | -0.004 |
Token | ave |
Token ID | 1015 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ercise | +0.097 |
ams | +0.093 |
opl | +0.093 |
yours | +0.086 |
isdom | +0.086 |
Neg logit contributions | |
Ana | -0.112 |
plun | -0.111 |
sob | -0.106 |
slammed | -0.105 |
Pen | -0.102 |
Token | him |
Token ID | 683 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
ets | +0.019 |
ercise | +0.019 |
ams | +0.018 |
ock | +0.016 |
vious | +0.016 |
Neg logit contributions | |
Ana | -0.027 |
Pen | -0.026 |
Mir | -0.025 |
Megan | -0.025 |
Ell | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
Ana | +0.029 |
Pen | +0.028 |
Mir | +0.027 |
Jenkins | +0.026 |
Megan | +0.026 |
Neg logit contributions | |
ercise | -0.021 |
ams | -0.020 |
ets | -0.019 |
ock | -0.018 |
isdom | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ercise | +0.096 |
ams | +0.094 |
ets | +0.094 |
ock | +0.087 |
isdom | +0.082 |
Neg logit contributions | |
Ana | -0.115 |
Pen | -0.110 |
Megan | -0.103 |
Mir | -0.103 |
El | -0.102 |
Token | all |
Token ID | 477 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ercise | +0.048 |
ets | +0.048 |
ams | +0.047 |
ock | +0.045 |
isdom | +0.041 |
Neg logit contributions | |
Ana | -0.069 |
Pen | -0.066 |
Mir | -0.063 |
Megan | -0.062 |
El | -0.062 |
Token | played |
Token ID | 2826 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ercise | +0.120 |
ets | +0.118 |
ams | +0.117 |
ock | +0.113 |
isdom | +0.107 |
Neg logit contributions | |
Ana | -0.123 |
Pen | -0.117 |
Megan | -0.113 |
Ell | -0.111 |
El | -0.110 |
Token | together |
Token ID | 1978 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ercise | +0.005 |
ets | +0.005 |
ams | +0.005 |
ock | +0.005 |
isdom | +0.004 |
Neg logit contributions | |
Ana | -0.007 |
Pen | -0.007 |
Mir | -0.007 |
Megan | -0.007 |
El | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
ercise | +0.037 |
ets | +0.037 |
ams | +0.036 |
ock | +0.034 |
isdom | +0.031 |
Neg logit contributions | |
Ana | -0.046 |
Pen | -0.044 |
Mir | -0.042 |
Megan | -0.042 |
El | -0.041 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ercise | +0.019 |
ams | +0.019 |
ets | +0.019 |
ock | +0.018 |
isdom | +0.016 |
Neg logit contributions | |
Ana | -0.024 |
Pen | -0.023 |
Mir | -0.022 |
Megan | -0.022 |
El | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ercise | +0.038 |
ams | +0.037 |
ets | +0.036 |
ock | +0.035 |
isdom | +0.032 |
Neg logit contributions | |
Ana | -0.047 |
Pen | -0.046 |
Mir | -0.043 |
Megan | -0.042 |
El | -0.042 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Ana | +0.023 |
Pen | +0.021 |
El | +0.020 |
Mir | +0.020 |
Megan | +0.020 |
Neg logit contributions | |
ams | -0.026 |
ercise | -0.026 |
ets | -0.024 |
ock | -0.024 |
isdom | -0.023 |
Token | sat |
Token ID | 3332 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ercise | +0.055 |
ets | +0.055 |
ams | +0.055 |
ock | +0.052 |
vious | +0.047 |
Neg logit contributions | |
Ana | -0.066 |
Pen | -0.063 |
Mir | -0.060 |
Megan | -0.059 |
plun | -0.058 |
Token | on |
Token ID | 319 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Ana | +0.032 |
Pen | +0.031 |
Mir | +0.030 |
Megan | +0.029 |
El | +0.029 |
Neg logit contributions | |
ercise | -0.024 |
ams | -0.023 |
ets | -0.023 |
ock | -0.022 |
isdom | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Ana | +0.055 |
Pen | +0.052 |
Mir | +0.050 |
Megan | +0.050 |
El | +0.049 |
Neg logit contributions | |
ercise | -0.042 |
ams | -0.041 |
ets | -0.041 |
ock | -0.039 |
isdom | -0.036 |
Token | bench |
Token ID | 7624 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ercise | +0.048 |
ets | +0.048 |
ams | +0.048 |
ock | +0.046 |
isdom | +0.044 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.018 |
Mir | -0.016 |
Megan | -0.016 |
El | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
Ana | +0.092 |
Pen | +0.089 |
Mir | +0.086 |
Megan | +0.085 |
El | +0.084 |
Neg logit contributions | |
ets | -0.041 |
ams | -0.040 |
ercise | -0.039 |
ock | -0.036 |
isdom | -0.031 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ercise | +0.088 |
ams | +0.087 |
ets | +0.085 |
ock | +0.076 |
pads | +0.071 |
Neg logit contributions | |
Ana | -0.119 |
plun | -0.114 |
Pen | -0.113 |
gen | -0.112 |
Mir | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ercise | +0.025 |
ams | +0.025 |
ets | +0.025 |
ock | +0.023 |
isdom | +0.021 |
Neg logit contributions | |
Ana | -0.033 |
Pen | -0.031 |
Mir | -0.030 |
Megan | -0.029 |
El | -0.029 |
Token | big |
Token ID | 1263 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
ercise | +0.039 |
ets | +0.039 |
ams | +0.039 |
ock | +0.037 |
isdom | +0.034 |
Neg logit contributions | |
Ana | -0.041 |
Pen | -0.039 |
Mir | -0.037 |
Megan | -0.037 |
El | -0.037 |
Token | ice |
Token ID | 4771 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Ana | +0.002 |
Pen | +0.002 |
Megan | +0.001 |
Mir | +0.001 |
El | +0.001 |
Neg logit contributions | |
ets | -0.002 |
ercise | -0.002 |
ams | -0.002 |
ock | -0.002 |
isdom | -0.001 |
Token | cream |
Token ID | 8566 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Ana | +0.010 |
Pen | +0.010 |
Mir | +0.009 |
Megan | +0.009 |
El | +0.009 |
Neg logit contributions | |
ercise | -0.009 |
ets | -0.009 |
ams | -0.009 |
ock | -0.008 |
isdom | -0.008 |
Token | seen |
Token ID | 1775 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ercise | +0.111 |
ets | +0.106 |
ams | +0.105 |
ock | +0.101 |
isdom | +0.098 |
Neg logit contributions | |
Ana | -0.103 |
Pen | -0.098 |
Mir | -0.094 |
Megan | -0.093 |
Mil | -0.090 |
Token | snow |
Token ID | 6729 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ercise | +0.055 |
ets | +0.055 |
ams | +0.054 |
ock | +0.049 |
isdom | +0.048 |
Neg logit contributions | |
Ana | -0.053 |
Pen | -0.051 |
Mir | -0.048 |
El | -0.047 |
Megan | -0.047 |
Token | before |
Token ID | 878 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Ana | +0.060 |
Pen | +0.057 |
Megan | +0.054 |
Mir | +0.054 |
El | +0.053 |
Neg logit contributions | |
ock | -0.050 |
ets | -0.050 |
ams | -0.049 |
ercise | -0.048 |
les | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
Ana | +0.086 |
Pen | +0.082 |
gen | +0.079 |
Megan | +0.079 |
Mir | +0.078 |
Neg logit contributions | |
ets | -0.048 |
ams | -0.046 |
ercise | -0.046 |
ock | -0.045 |
isdom | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
Mir | +0.019 |
Megan | +0.018 |
El | +0.018 |
Neg logit contributions | |
ercise | -0.024 |
ets | -0.023 |
ams | -0.023 |
ock | -0.023 |
isdom | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ets | +0.022 |
ercise | +0.021 |
ams | +0.021 |
ock | +0.020 |
vious | +0.019 |
Neg logit contributions | |
Ana | -0.022 |
Pen | -0.021 |
Mir | -0.020 |
Megan | -0.019 |
El | -0.019 |
Token | They |
Token ID | 2990 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
ets | +0.015 |
ercise | +0.014 |
ams | +0.014 |
ock | +0.014 |
vious | +0.014 |
Neg logit contributions | |
Ana | -0.013 |
Pen | -0.012 |
Mir | -0.012 |
Megan | -0.011 |
El | -0.011 |
Token | drove |
Token ID | 10357 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
Mir | +0.019 |
plun | +0.019 |
Megan | +0.019 |
Neg logit contributions | |
ets | -0.017 |
ams | -0.017 |
ercise | -0.017 |
ock | -0.016 |
vious | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ercise | +0.029 |
ets | +0.028 |
ams | +0.028 |
ock | +0.026 |
isdom | +0.024 |
Neg logit contributions | |
Ana | -0.044 |
Pen | -0.042 |
Mir | -0.040 |
Megan | -0.040 |
El | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.043 |
Megan | +0.040 |
stack | +0.040 |
El | +0.040 |
Neg logit contributions | |
ets | -0.035 |
ercise | -0.035 |
ams | -0.033 |
ock | -0.033 |
ear | -0.029 |
Token | long |
Token ID | 890 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
ets | +0.001 |
ercise | +0.001 |
ams | +0.001 |
ock | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
Ana | -0.002 |
Pen | -0.001 |
Megan | -0.001 |
Mir | -0.001 |
El | -0.001 |
Token | could |
Token ID | 714 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Ana | +0.007 |
Pen | +0.006 |
Megan | +0.006 |
Mir | +0.006 |
Jenkins | +0.006 |
Neg logit contributions | |
ets | -0.005 |
ams | -0.005 |
ercise | -0.005 |
ock | -0.005 |
vious | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
Ana | +0.041 |
Pen | +0.039 |
Mir | +0.037 |
Megan | +0.037 |
El | +0.037 |
Neg logit contributions | |
ets | -0.029 |
ercise | -0.028 |
ams | -0.028 |
ock | -0.027 |
ear | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ets | +0.000 |
ercise | +0.000 |
ams | +0.000 |
ear | +0.000 |
pads | +0.000 |
Neg logit contributions | |
gen | -0.000 |
teaspoon | -0.000 |
Ana | -0.000 |
Pen | -0.000 |
plun | -0.000 |
Token | passed |
Token ID | 3804 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Ana | +0.007 |
Pen | +0.007 |
gen | +0.007 |
Jenkins | +0.007 |
Mir | +0.007 |
Neg logit contributions | |
ets | -0.006 |
ams | -0.006 |
ercise | -0.006 |
ock | -0.005 |
pads | -0.005 |
Token | many |
Token ID | 867 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ets | +0.031 |
ams | +0.030 |
ercise | +0.029 |
ock | +0.028 |
ear | +0.025 |
Neg logit contributions | |
Ana | -0.050 |
Pen | -0.048 |
gen | -0.048 |
plun | -0.047 |
stack | -0.047 |
Token | kids |
Token ID | 3988 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
ercise | +0.011 |
ams | +0.011 |
ets | +0.011 |
ock | +0.010 |
isdom | +0.010 |
Neg logit contributions | |
Ana | -0.019 |
Pen | -0.018 |
Mir | -0.017 |
Megan | -0.017 |
El | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ets | +0.013 |
ams | +0.012 |
ercise | +0.012 |
ock | +0.011 |
ear | +0.010 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.020 |
gen | -0.019 |
Mir | -0.019 |
plun | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
gen | +0.025 |
Pen | +0.025 |
Ana | +0.025 |
plun | +0.024 |
teaspoon | +0.023 |
Neg logit contributions | |
ets | -0.016 |
ercise | -0.015 |
ams | -0.015 |
ock | -0.013 |
ear | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Ana | +0.017 |
Pen | +0.017 |
Mir | +0.016 |
plun | +0.016 |
Megan | +0.016 |
Neg logit contributions | |
ets | -0.015 |
ercise | -0.014 |
ams | -0.014 |
ock | -0.014 |
vious | -0.013 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.042 |
plun | +0.041 |
gen | +0.040 |
stack | +0.040 |
Neg logit contributions | |
ams | -0.039 |
ets | -0.038 |
ercise | -0.036 |
ock | -0.034 |
weet | -0.032 |
Token | at |
Token ID | 379 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
ercise | +0.033 |
ets | +0.033 |
ams | +0.033 |
ock | +0.031 |
isdom | +0.028 |
Neg logit contributions | |
Ana | -0.042 |
Pen | -0.041 |
Mir | -0.039 |
Megan | -0.039 |
El | -0.038 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ercise | +0.023 |
ets | +0.023 |
ams | +0.022 |
ock | +0.021 |
isdom | +0.020 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.025 |
Mir | -0.024 |
Megan | -0.023 |
El | -0.023 |
Token | about |
Token ID | 546 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ercise | +0.041 |
ets | +0.037 |
ams | +0.035 |
vious | +0.034 |
isdom | +0.033 |
Neg logit contributions | |
Ana | -0.052 |
Pen | -0.050 |
Megan | -0.049 |
Mir | -0.049 |
Ell | -0.047 |
Token | their |
Token ID | 511 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Ana | +0.022 |
Pen | +0.021 |
Mir | +0.020 |
Megan | +0.020 |
plun | +0.019 |
Neg logit contributions | |
ercise | -0.018 |
ets | -0.017 |
ams | -0.017 |
ock | -0.016 |
isdom | -0.015 |
Token | dream |
Token ID | 4320 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Ana | +0.038 |
Pen | +0.036 |
Mir | +0.034 |
Megan | +0.034 |
El | +0.034 |
Neg logit contributions | |
ercise | -0.027 |
ets | -0.027 |
ams | -0.027 |
ock | -0.025 |
isdom | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ercise | +0.026 |
ams | +0.026 |
ets | +0.025 |
ock | +0.024 |
isdom | +0.022 |
Neg logit contributions | |
Ana | -0.032 |
Pen | -0.030 |
Mir | -0.029 |
Megan | -0.028 |
El | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Ana | +0.030 |
Pen | +0.029 |
plun | +0.029 |
gen | +0.029 |
El | +0.027 |
Neg logit contributions | |
ams | -0.022 |
ercise | -0.022 |
ets | -0.022 |
ear | -0.020 |
isdom | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ercise | +0.013 |
ams | +0.012 |
ets | +0.012 |
ock | +0.012 |
ear | +0.011 |
Neg logit contributions | |
Ana | -0.014 |
Pen | -0.013 |
Megan | -0.012 |
Mir | -0.012 |
plun | -0.012 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ercise | +0.005 |
ams | +0.005 |
ets | +0.005 |
ock | +0.005 |
ear | +0.004 |
Neg logit contributions | |
Ana | -0.008 |
Pen | -0.008 |
Mir | -0.007 |
El | -0.007 |
Megan | -0.007 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ets | +0.030 |
ams | +0.030 |
ock | +0.030 |
ercise | +0.030 |
les | +0.026 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.037 |
plun | -0.037 |
stack | -0.035 |
Mir | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ercise | +0.030 |
ets | +0.028 |
ams | +0.028 |
ock | +0.026 |
isdom | +0.025 |
Neg logit contributions | |
Ana | -0.041 |
Pen | -0.039 |
Mir | -0.038 |
El | -0.037 |
Megan | -0.036 |
Token | hugged |
Token ID | 41130 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
ercise | +0.050 |
ams | +0.048 |
ets | +0.048 |
ock | +0.045 |
isdom | +0.041 |
Neg logit contributions | |
Ana | -0.076 |
Pen | -0.072 |
plun | -0.072 |
Jenkins | -0.071 |
stack | -0.070 |
Token | trees |
Token ID | 7150 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ercise | +0.019 |
ets | +0.019 |
ams | +0.019 |
ock | +0.018 |
vious | +0.016 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.025 |
Mir | -0.024 |
Megan | -0.024 |
plun | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Ana | +0.014 |
Pen | +0.014 |
Mir | +0.013 |
El | +0.013 |
Megan | +0.013 |
Neg logit contributions | |
ercise | -0.013 |
ets | -0.012 |
ams | -0.012 |
ock | -0.012 |
isdom | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ercise | +0.044 |
ets | +0.043 |
ams | +0.043 |
ock | +0.040 |
isdom | +0.037 |
Neg logit contributions | |
Ana | -0.054 |
Pen | -0.052 |
Mir | -0.049 |
Megan | -0.049 |
El | -0.049 |
Token | noticed |
Token ID | 6810 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Ana | +0.014 |
Pen | +0.013 |
plun | +0.013 |
Mir | +0.012 |
gen | +0.012 |
Neg logit contributions | |
ercise | -0.015 |
ets | -0.014 |
ams | -0.014 |
ock | -0.013 |
isdom | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ets | +0.056 |
ercise | +0.055 |
ams | +0.054 |
ock | +0.050 |
isdom | +0.048 |
Neg logit contributions | |
Ana | -0.054 |
Pen | -0.052 |
El | -0.049 |
Mir | -0.049 |
Megan | -0.049 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Ana | +0.031 |
Pen | +0.031 |
Mir | +0.031 |
Megan | +0.030 |
El | +0.029 |
Neg logit contributions | |
ercise | -0.020 |
ock | -0.020 |
ams | -0.019 |
ets | -0.019 |
weet | -0.018 |
Token | hopping |
Token ID | 47153 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ercise | +0.010 |
ets | +0.010 |
ams | +0.009 |
ock | +0.009 |
isdom | +0.008 |
Neg logit contributions | |
Ana | -0.011 |
Pen | -0.011 |
Mir | -0.010 |
Megan | -0.010 |
El | -0.010 |
Token | around |
Token ID | 1088 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ercise | +0.030 |
ams | +0.030 |
ets | +0.029 |
isdom | +0.028 |
ock | +0.026 |
Neg logit contributions | |
Ana | -0.041 |
Pen | -0.040 |
El | -0.039 |
plun | -0.038 |
Megan | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Ana | +0.059 |
Pen | +0.058 |
Mir | +0.055 |
gen | +0.054 |
Megan | +0.054 |
Neg logit contributions | |
ercise | -0.031 |
ets | -0.031 |
ams | -0.030 |
ock | -0.029 |
ear | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ercise | +0.026 |
ets | +0.026 |
ams | +0.025 |
ock | +0.024 |
vious | +0.022 |
Neg logit contributions | |
Ana | -0.035 |
Pen | -0.034 |
Mir | -0.032 |
Megan | -0.032 |
gen | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Ana | +0.025 |
Pen | +0.024 |
Mir | +0.023 |
plun | +0.023 |
Megan | +0.022 |
Neg logit contributions | |
ercise | -0.028 |
ets | -0.027 |
ams | -0.027 |
ock | -0.025 |
isdom | -0.024 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Ana | +0.006 |
Pen | +0.006 |
stack | +0.006 |
plun | +0.006 |
Jenkins | +0.006 |
Neg logit contributions | |
ams | -0.006 |
ets | -0.006 |
ercise | -0.006 |
vious | -0.006 |
ear | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ercise | +0.030 |
ams | +0.029 |
ets | +0.028 |
ock | +0.025 |
isdom | +0.025 |
Neg logit contributions | |
Ana | -0.039 |
Pen | -0.037 |
El | -0.036 |
Mir | -0.035 |
Megan | -0.035 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Ana | +0.003 |
gen | +0.003 |
plun | +0.003 |
Pen | +0.003 |
Mir | +0.003 |
Neg logit contributions | |
ets | -0.002 |
ercise | -0.002 |
ams | -0.002 |
vious | -0.002 |
ear | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Ana | +0.051 |
Pen | +0.049 |
plun | +0.049 |
Megan | +0.047 |
Mir | +0.047 |
Neg logit contributions | |
ercise | -0.030 |
ams | -0.028 |
ets | -0.027 |
ock | -0.024 |
isdom | -0.024 |
Token | hunter |
Token ID | 19177 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Ana | +0.043 |
Pen | +0.042 |
Mir | +0.039 |
Megan | +0.038 |
El | +0.038 |
Neg logit contributions | |
ets | -0.045 |
ercise | -0.045 |
ams | -0.045 |
ock | -0.042 |
isdom | -0.039 |
Token | noticed |
Token ID | 6810 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.021 |
Megan | +0.020 |
Mir | +0.019 |
plun | +0.019 |
Neg logit contributions | |
ets | -0.019 |
ercise | -0.019 |
ams | -0.018 |
ock | -0.017 |
vious | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ercise | +0.017 |
ets | +0.016 |
ams | +0.016 |
ock | +0.016 |
isdom | +0.014 |
Neg logit contributions | |
Ana | -0.025 |
Pen | -0.024 |
Megan | -0.022 |
Mir | -0.022 |
plun | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
Ana | +0.052 |
Pen | +0.050 |
Mir | +0.048 |
Megan | +0.048 |
Mil | +0.046 |
Neg logit contributions | |
ets | -0.039 |
ercise | -0.038 |
ams | -0.038 |
ock | -0.036 |
ully | -0.034 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ercise | +0.072 |
ams | +0.069 |
ets | +0.066 |
ock | +0.063 |
vious | +0.059 |
Neg logit contributions | |
Ana | -0.098 |
Pen | -0.095 |
plun | -0.092 |
Megan | -0.091 |
Jenkins | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ercise | +0.041 |
ets | +0.041 |
ams | +0.040 |
ock | +0.038 |
isdom | +0.036 |
Neg logit contributions | |
Ana | -0.044 |
Pen | -0.042 |
Mir | -0.040 |
El | -0.040 |
Megan | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Ana | +0.009 |
Pen | +0.009 |
plun | +0.009 |
gen | +0.009 |
Megan | +0.009 |
Neg logit contributions | |
ercise | -0.007 |
ets | -0.007 |
ams | -0.007 |
ock | -0.006 |
ear | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
Ana | +0.020 |
Megan | +0.020 |
Pen | +0.019 |
stack | +0.019 |
El | +0.018 |
Neg logit contributions | |
ercise | -0.011 |
ock | -0.011 |
ams | -0.011 |
ets | -0.010 |
weet | -0.010 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ercise | +0.025 |
ams | +0.024 |
ock | +0.024 |
ets | +0.024 |
vious | +0.022 |
Neg logit contributions | |
Ana | -0.019 |
Pen | -0.019 |
Megan | -0.018 |
Mir | -0.017 |
El | -0.017 |
Token | named |
Token ID | 3706 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Ana | +0.027 |
Pen | +0.026 |
Mir | +0.025 |
Megan | +0.024 |
El | +0.024 |
Neg logit contributions | |
ercise | -0.027 |
ets | -0.027 |
ams | -0.026 |
ock | -0.025 |
vious | -0.023 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
ets | +0.045 |
ercise | +0.043 |
ams | +0.042 |
weet | +0.042 |
ock | +0.042 |
Neg logit contributions | |
gen | -0.049 |
plun | -0.047 |
Ana | -0.047 |
stack | -0.047 |
Pen | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ercise | +0.002 |
ets | +0.002 |
ams | +0.002 |
ock | +0.002 |
isdom | +0.002 |
Neg logit contributions | |
Ana | -0.003 |
Pen | -0.003 |
Mir | -0.002 |
Megan | -0.002 |
El | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
ets | +0.033 |
ercise | +0.032 |
ams | +0.031 |
ock | +0.031 |
vious | +0.028 |
Neg logit contributions | |
Ana | -0.035 |
plun | -0.035 |
gen | -0.035 |
Mir | -0.034 |
Pen | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Ana | +0.025 |
Pen | +0.025 |
Mir | +0.023 |
Megan | +0.023 |
El | +0.023 |
Neg logit contributions | |
ercise | -0.019 |
ets | -0.019 |
ams | -0.018 |
ock | -0.017 |
isdom | -0.016 |
Token | only |
Token ID | 691 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Ana | +0.031 |
Pen | +0.030 |
stack | +0.029 |
Megan | +0.029 |
plun | +0.029 |
Neg logit contributions | |
ams | -0.023 |
ercise | -0.023 |
ets | -0.022 |
vious | -0.021 |
ock | -0.021 |
Token | three |
Token ID | 1115 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ets | +0.012 |
ams | +0.012 |
ercise | +0.012 |
ock | +0.011 |
vious | +0.011 |
Neg logit contributions | |
stack | -0.015 |
gen | -0.014 |
Ana | -0.014 |
Pen | -0.013 |
plun | -0.013 |
Token | years |
Token ID | 812 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
Ana | +0.000 |
Pen | +0.000 |
Mir | +0.000 |
Megan | +0.000 |
El | +0.000 |
Neg logit contributions | |
ercise | -0.000 |
ets | -0.000 |
ams | -0.000 |
ock | -0.000 |
isdom | -0.000 |
Token | old |
Token ID | 1468 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Ana | +0.002 |
Pen | +0.002 |
Mir | +0.002 |
Megan | +0.002 |
El | +0.002 |
Neg logit contributions | |
ercise | -0.002 |
ets | -0.001 |
ams | -0.001 |
ock | -0.001 |
isdom | -0.001 |
Token | woman |
Token ID | 2415 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ams | +0.050 |
ercise | +0.048 |
ock | +0.047 |
isdom | +0.044 |
weet | +0.043 |
Neg logit contributions | |
plun | -0.072 |
Ana | -0.072 |
igor | -0.069 |
Jenkins | -0.068 |
ocated | -0.068 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ets | +0.033 |
ams | +0.032 |
ercise | +0.030 |
ock | +0.029 |
vious | +0.028 |
Neg logit contributions | |
Ana | -0.035 |
Pen | -0.034 |
plun | -0.034 |
Mir | -0.033 |
Jenkins | -0.032 |
Token | 't |
Token ID | 470 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ercise | +0.035 |
ets | +0.035 |
ock | +0.034 |
ams | +0.033 |
ear | +0.032 |
Neg logit contributions | |
Ana | -0.022 |
Pen | -0.020 |
Mir | -0.019 |
Megan | -0.018 |
El | -0.018 |
Token | know |
Token ID | 760 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ets | +0.043 |
ercise | +0.043 |
ams | +0.042 |
ock | +0.040 |
vious | +0.036 |
Neg logit contributions | |
Ana | -0.058 |
Pen | -0.056 |
Mir | -0.053 |
Megan | -0.053 |
El | -0.052 |
Token | what |
Token ID | 644 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
ets | +0.018 |
ams | +0.018 |
ercise | +0.018 |
ock | +0.017 |
isdom | +0.016 |
Neg logit contributions | |
Ana | -0.043 |
Pen | -0.042 |
plun | -0.042 |
Jenkins | -0.040 |
stack | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
Ana | +0.033 |
Pen | +0.032 |
plun | +0.031 |
Mir | +0.031 |
stack | +0.031 |
Neg logit contributions | |
ercise | -0.014 |
ets | -0.013 |
ams | -0.012 |
isdom | -0.012 |
ock | -0.011 |
Token | do |
Token ID | 466 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Ana | +0.077 |
Pen | +0.073 |
Mir | +0.069 |
plun | +0.067 |
Megan | +0.067 |
Neg logit contributions | |
ets | -0.092 |
ercise | -0.091 |
ams | -0.090 |
ock | -0.087 |
isdom | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Ana | +0.045 |
Pen | +0.044 |
Mir | +0.041 |
Megan | +0.041 |
El | +0.041 |
Neg logit contributions | |
ets | -0.034 |
ercise | -0.033 |
ams | -0.033 |
ock | -0.031 |
isdom | -0.028 |
Token | so |
Token ID | 523 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Ana | +0.056 |
Pen | +0.054 |
Mir | +0.051 |
Megan | +0.051 |
plun | +0.050 |
Neg logit contributions | |
ets | -0.041 |
ams | -0.040 |
ercise | -0.040 |
ock | -0.038 |
vious | -0.034 |
Token | they |
Token ID | 484 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
ams | +0.028 |
ets | +0.028 |
ercise | +0.028 |
ock | +0.026 |
isdom | +0.024 |
Neg logit contributions | |
Ana | -0.029 |
Pen | -0.028 |
plun | -0.028 |
gen | -0.027 |
Mir | -0.026 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ets | +0.013 |
ercise | +0.012 |
ams | +0.012 |
ock | +0.011 |
vious | +0.010 |
Neg logit contributions | |
Ana | -0.018 |
Pen | -0.018 |
Mir | -0.017 |
Megan | -0.017 |
plun | -0.017 |
Token | Qu |
Token ID | 4507 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ercise | +0.021 |
ets | +0.021 |
ams | +0.021 |
ock | +0.020 |
isdom | +0.018 |
Neg logit contributions | |
Ana | -0.023 |
Pen | -0.022 |
Mir | -0.021 |
Megan | -0.021 |
El | -0.021 |
Token | ack |
Token ID | 441 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
ercise | +0.034 |
ams | +0.031 |
ets | +0.030 |
ock | +0.029 |
isdom | +0.028 |
Neg logit contributions | |
Ana | -0.043 |
Pen | -0.039 |
Megan | -0.039 |
Mil | -0.038 |
plun | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ets | +0.018 |
ercise | +0.017 |
ams | +0.017 |
ock | +0.016 |
vious | +0.015 |
Neg logit contributions | |
Ana | -0.015 |
Pen | -0.015 |
Mir | -0.014 |
Megan | -0.014 |
El | -0.013 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Ana | +0.048 |
Pen | +0.046 |
Mir | +0.043 |
Megan | +0.042 |
El | +0.042 |
Neg logit contributions | |
ams | -0.048 |
ercise | -0.048 |
ets | -0.048 |
ock | -0.045 |
vious | -0.043 |
Token | because |
Token ID | 780 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ercise | +0.023 |
ams | +0.022 |
ets | +0.021 |
ock | +0.019 |
isdom | +0.018 |
Neg logit contributions | |
Ana | -0.035 |
Pen | -0.033 |
Mir | -0.032 |
El | -0.032 |
Megan | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Ana | +0.036 |
Pen | +0.035 |
plun | +0.033 |
Mir | +0.033 |
stack | +0.032 |
Neg logit contributions | |
ams | -0.021 |
ercise | -0.019 |
ets | -0.019 |
ock | -0.019 |
ear | -0.017 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Ana | +0.008 |
Pen | +0.008 |
Mir | +0.008 |
Megan | +0.007 |
El | +0.007 |
Neg logit contributions | |
ercise | -0.009 |
ets | -0.009 |
ams | -0.009 |
ock | -0.008 |
isdom | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ercise | +0.044 |
ets | +0.044 |
ams | +0.044 |
ock | +0.040 |
isdom | +0.036 |
Neg logit contributions | |
Ana | -0.085 |
Pen | -0.082 |
Mir | -0.079 |
Megan | -0.078 |
El | -0.078 |
Token | swim |
Token ID | 9422 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Ana | +0.078 |
Pen | +0.074 |
Mir | +0.070 |
Megan | +0.070 |
El | +0.068 |
Neg logit contributions | |
ercise | -0.072 |
ets | -0.071 |
ams | -0.069 |
ock | -0.068 |
isdom | -0.062 |
Token | in |
Token ID | 287 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ercise | +0.041 |
ets | +0.040 |
ams | +0.040 |
ock | +0.038 |
isdom | +0.035 |
Neg logit contributions | |
Ana | -0.050 |
Pen | -0.048 |
Megan | -0.046 |
Mir | -0.045 |
El | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
Ana | +0.073 |
Pen | +0.071 |
Mir | +0.067 |
Megan | +0.066 |
El | +0.065 |
Neg logit contributions | |
ets | -0.058 |
ercise | -0.058 |
ams | -0.058 |
ock | -0.055 |
vious | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Ana | +0.006 |
Pen | +0.006 |
Mir | +0.006 |
Megan | +0.006 |
El | +0.006 |
Neg logit contributions | |
ercise | -0.005 |
ets | -0.005 |
ams | -0.005 |
ock | -0.004 |
isdom | -0.004 |
Token | Tommy |
Token ID | 19919 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
ercise | +0.057 |
ams | +0.054 |
ets | +0.053 |
ock | +0.052 |
vious | +0.048 |
Neg logit contributions | |
Ana | -0.060 |
Pen | -0.056 |
Megan | -0.053 |
Mir | -0.052 |
Jenkins | -0.051 |
Token | â |
Token ID | 22940 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
ets | +0.025 |
ercise | +0.023 |
ams | +0.023 |
ock | +0.022 |
pads | +0.022 |
Neg logit contributions | |
Ana | -0.025 |
Pen | -0.023 |
Mir | -0.023 |
Megan | -0.023 |
gen | -0.023 |
Token | € |
Token ID | 26391 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
ercise | +0.067 |
ams | +0.066 |
ets | +0.066 |
ock | +0.062 |
isdom | +0.057 |
Neg logit contributions | |
Ana | -0.080 |
Pen | -0.078 |
Mir | -0.073 |
Megan | -0.073 |
El | -0.072 |
Token | ™ |
Token ID | 8151 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Ana | +0.019 |
Pen | +0.018 |
Mir | +0.017 |
Megan | +0.017 |
El | +0.017 |
Neg logit contributions | |
ercise | -0.019 |
ams | -0.019 |
ets | -0.019 |
ock | -0.018 |
isdom | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
ercise | +0.044 |
ets | +0.044 |
ams | +0.044 |
ock | +0.041 |
isdom | +0.037 |
Neg logit contributions | |
Ana | -0.056 |
Pen | -0.054 |
Mir | -0.051 |
Megan | -0.051 |
El | -0.050 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Ana | +0.024 |
Pen | +0.023 |
Mir | +0.022 |
Megan | +0.021 |
El | +0.021 |
Neg logit contributions | |
ets | -0.025 |
ercise | -0.025 |
ams | -0.025 |
ock | -0.024 |
isdom | -0.021 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ets | +0.031 |
ercise | +0.029 |
ams | +0.029 |
ock | +0.028 |
vious | +0.027 |
Neg logit contributions | |
Ana | -0.027 |
Pen | -0.026 |
Mir | -0.024 |
Megan | -0.024 |
El | -0.023 |
Token | off |
Token ID | 572 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ercise | +0.037 |
ams | +0.037 |
ets | +0.036 |
ock | +0.034 |
isdom | +0.033 |
Neg logit contributions | |
Ana | -0.047 |
Pen | -0.046 |
El | -0.043 |
Mir | -0.043 |
Megan | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Ana | +0.117 |
Pen | +0.112 |
Mir | +0.107 |
Megan | +0.106 |
gen | +0.106 |
Neg logit contributions | |
ets | -0.065 |
ams | -0.062 |
ock | -0.062 |
ercise | -0.060 |
ear | -0.053 |
Token | His |
Token ID | 2399 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ercise | +0.004 |
ams | +0.004 |
ets | +0.004 |
ock | +0.004 |
isdom | +0.003 |
Neg logit contributions | |
Ana | -0.005 |
Pen | -0.005 |
Mir | -0.005 |
Megan | -0.005 |
El | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
ets | +0.007 |
ercise | +0.007 |
ams | +0.006 |
ock | +0.006 |
vious | +0.006 |
Neg logit contributions | |
Ana | -0.010 |
Pen | -0.010 |
gen | -0.009 |
Mir | -0.009 |
Megan | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Ana | +0.002 |
Mir | +0.002 |
Pen | +0.002 |
Megan | +0.002 |
gen | +0.002 |
Neg logit contributions | |
ets | -0.003 |
ercise | -0.002 |
ams | -0.002 |
ock | -0.002 |
vious | -0.002 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Ana | +0.039 |
Pen | +0.036 |
Mir | +0.034 |
Megan | +0.034 |
El | +0.033 |
Neg logit contributions | |
ets | -0.044 |
ams | -0.043 |
ercise | -0.043 |
ock | -0.041 |
vious | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ercise | +0.024 |
ams | +0.022 |
ets | +0.021 |
ock | +0.019 |
isdom | +0.019 |
Neg logit contributions | |
Ana | -0.034 |
Pen | -0.032 |
Mir | -0.032 |
El | -0.031 |
Ell | -0.031 |
Token | cried |
Token ID | 16896 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
ercise | +0.052 |
ets | +0.051 |
ams | +0.050 |
ock | +0.048 |
vious | +0.045 |
Neg logit contributions | |
Ana | -0.045 |
Pen | -0.043 |
Mir | -0.040 |
Megan | -0.040 |
El | -0.039 |
Token | because |
Token ID | 780 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ets | +0.001 |
ercise | +0.001 |
ams | +0.001 |
ock | +0.001 |
isdom | +0.001 |
Neg logit contributions | |
Ana | -0.002 |
Pen | -0.002 |
Mir | -0.002 |
Megan | -0.002 |
El | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Ana | +0.011 |
Pen | +0.011 |
Mir | +0.010 |
Megan | +0.010 |
El | +0.010 |
Neg logit contributions | |
ercise | -0.013 |
ets | -0.013 |
ams | -0.013 |
ock | -0.012 |
isdom | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ercise | +0.065 |
ams | +0.062 |
ets | +0.062 |
isdom | +0.056 |
ear | +0.055 |
Neg logit contributions | |
Ana | -0.064 |
Pen | -0.062 |
Megan | -0.058 |
Mir | -0.057 |
El | -0.056 |
Token | hard |
Token ID | 1327 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Ana | +0.035 |
Pen | +0.034 |
Mir | +0.032 |
Megan | +0.032 |
El | +0.032 |
Neg logit contributions | |
ercise | -0.029 |
ets | -0.029 |
ams | -0.028 |
ock | -0.027 |
vious | -0.024 |
Token | work |
Token ID | 670 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
ercise | +0.018 |
ams | +0.017 |
ock | +0.017 |
ets | +0.016 |
vious | +0.015 |
Neg logit contributions | |
Ana | -0.018 |
Pen | -0.017 |
Mir | -0.016 |
El | -0.016 |
plun | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Ana | +0.021 |
Pen | +0.020 |
Mir | +0.020 |
Megan | +0.019 |
El | +0.019 |
Neg logit contributions | |
ets | -0.026 |
ams | -0.024 |
ercise | -0.024 |
ock | -0.024 |
vious | -0.022 |
Token | hurt |
Token ID | 5938 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ercise | +0.082 |
ets | +0.082 |
ams | +0.082 |
ock | +0.078 |
isdom | +0.072 |
Neg logit contributions | |
Ana | -0.078 |
Pen | -0.074 |
Mir | -0.070 |
Megan | -0.069 |
El | -0.069 |
Token | them |
Token ID | 606 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ercise | +0.010 |
ets | +0.009 |
ams | +0.009 |
ock | +0.009 |
isdom | +0.008 |
Neg logit contributions | |
Ana | -0.013 |
Pen | -0.013 |
Mir | -0.012 |
Megan | -0.012 |
El | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Ana | +0.014 |
Pen | +0.013 |
Megan | +0.012 |
Mir | +0.012 |
El | +0.012 |
Neg logit contributions | |
ercise | -0.013 |
ets | -0.013 |
ams | -0.013 |
ock | -0.012 |
isdom | -0.011 |
Token | We |
Token ID | 775 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Ana | +0.015 |
Pen | +0.014 |
Mir | +0.013 |
Megan | +0.013 |
El | +0.013 |
Neg logit contributions | |
ercise | -0.015 |
ets | -0.015 |
ams | -0.014 |
ock | -0.014 |
isdom | -0.013 |
Token | have |
Token ID | 423 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ercise | +0.029 |
ams | +0.029 |
ets | +0.028 |
ock | +0.027 |
isdom | +0.025 |
Neg logit contributions | |
Ana | -0.026 |
Pen | -0.025 |
Mir | -0.023 |
Megan | -0.023 |
El | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
ets | +0.058 |
ock | +0.058 |
ams | +0.057 |
ercise | +0.057 |
ully | +0.051 |
Neg logit contributions | |
Pen | -0.068 |
Ana | -0.068 |
Mir | -0.064 |
Megan | -0.063 |
bathroom | -0.062 |
Token | be |
Token ID | 307 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Ana | +0.095 |
Pen | +0.090 |
Mir | +0.085 |
Megan | +0.084 |
El | +0.083 |
Neg logit contributions | |
ercise | -0.099 |
ets | -0.098 |
ams | -0.097 |
ock | -0.092 |
isdom | -0.086 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ets | +0.034 |
ercise | +0.034 |
ams | +0.033 |
ock | +0.032 |
isdom | +0.030 |
Neg logit contributions | |
Ana | -0.037 |
Pen | -0.035 |
Mir | -0.034 |
Megan | -0.033 |
El | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Ana | +0.003 |
Pen | +0.003 |
Megan | +0.003 |
Mir | +0.003 |
El | +0.003 |
Neg logit contributions | |
ercise | -0.003 |
ets | -0.003 |
ams | -0.003 |
ock | -0.002 |
isdom | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
Ana | +0.012 |
Pen | +0.011 |
Mir | +0.011 |
Megan | +0.010 |
El | +0.010 |
Neg logit contributions | |
ets | -0.010 |
ercise | -0.010 |
ams | -0.010 |
ock | -0.009 |
vious | -0.008 |
Token | ," |
Token ID | 553 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Ana | +0.017 |
Pen | +0.017 |
Mir | +0.016 |
Megan | +0.016 |
El | +0.016 |
Neg logit contributions | |
ercise | -0.013 |
ets | -0.013 |
ams | -0.013 |
ock | -0.012 |
isdom | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ercise | +0.042 |
ets | +0.042 |
ams | +0.040 |
vious | +0.038 |
ock | +0.037 |
Neg logit contributions | |
Ana | -0.047 |
Pen | -0.045 |
Mir | -0.043 |
gen | -0.043 |
Jenkins | -0.042 |
Token | just |
Token ID | 655 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
ets | +0.000 |
ercise | +0.000 |
ams | +0.000 |
pads | +0.000 |
ock | +0.000 |
Neg logit contributions | |
Ana | -0.000 |
Pen | -0.000 |
Mir | -0.000 |
stack | -0.000 |
Lopez | -0.000 |
Token | stood |
Token ID | 6204 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ets | +0.064 |
ams | +0.062 |
ercise | +0.061 |
ock | +0.058 |
vious | +0.055 |
Neg logit contributions | |
Ana | -0.060 |
Pen | -0.057 |
plun | -0.054 |
Mir | -0.053 |
gen | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
Ana | +0.044 |
Pen | +0.043 |
Mir | +0.040 |
Megan | +0.040 |
plun | +0.039 |
Neg logit contributions | |
ams | -0.035 |
ercise | -0.034 |
ets | -0.033 |
ock | -0.031 |
ear | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Ana | +0.096 |
Pen | +0.091 |
Mir | +0.087 |
stack | +0.086 |
Mil | +0.085 |
Neg logit contributions | |
ets | -0.056 |
ock | -0.054 |
ams | -0.053 |
ercise | -0.052 |
ear | -0.049 |
Token | hallway |
Token ID | 23959 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
ets | +0.007 |
ercise | +0.007 |
ams | +0.007 |
ock | +0.007 |
vious | +0.006 |
Neg logit contributions | |
Ana | -0.004 |
Pen | -0.004 |
Mir | -0.004 |
El | -0.004 |
Megan | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Ana | +0.129 |
Pen | +0.124 |
Mir | +0.117 |
El | +0.116 |
plun | +0.115 |
Neg logit contributions | |
ets | -0.085 |
ams | -0.081 |
ercise | -0.078 |
ock | -0.076 |
vious | -0.068 |
Token | The |
Token ID | 383 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ercise | +0.005 |
ams | +0.004 |
ets | +0.004 |
ear | +0.004 |
isdom | +0.004 |
Neg logit contributions | |
Ana | -0.009 |
gen | -0.009 |
plun | -0.009 |
Pen | -0.009 |
teaspoon | -0.009 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Pen | +0.012 |
Ana | +0.012 |
Mir | +0.011 |
Megan | +0.011 |
El | +0.011 |
Neg logit contributions | |
ets | -0.014 |
ock | -0.013 |
ercise | -0.013 |
ams | -0.013 |
vious | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
Ana | +0.063 |
Pen | +0.060 |
Mir | +0.058 |
Megan | +0.056 |
stack | +0.056 |
Neg logit contributions | |
ets | -0.062 |
ock | -0.060 |
ercise | -0.060 |
ams | -0.058 |
les | -0.054 |
Token | strange |
Token ID | 6283 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
Ana | +0.095 |
Pen | +0.089 |
Mir | +0.085 |
Megan | +0.083 |
Mil | +0.083 |
Neg logit contributions | |
ercise | -0.075 |
ets | -0.074 |
ock | -0.074 |
ams | -0.073 |
vious | -0.065 |
Token | so |
Token ID | 523 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
Ana | +0.056 |
Pen | +0.053 |
Mir | +0.050 |
Megan | +0.050 |
El | +0.049 |
Neg logit contributions | |
ercise | -0.061 |
ets | -0.061 |
ams | -0.060 |
ock | -0.057 |
isdom | -0.053 |
Token | difficult |
Token ID | 2408 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ets | +0.019 |
ercise | +0.019 |
ams | +0.019 |
ock | +0.018 |
vious | +0.016 |
Neg logit contributions | |
Ana | -0.020 |
Pen | -0.019 |
Mir | -0.018 |
Megan | -0.018 |
El | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
ercise | +0.036 |
ams | +0.036 |
ets | +0.035 |
ock | +0.033 |
isdom | +0.030 |
Neg logit contributions | |
Ana | -0.049 |
Pen | -0.047 |
Mir | -0.045 |
El | -0.044 |
Megan | -0.044 |
Token | make |
Token ID | 787 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Ana | +0.081 |
Pen | +0.076 |
Mir | +0.073 |
Jenkins | +0.073 |
Megan | +0.073 |
Neg logit contributions | |
ock | -0.071 |
ercise | -0.070 |
ets | -0.069 |
ams | -0.064 |
ear | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ercise | +0.045 |
ets | +0.044 |
ams | +0.044 |
ock | +0.042 |
ear | +0.038 |
Neg logit contributions | |
Ana | -0.061 |
Pen | -0.058 |
Megan | -0.055 |
Mir | -0.055 |
El | -0.054 |
Token | bed |
Token ID | 3996 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Ana | +0.025 |
Pen | +0.024 |
Megan | +0.023 |
Mir | +0.022 |
El | +0.022 |
Neg logit contributions | |
ets | -0.028 |
ercise | -0.028 |
ock | -0.027 |
ams | -0.027 |
vious | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Ana | +0.102 |
Pen | +0.099 |
Mir | +0.094 |
El | +0.092 |
Megan | +0.092 |
Neg logit contributions | |
ets | -0.085 |
ams | -0.080 |
ercise | -0.080 |
ock | -0.078 |
vious | -0.069 |
Token | â |
Token ID | 22940 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
ercise | +0.027 |
ets | +0.026 |
ams | +0.026 |
ock | +0.025 |
isdom | +0.023 |
Neg logit contributions | |
Ana | -0.030 |
Pen | -0.029 |
Mir | -0.027 |
Megan | -0.027 |
El | -0.027 |
Token | € |
Token ID | 26391 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
ams | +0.098 |
ercise | +0.096 |
ets | +0.096 |
ock | +0.091 |
isdom | +0.087 |
Neg logit contributions | |
Pen | -0.072 |
Ana | -0.071 |
Megan | -0.066 |
Mir | -0.065 |
plun | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Ana | +0.002 |
Pen | +0.002 |
Mir | +0.002 |
Megan | +0.002 |
El | +0.002 |
Neg logit contributions | |
ercise | -0.002 |
ets | -0.002 |
ams | -0.002 |
ock | -0.002 |
isdom | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
ercise | +0.024 |
ets | +0.024 |
ams | +0.024 |
ock | +0.024 |
ear | +0.022 |
Neg logit contributions | |
Ana | -0.028 |
Pen | -0.027 |
Mir | -0.025 |
gen | -0.025 |
Megan | -0.025 |
Token | woods |
Token ID | 16479 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ets | +0.046 |
ercise | +0.045 |
ams | +0.045 |
ock | +0.042 |
isdom | +0.040 |
Neg logit contributions | |
Ana | -0.036 |
Pen | -0.035 |
Mir | -0.032 |
El | -0.032 |
Megan | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Ana | +0.090 |
Pen | +0.087 |
Megan | +0.082 |
Mir | +0.082 |
plun | +0.081 |
Neg logit contributions | |
ets | -0.060 |
ams | -0.059 |
ercise | -0.057 |
ock | -0.054 |
ear | -0.049 |
Token | It |
Token ID | 632 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ets | +0.038 |
ercise | +0.037 |
ams | +0.037 |
ock | +0.033 |
ear | +0.032 |
Neg logit contributions | |
Ana | -0.058 |
gen | -0.056 |
Pen | -0.055 |
stack | -0.053 |
plun | -0.053 |
Token | was |
Token ID | 373 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ercise | +0.005 |
ets | +0.005 |
ock | +0.005 |
ams | +0.005 |
vious | +0.005 |
Neg logit contributions | |
Ana | -0.006 |
Lee | -0.006 |
Pen | -0.006 |
plun | -0.005 |
Mir | -0.005 |
Token | cold |
Token ID | 4692 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Ana | +0.052 |
Pen | +0.049 |
Mir | +0.046 |
Megan | +0.046 |
El | +0.046 |
Neg logit contributions | |
ams | -0.042 |
ercise | -0.042 |
ets | -0.042 |
ock | -0.040 |
vious | -0.036 |
Token | outside |
Token ID | 2354 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Ana | +0.011 |
Pen | +0.011 |
El | +0.011 |
Ell | +0.011 |
Mir | +0.011 |
Neg logit contributions | |
ercise | -0.011 |
ams | -0.010 |
isdom | -0.010 |
ets | -0.009 |
earned | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
Ana | +0.136 |
Pen | +0.132 |
Mir | +0.126 |
Megan | +0.125 |
El | +0.124 |
Neg logit contributions | |
ercise | -0.090 |
ets | -0.088 |
ams | -0.087 |
ock | -0.081 |
isdom | -0.075 |
Token | but |
Token ID | 475 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Ana | +0.002 |
Pen | +0.002 |
Mir | +0.002 |
Megan | +0.002 |
El | +0.002 |
Neg logit contributions | |
ercise | -0.002 |
ets | -0.002 |
ams | -0.002 |
ock | -0.002 |
isdom | -0.002 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
ercise | +0.033 |
ams | +0.033 |
ets | +0.032 |
ock | +0.031 |
isdom | +0.028 |
Neg logit contributions | |
Ana | -0.028 |
Pen | -0.026 |
Mir | -0.025 |
plun | -0.025 |
gen | -0.025 |
Token | still |
Token ID | 991 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ercise | +0.021 |
ets | +0.020 |
ams | +0.020 |
pads | +0.018 |
isdom | +0.017 |
Neg logit contributions | |
Ana | -0.024 |
gen | -0.022 |
Pen | -0.022 |
Mir | -0.022 |
plun | -0.022 |
Token | stayed |
Token ID | 9658 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ets | +0.042 |
ams | +0.042 |
ercise | +0.041 |
ock | +0.037 |
isdom | +0.036 |
Neg logit contributions | |
Ana | -0.049 |
Pen | -0.046 |
Mir | -0.044 |
gen | -0.044 |
plun | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ams | +0.054 |
ercise | +0.052 |
ets | +0.051 |
ock | +0.045 |
vious | +0.043 |
Neg logit contributions | |
Ana | -0.123 |
Pen | -0.121 |
Megan | -0.115 |
Mir | -0.114 |
El | -0.113 |
Token | they |
Token ID | 484 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
Ana | +0.031 |
Pen | +0.029 |
plun | +0.028 |
Megan | +0.027 |
Mir | +0.027 |
Neg logit contributions | |
ercise | -0.029 |
ams | -0.029 |
ets | -0.029 |
ock | -0.027 |
weet | -0.025 |
Token | bring |
Token ID | 2222 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
ets | +0.041 |
ercise | +0.040 |
ams | +0.039 |
ock | +0.037 |
vious | +0.035 |
Neg logit contributions | |
Ana | -0.044 |
Pen | -0.043 |
Mir | -0.041 |
plun | -0.040 |
Megan | -0.040 |
Token | their |
Token ID | 511 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
ercise | +0.103 |
ets | +0.103 |
ams | +0.101 |
ock | +0.096 |
isdom | +0.089 |
Neg logit contributions | |
Ana | -0.120 |
Pen | -0.115 |
Mir | -0.109 |
Megan | -0.109 |
El | -0.108 |
Token | bikes |
Token ID | 16715 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ercise | +0.004 |
ets | +0.004 |
ams | +0.004 |
ock | +0.004 |
isdom | +0.004 |
Neg logit contributions | |
Ana | -0.005 |
Pen | -0.005 |
Mir | -0.004 |
Megan | -0.004 |
El | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
ercise | +0.076 |
ets | +0.072 |
ams | +0.070 |
isdom | +0.069 |
ock | +0.067 |
Neg logit contributions | |
Ana | -0.080 |
Pen | -0.078 |
Megan | -0.075 |
Ell | -0.074 |
El | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Ana | +0.109 |
Pen | +0.102 |
plun | +0.099 |
gen | +0.099 |
Jenkins | +0.099 |
Neg logit contributions | |
ercise | -0.073 |
ets | -0.070 |
ock | -0.069 |
ams | -0.068 |
weet | -0.062 |
Token | park |
Token ID | 3952 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Ana | +0.001 |
Pen | +0.001 |
Megan | +0.001 |
Mir | +0.001 |
El | +0.001 |
Neg logit contributions | |
ercise | -0.001 |
ets | -0.001 |
ams | -0.001 |
ock | -0.001 |
vious | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
Ana | +0.047 |
Pen | +0.045 |
Mir | +0.043 |
Megan | +0.043 |
El | +0.042 |
Neg logit contributions | |
ets | -0.033 |
ercise | -0.033 |
ams | -0.033 |
ock | -0.031 |
isdom | -0.028 |
Token | ride |
Token ID | 6594 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
ercise | +0.094 |
ets | +0.092 |
ams | +0.090 |
ock | +0.083 |
isdom | +0.077 |
Neg logit contributions | |
Ana | -0.105 |
Pen | -0.100 |
plun | -0.095 |
Mir | -0.095 |
gen | -0.094 |
Token | around |
Token ID | 1088 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
ercise | +0.059 |
ets | +0.059 |
ams | +0.059 |
ock | +0.055 |
isdom | +0.049 |
Neg logit contributions | |
Ana | -0.079 |
Pen | -0.075 |
Mir | -0.072 |
Megan | -0.071 |
gen | -0.071 |