TOP ACTIVATIONS
MAX = 14.959

sitting in the neighbor â s garden .
special place in Lily â s room . Lily
to sit in Emma â s nice cell .
catch it in Lisa â s net . They
were playing in Molly â s garden . Suddenly
perfectly in R avi â s room . â
was around the river â s bend . He
to break into people â s homes . Sam
hanging in their daughter â s room . <|endoftext|>
Tommy were in Tommy â s bedroom . Tommy
t fit I â ll give back to
junk in her parent â s garage . She
there lived many animals â a cow ,
grown in the day â s warmth .
were playing at Sally â s house . Sally
bird enjoyed the squirrel â s nuts .
then hopped onto Alice â s shoulder . They
your way home again â . The
to respect other people â s belongings so that
present for her mom â s birthday .

MIN ACTIVATIONS
MIN = -10.166

She says . " Playing with the lab set
Mom says . " Deal ! Thank you ,
my explained . " Really ?" Sara asked .
she said . " Yes , mom my .
Tom said . " Thank you , Tom .
tree says . " You have grown fond of
Lily said . " By e , Ben and
and Mia . " I am sorry , Tom
She says : " That 's right . You
and said . " That sounds great , Mom
said yes . " Yes , Lily . We
he said . " Yes , Mr . Lee
she says . " Yes , lady . I
their sandbox . " M ia , look !"
Ben said . " More blocks ? That sounds
Mom said . " OK , mom . We
said sorry . " I am sorry , Ben
Lily said . " OK , I 'll try
Dad said . " A promise ?" Tim asked
Lily said . " Can we play with it

INTERVAL 8.678 - 14.959
CONTAINS 0.023%

silly that they couldn â t agree . He
Let 's go inside â . And
s encouragement he didn â t give up .
connected with the mosquito â s body .
comfortable princess of all â if she only

INTERVAL 2.397 - 8.678
CONTAINS 12.868%

an elderly person walking by on the street . The person
a big model car in the shop window . It is
really boring things all day . One day , the crane
opard was brave and ready to protect his friends .
in her room . She did not know what was on

INTERVAL -3.885 - 2.397
CONTAINS 82.482%

a house . He sn uck around the house and tried
to keep it forever . The key was
to swim away . Joe y waved goodbye to
was ready to start reading and learning new words . She
them around , breaking them and making them dirty . Tom

INTERVAL -10.166 - -3.885
CONTAINS 4.627%

trucks in their room . Some are big , some are
Lily 's friend , Tim , came to play with her
calm down the animals and put them back in the cages
on her hips and said , " It 's time for
again . He was never put in a cage ever again
Token sitting
Token ID5586
Feature activation-3.66e-01

Pos logit contributions
 cries+0.007
 screams+0.006
 shouts+0.006
aned+0.005
 farewell+0.005
Neg logit contributions
 chefs-0.007
 ju-0.007
please-0.006
 pigs-0.006
Which-0.006
Token in
Token ID287
Feature activation+3.23e+00

Pos logit contributions
 chefs+0.009
 ju+0.009
 which+0.008
 pigs+0.008
Which+0.008
Neg logit contributions
 cries-0.010
 screams-0.010
aned-0.008
 shouts-0.008
am-0.008
Token the
Token ID262
Feature activation+2.73e+00

Pos logit contributions
 cries+0.084
 screams+0.083
 shouts+0.073
aned+0.072
night+0.070
Neg logit contributions
 chefs-0.088
 ju-0.087
 which-0.081
Which-0.078
 pigs-0.077
Token neighbor
Token ID4780
Feature activation+2.27e+00

Pos logit contributions
 cries+0.078
 screams+0.077
aned+0.073
am+0.071
 shouts+0.070
Neg logit contributions
 ju-0.067
 chefs-0.063
 which-0.062
 ones-0.060
Which-0.059
Tokenâ
Token ID22940
Feature activation+6.46e+00

Pos logit contributions
 screams+0.048
 cries+0.048
aned+0.043
 farewell+0.041
ulously+0.041
Neg logit contributions
 ju-0.071
 chefs-0.070
 which-0.068
 pigs-0.064
 ones-0.064
Token
Token ID26391
Feature activation+1.15e+01

Pos logit contributions
 cries+0.146
 screams+0.146
 shouts+0.119
 hurts+0.113
 yells+0.112
Neg logit contributions
Why-0.189
line-0.180
please-0.176
 which-0.175
 cartridge-0.175
Token
Token ID8151
Feature activation+2.02e-01

Pos logit contributions
 cries+0.313
 screams+0.312
ulously+0.285
aned+0.279
 shouts+0.276
Neg logit contributions
 chefs-0.283
 which-0.283
 ju-0.268
 ones-0.254
line-0.251
Tokens
Token ID82
Feature activation+1.59e+00

Pos logit contributions
 cries+0.006
 screams+0.006
 shouts+0.005
night+0.005
aned+0.005
Neg logit contributions
 chefs-0.005
 ju-0.005
 which-0.005
 pigs-0.004
Which-0.004
Token garden
Token ID11376
Feature activation+6.84e-01

Pos logit contributions
 screams+0.038
 cries+0.038
aned+0.034
ulously+0.033
 shouts+0.033
Neg logit contributions
 chefs-0.044
 ju-0.044
 which-0.044
 ones-0.041
 pigs-0.040
Token.
Token ID13
Feature activation+1.69e+00

Pos logit contributions
 cries+0.016
 screams+0.016
 shouts+0.014
aned+0.013
 farewell+0.013
Neg logit contributions
 chefs-0.020
 ju-0.020
Which-0.018
 which-0.018
please-0.018
Token
Token ID220
Feature activation+9.96e-01

Pos logit contributions
 cries+0.042
 screams+0.042
 shouts+0.036
aned+0.036
ulously+0.035
Neg logit contributions
 chefs-0.047
 ju-0.047
 which-0.044
Which-0.042
 pigs-0.042
Token special
Token ID2041
Feature activation+5.16e-01

Pos logit contributions
 cries+0.003
 screams+0.003
 shouts+0.002
 farewell+0.002
night+0.002
Neg logit contributions
 chefs-0.002
 ju-0.002
 which-0.002
ters-0.002
Which-0.002
Token place
Token ID1295
Feature activation+4.38e-01

Pos logit contributions
 cries+0.015
 screams+0.015
 shouts+0.013
aned+0.013
ulously+0.013
Neg logit contributions
 chefs-0.012
 ju-0.012
 which-0.011
Which-0.011
 ones-0.011
Token in
Token ID287
Feature activation+2.86e+00

Pos logit contributions
 cries+0.010
 screams+0.010
 shouts+0.009
aned+0.009
 farewell+0.009
Neg logit contributions
 chefs-0.013
 ju-0.013
 which-0.011
Which-0.011
 pigs-0.011
Token Lily
Token ID20037
Feature activation+4.85e+00

Pos logit contributions
 cries+0.061
 screams+0.059
 shouts+0.051
ulously+0.051
 farewell+0.048
Neg logit contributions
 chefs-0.090
 ju-0.089
please-0.083
 which-0.079
 pigs-0.079
Tokenâ
Token ID22940
Feature activation+6.32e+00

Pos logit contributions
 screams+0.111
 cries+0.109
aned+0.098
ulously+0.093
 shouts+0.092
Neg logit contributions
 ju-0.146
 chefs-0.144
 which-0.139
 ones-0.133
 pigs-0.133
Token
Token ID26391
Feature activation+1.13e+01

Pos logit contributions
 screams+0.137
 cries+0.136
 shouts+0.107
aned+0.106
ulously+0.103
Neg logit contributions
 ju-0.186
 which-0.184
Why-0.183
please-0.181
line-0.178
Token
Token ID8151
Feature activation+5.01e-01

Pos logit contributions
 cries+0.322
 screams+0.320
ulously+0.294
aned+0.291
 shouts+0.284
Neg logit contributions
 chefs-0.262
 which-0.256
 ju-0.255
 ones-0.237
line-0.228
Tokens
Token ID82
Feature activation+1.27e+00

Pos logit contributions
 cries+0.013
 screams+0.013
 shouts+0.012
night+0.011
ulously+0.011
Neg logit contributions
 chefs-0.013
 ju-0.013
 which-0.012
 pigs-0.012
ters-0.012
Token room
Token ID2119
Feature activation+3.26e+00

Pos logit contributions
 screams+0.030
 cries+0.030
aned+0.027
 shouts+0.026
ulously+0.025
Neg logit contributions
 ju-0.037
 chefs-0.036
 which-0.035
 ones-0.034
 pigs-0.033
Token.
Token ID13
Feature activation+6.67e-01

Pos logit contributions
 cries+0.075
 screams+0.073
 shouts+0.063
aned+0.061
night+0.060
Neg logit contributions
 chefs-0.098
 ju-0.097
Which-0.089
 which-0.088
 pigs-0.087
Token Lily
Token ID20037
Feature activation+3.16e-01

Pos logit contributions
 cries+0.014
 screams+0.013
 shouts+0.012
 farewell+0.011
ulously+0.011
Neg logit contributions
 chefs-0.022
 ju-0.021
please-0.019
 which-0.019
 ones-0.019
Token to
Token ID284
Feature activation+2.41e+00

Pos logit contributions
umber+0.056
 ju+0.054
line+0.054
 cartridge+0.052
Or+0.052
Neg logit contributions
 cries-0.027
 screams-0.024
 shouts-0.020
night-0.019
 farewell-0.019
Token sit
Token ID1650
Feature activation+1.38e+00

Pos logit contributions
 cries+0.070
 screams+0.070
aned+0.062
 shouts+0.062
night+0.060
Neg logit contributions
 chefs-0.058
 ju-0.057
 which-0.052
 pigs-0.050
 ones-0.050
Token in
Token ID287
Feature activation+2.80e+00

Pos logit contributions
 cries+0.031
 screams+0.029
am+0.028
ow+0.027
night+0.026
Neg logit contributions
 ju-0.040
 chefs-0.038
 basil-0.036
Which-0.036
 cartridge-0.035
Token Emma
Token ID18966
Feature activation+6.37e+00

Pos logit contributions
 cries+0.069
 screams+0.068
 shouts+0.059
aned+0.057
ulously+0.057
Neg logit contributions
 chefs-0.079
 ju-0.079
 which-0.072
Which-0.071
 pigs-0.070
Tokenâ
Token ID22940
Feature activation+6.11e+00

Pos logit contributions
 screams+0.168
aned+0.162
 cries+0.157
ulously+0.154
 farewell+0.150
Neg logit contributions
 which-0.167
 ju-0.167
 chefs-0.162
 pigs-0.157
 especially-0.157
Token
Token ID26391
Feature activation+1.11e+01

Pos logit contributions
 screams+0.132
 cries+0.129
 shouts+0.106
aned+0.100
 yells+0.098
Neg logit contributions
 ju-0.182
please-0.181
Why-0.181
 chefs-0.179
line-0.178
Token
Token ID8151
Feature activation+3.60e-01

Pos logit contributions
 screams+0.303
 cries+0.300
ulously+0.272
aned+0.269
 shouts+0.267
Neg logit contributions
 chefs-0.271
 which-0.264
 ju-0.259
 ones-0.246
 especially-0.244
Tokens
Token ID82
Feature activation+1.43e+00

Pos logit contributions
 cries+0.010
 screams+0.010
 shouts+0.009
aned+0.008
ulously+0.008
Neg logit contributions
 chefs-0.009
 ju-0.009
 which-0.009
 pigs-0.008
Which-0.008
Token nice
Token ID3621
Feature activation+1.93e+00

Pos logit contributions
 screams+0.034
 cries+0.033
aned+0.032
ulously+0.032
 shouts+0.029
Neg logit contributions
 which-0.040
 ju-0.039
 chefs-0.039
 ones-0.038
 pigs-0.036
Token cell
Token ID2685
Feature activation-4.60e-01

Pos logit contributions
 screams+0.054
 cries+0.054
aned+0.051
ulously+0.050
 shouts+0.047
Neg logit contributions
 chefs-0.047
 ju-0.046
 ones-0.044
 which-0.043
 pigs-0.041
Token.
Token ID13
Feature activation+2.06e+00

Pos logit contributions
 chefs+0.012
 ju+0.012
Which+0.011
 which+0.011
 pigs+0.011
Neg logit contributions
 cries-0.012
 screams-0.012
 shouts-0.011
aned-0.010
night-0.010
Token catch
Token ID4929
Feature activation-1.57e+00

Pos logit contributions
 cries+0.059
 screams+0.059
 shouts+0.051
ulously+0.051
ered+0.049
Neg logit contributions
 ju-0.054
 chefs-0.053
Which-0.048
 pigs-0.047
 ones-0.046
Token it
Token ID340
Feature activation+2.67e+00

Pos logit contributions
 chefs+0.045
 ju+0.044
please+0.040
Which+0.040
 builder+0.040
Neg logit contributions
 cries-0.040
 screams-0.039
 shouts-0.034
 farewell-0.032
 yells-0.031
Token in
Token ID287
Feature activation+2.31e+00

Pos logit contributions
 cries+0.066
 screams+0.065
 shouts+0.056
aned+0.054
 farewell+0.054
Neg logit contributions
 chefs-0.077
 ju-0.075
Which-0.069
 which-0.068
 pigs-0.068
Token Lisa
Token ID15378
Feature activation+6.80e+00

Pos logit contributions
 cries+0.050
 screams+0.049
 shouts+0.041
ulously+0.041
 farewell+0.040
Neg logit contributions
 ju-0.074
 chefs-0.073
please-0.067
 pigs-0.065
 builder-0.065
Tokenâ
Token ID22940
Feature activation+6.25e+00

Pos logit contributions
 cries+0.147
 screams+0.147
aned+0.130
 shouts+0.124
ulously+0.124
Neg logit contributions
 ju-0.208
 chefs-0.205
 which-0.200
 ones-0.189
 pigs-0.189
Token
Token ID26391
Feature activation+1.10e+01

Pos logit contributions
 screams+0.140
 cries+0.139
 shouts+0.108
 hurts+0.107
aned+0.106
Neg logit contributions
Why-0.178
 which-0.173
please-0.172
line-0.171
 ju-0.168
Token
Token ID8151
Feature activation+3.44e-01

Pos logit contributions
 cries+0.291
 screams+0.291
aned+0.260
ulously+0.260
 shouts+0.257
Neg logit contributions
 which-0.271
 chefs-0.267
 ju-0.265
 ones-0.249
line-0.240
Tokens
Token ID82
Feature activation+1.17e+00

Pos logit contributions
 cries+0.009
 screams+0.009
 shouts+0.008
night+0.008
ulously+0.008
Neg logit contributions
 chefs-0.009
 ju-0.009
 which-0.008
ters-0.008
 pigs-0.008
Token net
Token ID2010
Feature activation+1.92e+00

Pos logit contributions
 cries+0.026
 screams+0.026
aned+0.023
 shouts+0.022
ulously+0.021
Neg logit contributions
 ju-0.035
 chefs-0.035
 which-0.034
 ones-0.032
 pigs-0.032
Token.
Token ID13
Feature activation+6.22e-01

Pos logit contributions
 cries+0.045
 screams+0.044
 shouts+0.038
aned+0.036
 farewell+0.036
Neg logit contributions
 chefs-0.058
 ju-0.057
Which-0.052
 which-0.051
please-0.051
Token They
Token ID1119
Feature activation-1.90e+00

Pos logit contributions
 cries+0.015
 screams+0.015
 shouts+0.013
aned+0.013
ulously+0.012
Neg logit contributions
 chefs-0.018
 ju-0.018
 which-0.017
Which-0.016
 pigs-0.016
Token were
Token ID547
Feature activation+6.45e-01

Pos logit contributions
 chefs+0.035
 ju+0.035
 which+0.031
Which+0.031
 pigs+0.030
Neg logit contributions
 cries-0.047
 screams-0.047
 shouts-0.042
aned-0.041
night-0.040
Token playing
Token ID2712
Feature activation-1.00e+00

Pos logit contributions
 cries+0.018
 screams+0.018
 shouts+0.016
aned+0.016
ulously+0.015
Neg logit contributions
 chefs-0.016
 ju-0.016
 which-0.015
Which-0.014
 pigs-0.014
Token in
Token ID287
Feature activation+3.45e+00

Pos logit contributions
 ju+0.027
 chefs+0.023
 redd+0.023
 basil+0.023
Which+0.023
Neg logit contributions
 cries-0.027
 screams-0.027
 shouts-0.023
>-0.023
night-0.023
Token Molly
Token ID30236
Feature activation+6.12e+00

Pos logit contributions
 cries+0.092
 screams+0.090
 shouts+0.079
aned+0.079
night+0.076
Neg logit contributions
 chefs-0.093
 ju-0.091
 which-0.086
Which-0.082
 pigs-0.081
Tokenâ
Token ID22940
Feature activation+5.73e+00

Pos logit contributions
 screams+0.132
 cries+0.131
aned+0.118
 farewell+0.112
 shouts+0.112
Neg logit contributions
 chefs-0.193
 ju-0.188
 which-0.182
 pigs-0.175
 ones-0.173
Token
Token ID26391
Feature activation+1.10e+01

Pos logit contributions
 screams+0.121
 cries+0.121
 shouts+0.098
aned+0.092
 yells+0.091
Neg logit contributions
 ju-0.176
line-0.176
 chefs-0.176
please-0.174
Why-0.173
Token
Token ID8151
Feature activation+4.58e-01

Pos logit contributions
 cries+0.297
 screams+0.296
aned+0.264
ulously+0.264
 shouts+0.263
Neg logit contributions
 chefs-0.282
 which-0.266
 ju-0.264
 ones-0.248
 especially-0.246
Tokens
Token ID82
Feature activation+1.37e+00

Pos logit contributions
 screams+0.013
 cries+0.013
 shouts+0.012
night+0.011
aned+0.011
Neg logit contributions
 chefs-0.011
 ju-0.011
 which-0.010
 pigs-0.009
 especially-0.009
Token garden
Token ID11376
Feature activation+1.04e+00

Pos logit contributions
 cries+0.035
 screams+0.035
 shouts+0.031
aned+0.031
ulously+0.030
Neg logit contributions
 chefs-0.038
 ju-0.037
 which-0.035
 ones-0.034
 pigs-0.033
Token.
Token ID13
Feature activation+1.92e+00

Pos logit contributions
 cries+0.024
 screams+0.023
 shouts+0.020
am+0.019
night+0.019
Neg logit contributions
 ju-0.032
 chefs-0.031
Which-0.029
please-0.028
Ros-0.028
Token Suddenly
Token ID24975
Feature activation+7.01e-01

Pos logit contributions
 cries+0.047
 screams+0.047
 shouts+0.041
>+0.038
 farewell+0.038
Neg logit contributions
 chefs-0.054
 ju-0.054
 which-0.049
please-0.049
ters-0.048
Token perfectly
Token ID7138
Feature activation+1.70e+00

Pos logit contributions
 ju+0.029
 chefs+0.028
Which+0.026
 pigs+0.025
please+0.025
Neg logit contributions
 cries-0.024
 screams-0.023
 shouts-0.020
night-0.019
aned-0.019
Token in
Token ID287
Feature activation+2.30e+00

Pos logit contributions
 cries+0.032
 screams+0.030
 shouts+0.026
aned+0.025
night+0.024
Neg logit contributions
 chefs-0.057
 ju-0.057
Which-0.054
 pigs-0.053
Ros-0.052
Token R
Token ID371
Feature activation+4.22e+00

Pos logit contributions
 cries+0.046
 screams+0.045
ulously+0.039
 shouts+0.038
>+0.036
Neg logit contributions
 ju-0.076
 chefs-0.072
please-0.070
 cartridge-0.066
 pigs-0.065
Tokenavi
Token ID15820
Feature activation+3.67e+00

Pos logit contributions
 cries+0.110
 screams+0.109
 shouts+0.100
ulously+0.099
aned+0.098
Neg logit contributions
 chefs-0.113
 basil-0.101
umber-0.101
 which-0.099
 cartridge-0.098
Tokenâ
Token ID22940
Feature activation+5.84e+00

Pos logit contributions
 screams+0.091
 cries+0.091
aned+0.084
ulously+0.081
 farewell+0.080
Neg logit contributions
 chefs-0.100
 ju-0.097
 which-0.095
 pigs-0.091
 ones-0.091
Token
Token ID26391
Feature activation+1.09e+01

Pos logit contributions
 screams+0.127
 cries+0.125
 shouts+0.101
aned+0.099
 yells+0.095
Neg logit contributions
 ju-0.178
please-0.172
 chefs-0.170
line-0.170
 which-0.169
Token
Token ID8151
Feature activation-3.18e-02

Pos logit contributions
 cries+0.302
 screams+0.300
aned+0.267
ulously+0.265
 shouts+0.262
Neg logit contributions
 chefs-0.277
 ju-0.267
 which-0.262
 ones-0.246
 pigs-0.240
Tokens
Token ID82
Feature activation+6.00e-01

Pos logit contributions
 chefs+0.001
 ju+0.001
 which+0.001
ters+0.001
 pigs+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
ulously-0.001
night-0.001
Token room
Token ID2119
Feature activation+2.81e+00

Pos logit contributions
 screams+0.014
 cries+0.014
aned+0.012
 shouts+0.012
ulously+0.012
Neg logit contributions
 chefs-0.018
 ju-0.017
 which-0.017
 ones-0.016
 pigs-0.016
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
 cries+0.067
 screams+0.066
 shouts+0.057
aned+0.056
night+0.054
Neg logit contributions
 chefs-0.082
 ju-0.081
 which-0.075
Which-0.073
 pigs-0.073
Tokenâ
Token ID22940
Feature activation+2.55e+00

Pos logit contributions
 cries+0.027
 screams+0.026
 shouts+0.023
aned+0.022
 farewell+0.022
Neg logit contributions
 chefs-0.031
 ju-0.030
 which-0.028
Which-0.027
please-0.027
Token was
Token ID373
Feature activation+2.11e+00

Pos logit contributions
 chefs+0.125
 ju+0.123
 which+0.113
Which+0.109
 pigs+0.108
Neg logit contributions
 cries-0.140
 screams-0.139
 shouts-0.122
aned-0.121
ulously-0.118
Token around
Token ID1088
Feature activation+2.15e+00

Pos logit contributions
 cries+0.057
 screams+0.056
 shouts+0.051
 yells+0.048
aned+0.048
Neg logit contributions
 chefs-0.055
 ju-0.055
Which-0.049
 pigs-0.048
 basil-0.048
Token the
Token ID262
Feature activation+2.40e+00

Pos logit contributions
 cries+0.050
 screams+0.050
aned+0.042
 shouts+0.042
night+0.041
Neg logit contributions
 chefs-0.063
 ju-0.063
 which-0.060
Which-0.057
 ones-0.057
Token river
Token ID7850
Feature activation-8.21e-01

Pos logit contributions
 screams+0.070
 cries+0.070
 shouts+0.062
am+0.059
>+0.059
Neg logit contributions
 chefs-0.056
 ju-0.053
 which-0.052
Which-0.051
anges-0.051
Tokenâ
Token ID22940
Feature activation+6.17e+00

Pos logit contributions
 chefs+0.026
 ju+0.026
Which+0.024
please+0.023
Ros+0.023
Neg logit contributions
 cries-0.018
 screams-0.018
 shouts-0.016
am-0.015
aned-0.014
Token
Token ID26391
Feature activation+1.09e+01

Pos logit contributions
 cries+0.118
 screams+0.118
 shouts+0.094
aned+0.088
 yells+0.086
Neg logit contributions
 ju-0.206
 chefs-0.201
 which-0.198
Why-0.196
 ones-0.194
Token
Token ID8151
Feature activation-2.28e-01

Pos logit contributions
 cries+0.340
 screams+0.335
ulously+0.304
 shouts+0.300
aned+0.298
Neg logit contributions
 chefs-0.238
 ju-0.227
 which-0.223
 ones-0.206
line-0.200
Tokens
Token ID82
Feature activation+9.80e-01

Pos logit contributions
 chefs+0.006
 ju+0.006
 which+0.006
 pigs+0.005
 ones+0.005
Neg logit contributions
 cries-0.006
 screams-0.006
 shouts-0.005
aned-0.005
ulously-0.005
Token bend
Token ID19396
Feature activation+1.10e+00

Pos logit contributions
 cries+0.026
 screams+0.025
 shouts+0.022
aned+0.022
ulously+0.021
Neg logit contributions
 chefs-0.027
 ju-0.026
 which-0.024
 pigs-0.023
Which-0.023
Token.
Token ID13
Feature activation+2.16e+00

Pos logit contributions
 cries+0.032
 screams+0.032
 shouts+0.029
aned+0.028
ulously+0.028
Neg logit contributions
 chefs-0.025
 ju-0.025
 which-0.025
 ones-0.023
ters-0.022
Token He
Token ID679
Feature activation-4.18e-01

Pos logit contributions
 cries+0.062
 screams+0.062
aned+0.055
night+0.054
 shouts+0.054
Neg logit contributions
 ju-0.051
 chefs-0.050
 which-0.049
Which-0.047
 ones-0.046
Token to
Token ID284
Feature activation+2.38e+00

Pos logit contributions
 chefs+0.053
 ju+0.052
 which+0.048
Which+0.046
 pigs+0.046
Neg logit contributions
 cries-0.055
 screams-0.054
 shouts-0.048
aned-0.047
ulously-0.046
Token break
Token ID2270
Feature activation-3.25e-01

Pos logit contributions
 cries+0.072
 screams+0.070
 shouts+0.063
ulously+0.061
aned+0.060
Neg logit contributions
 ju-0.055
 chefs-0.055
Which-0.048
 which-0.048
 pigs-0.048
Token into
Token ID656
Feature activation+3.74e+00

Pos logit contributions
 ju+0.010
 chefs+0.010
please+0.009
Which+0.009
 pigs+0.009
Neg logit contributions
 cries-0.008
 screams-0.007
 shouts-0.006
ulously-0.006
aned-0.006
Token people
Token ID661
Feature activation+5.42e-01

Pos logit contributions
 cries+0.094
 screams+0.092
 shouts+0.080
ulously+0.077
aned+0.076
Neg logit contributions
 ju-0.106
 chefs-0.104
 which-0.094
Which-0.094
please-0.094
Tokenâ
Token ID22940
Feature activation+6.32e+00

Pos logit contributions
 cries+0.013
 screams+0.013
 shouts+0.012
aned+0.011
ulously+0.011
Neg logit contributions
 chefs-0.015
 ju-0.015
 which-0.014
Which-0.014
 pigs-0.014
Token
Token ID26391
Feature activation+1.09e+01

Pos logit contributions
 screams+0.157
 cries+0.154
 shouts+0.126
 farewell+0.119
 jaws+0.118
Neg logit contributions
Why-0.170
please-0.169
ters-0.168
line-0.166
 chefs-0.164
Token
Token ID8151
Feature activation-3.03e-01

Pos logit contributions
 cries+0.298
 screams+0.296
ulously+0.273
aned+0.265
night+0.260
Neg logit contributions
 chefs-0.266
 which-0.260
 ju-0.258
line-0.243
 ones-0.234
Tokens
Token ID82
Feature activation+1.66e-01

Pos logit contributions
 ju+0.007
 chefs+0.007
 which+0.007
line+0.007
ters+0.007
Neg logit contributions
 screams-0.009
 cries-0.009
night-0.007
 shouts-0.007
 farewell-0.007
Token homes
Token ID5682
Feature activation-7.02e-01

Pos logit contributions
 screams+0.004
 cries+0.004
aned+0.004
 shouts+0.004
night+0.004
Neg logit contributions
 chefs-0.004
 which-0.004
 ju-0.004
 ones-0.004
 pigs-0.004
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
 chefs+0.020
 ju+0.020
 which+0.018
Which+0.018
 pigs+0.018
Neg logit contributions
 cries-0.017
 screams-0.017
 shouts-0.015
aned-0.015
ulously-0.014
Token Sam
Token ID3409
Feature activation-1.74e-01

Pos logit contributions
 cries+0.026
 screams+0.026
 shouts+0.023
aned+0.022
ulously+0.021
Neg logit contributions
 chefs-0.030
 ju-0.029
 which-0.027
Which-0.026
 pigs-0.026
Token hanging
Token ID10938
Feature activation-1.69e+00

Pos logit contributions
 cries+0.014
 screams+0.014
 shouts+0.013
aned+0.012
night+0.012
Neg logit contributions
 chefs-0.008
 ju-0.008
Which-0.007
 which-0.007
 pigs-0.007
Token in
Token ID287
Feature activation+2.01e+00

Pos logit contributions
 chefs+0.046
 ju+0.045
Which+0.040
 which+0.040
please+0.040
Neg logit contributions
 cries-0.045
 screams-0.044
 shouts-0.038
 farewell-0.037
ulously-0.037
Token their
Token ID511
Feature activation+2.60e+00

Pos logit contributions
 cries+0.051
 screams+0.050
 shouts+0.044
ulously+0.042
aned+0.042
Neg logit contributions
 chefs-0.056
 ju-0.055
 which-0.050
Which-0.049
 pigs-0.049
Token daughter
Token ID4957
Feature activation+5.79e+00

Pos logit contributions
 screams+0.080
 cries+0.079
aned+0.078
rum+0.075
 shouts+0.073
Neg logit contributions
 ju-0.056
 which-0.051
 chefs-0.051
 ones-0.050
 prett-0.048
Tokenâ
Token ID22940
Feature activation+6.02e+00

Pos logit contributions
 screams+0.131
 cries+0.128
aned+0.120
ulously+0.114
 shouts+0.111
Neg logit contributions
 ju-0.170
 chefs-0.167
 which-0.165
 ones-0.157
 pigs-0.153
Token
Token ID26391
Feature activation+1.08e+01

Pos logit contributions
 screams+0.149
 cries+0.145
 shouts+0.123
 yells+0.115
 jaws+0.112
Neg logit contributions
 ju-0.165
Why-0.164
 which-0.159
please-0.159
 cartridge-0.157
Token
Token ID8151
Feature activation-1.45e-01

Pos logit contributions
 screams+0.280
 cries+0.278
aned+0.247
 shouts+0.244
ulously+0.244
Neg logit contributions
 which-0.279
 chefs-0.278
 ju-0.272
 ones-0.259
 especially-0.252
Tokens
Token ID82
Feature activation+1.04e+00

Pos logit contributions
 ju+0.004
 chefs+0.004
 which+0.004
 pigs+0.003
 ones+0.003
Neg logit contributions
 cries-0.004
 screams-0.004
 shouts-0.003
aned-0.003
ulously-0.003
Token room
Token ID2119
Feature activation+2.85e+00

Pos logit contributions
 screams+0.025
 cries+0.024
aned+0.023
 shouts+0.022
ulously+0.021
Neg logit contributions
 ju-0.029
 chefs-0.028
 which-0.028
 ones-0.027
 pigs-0.026
Token.
Token ID13
Feature activation+6.21e-01

Pos logit contributions
 cries+0.070
 screams+0.069
 shouts+0.060
aned+0.058
night+0.057
Neg logit contributions
 chefs-0.081
 ju-0.080
 which-0.074
Which-0.072
 pigs-0.072
Token<|endoftext|>
Token ID50256
Feature activation+5.22e+00

Pos logit contributions
 cries+0.016
 screams+0.016
 shouts+0.014
aned+0.014
ulously+0.014
Neg logit contributions
 chefs-0.017
 ju-0.016
 which-0.015
Which-0.015
 pigs-0.015
Token Tommy
Token ID19919
Feature activation+1.86e+00

Pos logit contributions
 cries+0.031
 screams+0.030
 shouts+0.027
aned+0.026
 farewell+0.026
Neg logit contributions
 chefs-0.029
 ju-0.029
 which-0.026
Which-0.026
 ones-0.025
Token were
Token ID547
Feature activation+1.18e+00

Pos logit contributions
 cries+0.058
 screams+0.058
aned+0.055
ulously+0.052
 farewell+0.051
Neg logit contributions
 chefs-0.038
 which-0.037
 ju-0.035
 pigs-0.034
 ones-0.033
Token in
Token ID287
Feature activation+3.24e+00

Pos logit contributions
 screams+0.040
 cries+0.039
aned+0.037
rum+0.035
 farewell+0.035
Neg logit contributions
 chefs-0.025
 especially-0.022
 ju-0.022
 which-0.021
 pigs-0.021
Token Tommy
Token ID19919
Feature activation+4.33e+00

Pos logit contributions
aned+0.102
 cries+0.101
 screams+0.101
am+0.094
night+0.090
Neg logit contributions
 chefs-0.071
 which-0.068
 ju-0.064
Why-0.064
 ones-0.064
Tokenâ
Token ID22940
Feature activation+5.53e+00

Pos logit contributions
 screams+0.124
aned+0.119
 farewell+0.116
ulously+0.116
 cries+0.113
Neg logit contributions
 which-0.107
 especially-0.097
 who-0.096
 chefs-0.095
 but-0.095
Token
Token ID26391
Feature activation+1.08e+01

Pos logit contributions
 screams+0.129
 cries+0.127
 jaws+0.107
 shouts+0.101
 hurts+0.101
Neg logit contributions
line-0.166
Why-0.158
please-0.154
 ju-0.150
 which-0.150
Token
Token ID8151
Feature activation-6.93e-01

Pos logit contributions
 screams+0.345
 cries+0.343
aned+0.309
ulously+0.308
 shouts+0.307
Neg logit contributions
 which-0.218
 chefs-0.214
 ju-0.208
 pigs-0.188
Why-0.187
Tokens
Token ID82
Feature activation+6.99e-01

Pos logit contributions
 ju+0.017
 which+0.016
 chefs+0.016
 pigs+0.015
 especially+0.015
Neg logit contributions
 screams-0.020
 cries-0.019
 shouts-0.017
night-0.017
 yells-0.016
Token bedroom
Token ID14043
Feature activation+2.58e+00

Pos logit contributions
 screams+0.018
 cries+0.018
aned+0.017
 shouts+0.016
ulously+0.016
Neg logit contributions
 chefs-0.019
 ju-0.018
 which-0.017
 ones-0.017
 pigs-0.016
Token.
Token ID13
Feature activation+2.36e+00

Pos logit contributions
 cries+0.069
 screams+0.068
 shouts+0.060
aned+0.059
ulously+0.058
Neg logit contributions
 chefs-0.068
 ju-0.066
 which-0.063
 ones-0.059
 pigs-0.059
Token Tommy
Token ID19919
Feature activation+8.67e-01

Pos logit contributions
 cries+0.056
 screams+0.055
 shouts+0.048
aned+0.046
ulously+0.045
Neg logit contributions
 chefs-0.070
 ju-0.069
 which-0.063
Which-0.062
 pigs-0.061
Token
Token ID8151
Feature activation+2.67e-02

Pos logit contributions
 cries+0.305
 screams+0.302
aned+0.277
ulously+0.275
night+0.260
Neg logit contributions
 chefs-0.242
 ju-0.239
 which-0.234
 ones-0.213
 especially-0.213
Tokent
Token ID83
Feature activation+1.42e+00

Pos logit contributions
 cries+0.001
 screams+0.001
 shouts+0.001
ulously+0.001
aned+0.001
Neg logit contributions
 ju-0.001
 chefs-0.001
 which-0.001
 pigs-0.001
ters-0.001
Token fit
Token ID4197
Feature activation-1.09e+00

Pos logit contributions
 cries+0.038
 screams+0.038
 shouts+0.033
aned+0.032
 farewell+0.032
Neg logit contributions
 chefs-0.039
 ju-0.038
Which-0.034
 which-0.034
 pigs-0.034
Token I
Token ID314
Feature activation-4.71e-01

Pos logit contributions
 chefs+0.031
 ju+0.031
 which+0.028
Which+0.028
 pigs+0.028
Neg logit contributions
 cries-0.026
 screams-0.026
 shouts-0.023
aned-0.022
night-0.021
Tokenâ
Token ID22940
Feature activation+5.85e+00

Pos logit contributions
 chefs+0.011
 ju+0.011
 which+0.010
Which+0.010
 pigs+0.010
Neg logit contributions
 cries-0.014
 screams-0.014
 shouts-0.012
aned-0.012
ulously-0.012
Token
Token ID26391
Feature activation+1.08e+01

Pos logit contributions
 screams+0.120
 cries+0.119
 jaws+0.088
ulously+0.088
 shouts+0.087
Neg logit contributions
 ju-0.186
Why-0.184
please-0.182
line-0.179
 which-0.175
Token
Token ID8151
Feature activation+1.83e-02

Pos logit contributions
 cries+0.302
 screams+0.298
ulously+0.271
aned+0.270
 farewell+0.254
Neg logit contributions
 chefs-0.271
 ju-0.262
 which-0.254
 ones-0.237
please-0.235
Tokenll
Token ID297
Feature activation+4.74e+00

Pos logit contributions
 cries+0.000
 screams+0.000
 shouts+0.000
ulously+0.000
night+0.000
Neg logit contributions
 ju-0.000
 chefs-0.000
 which-0.000
ters-0.000
 pigs-0.000
Token give
Token ID1577
Feature activation-4.08e+00

Pos logit contributions
 cries+0.128
 screams+0.126
 shouts+0.110
aned+0.109
night+0.108
Neg logit contributions
 chefs-0.121
 ju-0.120
 which-0.116
 ones-0.107
 pigs-0.106
Token back
Token ID736
Feature activation+2.67e+00

Pos logit contributions
 ju+0.114
 chefs+0.113
 which+0.106
 ones+0.102
Which+0.101
Neg logit contributions
 cries-0.101
 screams-0.101
aned-0.088
 shouts-0.086
ulously-0.085
Token to
Token ID284
Feature activation+1.73e+00

Pos logit contributions
 cries+0.067
 screams+0.066
 shouts+0.058
aned+0.056
ulously+0.055
Neg logit contributions
 chefs-0.075
 ju-0.074
 which-0.068
Which-0.066
 pigs-0.066
Token junk
Token ID18556
Feature activation-2.73e+00

Pos logit contributions
 cries+0.037
 screams+0.036
 shouts+0.031
aned+0.029
night+0.029
Neg logit contributions
 chefs-0.039
 ju-0.039
 which-0.036
Which-0.035
 pigs-0.034
Token in
Token ID287
Feature activation+2.76e+00

Pos logit contributions
 chefs+0.074
 ju+0.073
 which+0.068
 pigs+0.064
Which+0.064
Neg logit contributions
 cries-0.071
 screams-0.071
 shouts-0.062
aned-0.061
ulously-0.060
Token her
Token ID607
Feature activation+3.44e+00

Pos logit contributions
 cries+0.076
 screams+0.074
aned+0.069
am+0.066
night+0.065
Neg logit contributions
 chefs-0.072
 ju-0.069
 which-0.067
Why-0.064
 ones-0.064
Token parent
Token ID2560
Feature activation+5.98e-01

Pos logit contributions
 cries+0.090
 screams+0.090
aned+0.080
 shouts+0.078
ulously+0.076
Neg logit contributions
 chefs-0.093
 ju-0.092
 which-0.086
 ones-0.082
Which-0.082
Tokenâ
Token ID22940
Feature activation+5.84e+00

Pos logit contributions
 cries+0.012
 screams+0.012
 shouts+0.010
aned+0.010
ulously+0.010
Neg logit contributions
 chefs-0.020
 ju-0.019
 which-0.018
 pigs-0.018
Which-0.018
Token
Token ID26391
Feature activation+1.08e+01

Pos logit contributions
 screams+0.134
 cries+0.133
 shouts+0.107
aned+0.101
 yells+0.101
Neg logit contributions
Why-0.176
line-0.168
please-0.167
 ju-0.164
 chefs-0.162
Token
Token ID8151
Feature activation-3.14e-01

Pos logit contributions
 cries+0.289
 screams+0.287
 shouts+0.253
ulously+0.253
aned+0.251
Neg logit contributions
 chefs-0.281
 ju-0.272
 which-0.265
 ones-0.246
please-0.241
Tokens
Token ID82
Feature activation+7.05e-01

Pos logit contributions
 chefs+0.008
 ju+0.008
 which+0.008
 pigs+0.007
ters+0.007
Neg logit contributions
 screams-0.009
 cries-0.009
 shouts-0.008
night-0.007
ulously-0.007
Token garage
Token ID15591
Feature activation+5.43e-01

Pos logit contributions
 cries+0.017
 screams+0.016
aned+0.014
 shouts+0.014
ulously+0.014
Neg logit contributions
 chefs-0.021
 ju-0.020
 which-0.019
 ones-0.019
 pigs-0.018
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
 cries+0.014
 screams+0.014
 shouts+0.012
aned+0.012
ulously+0.011
Neg logit contributions
 chefs-0.015
 ju-0.015
 which-0.014
 pigs-0.013
 ones-0.013
Token She
Token ID1375
Feature activation-1.32e+00

Pos logit contributions
 cries+0.035
 screams+0.035
aned+0.032
ulously+0.031
night+0.031
Neg logit contributions
 ju-0.026
 chefs-0.026
 which-0.025
Why-0.023
Which-0.022
Token there
Token ID612
Feature activation-5.89e-02

Pos logit contributions
 chefs+0.036
 which+0.036
 ju+0.035
 ones+0.034
Which+0.032
Neg logit contributions
 screams-0.040
 cries-0.040
aned-0.037
 shouts-0.034
 yells-0.033
Token lived
Token ID5615
Feature activation+5.06e-01

Pos logit contributions
 chefs+0.002
 ju+0.002
 which+0.002
 ones+0.002
Which+0.002
Neg logit contributions
 cries-0.001
 screams-0.001
aned-0.001
 shouts-0.001
 farewell-0.001
Token many
Token ID867
Feature activation+9.81e-02

Pos logit contributions
 cries+0.015
 screams+0.015
aned+0.013
 shouts+0.013
night+0.013
Neg logit contributions
 chefs-0.012
 ju-0.012
 which-0.011
Which-0.011
 pigs-0.011
Token animals
Token ID4695
Feature activation-1.61e-01

Pos logit contributions
 cries+0.003
 screams+0.003
 shouts+0.003
am+0.003
 yells+0.003
Neg logit contributions
 cartridge-0.002
 ju-0.002
Ros-0.002
line-0.002
 chefs-0.002
Tokenâ
Token ID22940
Feature activation+5.67e+00

Pos logit contributions
 ju+0.005
 chefs+0.005
Which+0.005
 redd+0.005
 cartridge+0.005
Neg logit contributions
 cries-0.003
 screams-0.003
 shouts-0.003
am-0.003
ow-0.003
Token
Token ID26391
Feature activation+1.08e+01

Pos logit contributions
 cries+0.128
 screams+0.126
 shouts+0.105
aned+0.101
ulously+0.100
Neg logit contributions
 ju-0.172
 chefs-0.169
 which-0.162
please-0.159
 ones-0.156
Token
Token ID447
Feature activation+4.11e+00

Pos logit contributions
 cries+0.295
 screams+0.291
aned+0.255
 shouts+0.254
ulously+0.254
Neg logit contributions
 chefs-0.278
 ju-0.270
 which-0.256
 pigs-0.245
 ones-0.241
Token
Token ID250
Feature activation-5.74e+00

Pos logit contributions
 cries+0.151
 screams+0.150
 shouts+0.136
aned+0.134
night+0.132
Neg logit contributions
 chefs-0.069
 ju-0.067
 which-0.060
 pigs-0.056
Which-0.055
Tokena
Token ID64
Feature activation+1.53e+00

Pos logit contributions
 chefs+0.107
 ju+0.100
 which+0.092
 cartridge+0.090
 basil+0.084
Neg logit contributions
 cries-0.187
 screams-0.186
ulously-0.176
|-0.176
am-0.171
Token cow
Token ID9875
Feature activation+1.77e-01

Pos logit contributions
 cries+0.038
 screams+0.037
 shouts+0.032
aned+0.032
ulously+0.031
Neg logit contributions
 chefs-0.044
 ju-0.043
 which-0.041
 pigs-0.039
 ones-0.039
Token,
Token ID11
Feature activation-4.09e+00

Pos logit contributions
 cries+0.004
 screams+0.004
 shouts+0.004
aned+0.004
ulously+0.003
Neg logit contributions
 chefs-0.005
 ju-0.005
 which-0.005
Which-0.005
 pigs-0.005
Token grown
Token ID7334
Feature activation-4.15e-01

Pos logit contributions
 cries+0.018
 screams+0.018
 shouts+0.015
ulously+0.015
aned+0.015
Neg logit contributions
 chefs-0.019
 ju-0.019
Which-0.017
 which-0.017
Ros-0.017
Token in
Token ID287
Feature activation+2.93e+00

Pos logit contributions
 chefs+0.013
 ju+0.012
Which+0.012
 which+0.012
 pigs+0.011
Neg logit contributions
 cries-0.009
 screams-0.009
 shouts-0.008
aned-0.008
am-0.008
Token the
Token ID262
Feature activation+2.27e+00

Pos logit contributions
 cries+0.066
 screams+0.064
ulously+0.054
 shouts+0.054
rum+0.051
Neg logit contributions
 ju-0.089
 chefs-0.088
please-0.081
Which-0.080
 cartridge-0.079
Token day
Token ID1110
Feature activation+5.10e+00

Pos logit contributions
 cries+0.064
 screams+0.063
 shouts+0.055
ulously+0.054
night+0.054
Neg logit contributions
 chefs-0.057
 ju-0.054
 which-0.051
anges-0.049
Ros-0.049
Tokenâ
Token ID22940
Feature activation+5.95e+00

Pos logit contributions
 cries+0.113
 screams+0.109
 shouts+0.093
night+0.088
am+0.085
Neg logit contributions
 chefs-0.159
 ju-0.155
Which-0.150
please-0.142
Ros-0.142
Token
Token ID26391
Feature activation+1.07e+01

Pos logit contributions
 cries+0.128
 screams+0.127
 shouts+0.106
 yells+0.099
aned+0.095
Neg logit contributions
 ju-0.185
please-0.178
Why-0.178
 which-0.176
 chefs-0.175
Token
Token ID8151
Feature activation-1.10e-01

Pos logit contributions
 cries+0.287
 screams+0.284
 shouts+0.251
aned+0.249
ulously+0.249
Neg logit contributions
 chefs-0.276
 ju-0.270
 which-0.261
 pigs-0.246
please-0.245
Tokens
Token ID82
Feature activation+1.03e+00

Pos logit contributions
 chefs+0.003
 ju+0.003
 which+0.003
 pigs+0.003
 ones+0.003
Neg logit contributions
 cries-0.003
 screams-0.003
 shouts-0.003
aned-0.002
night-0.002
Token warmth
Token ID23125
Feature activation+1.97e+00

Pos logit contributions
 cries+0.028
 screams+0.027
 shouts+0.024
aned+0.024
ulously+0.023
Neg logit contributions
 chefs-0.027
 ju-0.027
 which-0.025
 ones-0.024
 pigs-0.024
Token.
Token ID13
Feature activation+1.92e+00

Pos logit contributions
 cries+0.046
 screams+0.045
 shouts+0.039
night+0.038
aned+0.038
Neg logit contributions
 chefs-0.058
 ju-0.057
Which-0.053
 which-0.052
please-0.051
Token
Token ID198
Feature activation-7.29e-01

Pos logit contributions
 cries+0.050
 screams+0.049
 shouts+0.043
aned+0.042
ulously+0.041
Neg logit contributions
 chefs-0.053
 ju-0.052
 which-0.047
Which-0.046
 pigs-0.046
Token were
Token ID547
Feature activation+7.68e-01

Pos logit contributions
 chefs+0.024
 ju+0.024
 which+0.022
Which+0.021
 pigs+0.021
Neg logit contributions
 cries-0.031
 screams-0.031
 shouts-0.028
aned-0.027
ulously-0.027
Token playing
Token ID2712
Feature activation-1.11e+00

Pos logit contributions
 cries+0.023
 screams+0.023
aned+0.020
 shouts+0.020
ulously+0.019
Neg logit contributions
 chefs-0.019
 ju-0.018
 which-0.017
 pigs-0.016
 ones-0.016
Token at
Token ID379
Feature activation+1.64e+00

Pos logit contributions
 ju+0.028
 chefs+0.026
 which+0.024
Which+0.024
 pigs+0.024
Neg logit contributions
 cries-0.031
 screams-0.031
 shouts-0.027
night-0.026
ulously-0.026
Token Sally
Token ID25737
Feature activation+3.56e+00

Pos logit contributions
 cries+0.047
 screams+0.047
aned+0.043
 shouts+0.041
night+0.040
Neg logit contributions
 chefs-0.041
 ju-0.039
 which-0.038
 ones-0.036
Which-0.036
Tokenâ
Token ID22940
Feature activation+5.52e+00

Pos logit contributions
 screams+0.095
 cries+0.093
aned+0.086
 farewell+0.086
ulously+0.084
Neg logit contributions
 which-0.093
 chefs-0.092
 ju-0.092
 especially-0.084
 pigs-0.083
Token
Token ID26391
Feature activation+1.07e+01

Pos logit contributions
 cries+0.096
 screams+0.095
 shouts+0.072
aned+0.067
ulously+0.067
Neg logit contributions
 ju-0.195
 chefs-0.190
 which-0.189
Why-0.186
line-0.185
Token
Token ID8151
Feature activation+3.15e-01

Pos logit contributions
 cries+0.329
 screams+0.326
 shouts+0.291
aned+0.289
ulously+0.287
Neg logit contributions
 chefs-0.237
 ju-0.231
 which-0.221
Which-0.201
 ones-0.201
Tokens
Token ID82
Feature activation+8.70e-01

Pos logit contributions
 cries+0.009
 screams+0.009
 shouts+0.008
night+0.007
aned+0.007
Neg logit contributions
 chefs-0.008
 ju-0.008
 which-0.007
 pigs-0.007
ters-0.007
Token house
Token ID2156
Feature activation+7.50e-01

Pos logit contributions
 cries+0.026
 screams+0.026
aned+0.026
rum+0.024
ulously+0.024
Neg logit contributions
 chefs-0.020
 which-0.019
 ju-0.018
 ones-0.018
Why-0.016
Token.
Token ID13
Feature activation+1.87e+00

Pos logit contributions
 cries+0.018
 screams+0.017
 shouts+0.015
aned+0.015
night+0.014
Neg logit contributions
 ju-0.022
 chefs-0.022
Which-0.020
 which-0.020
 pigs-0.019
Token Sally
Token ID25737
Feature activation-3.95e-01

Pos logit contributions
 cries+0.044
 screams+0.043
 shouts+0.039
am+0.037
>+0.037
Neg logit contributions
 chefs-0.053
 ju-0.050
 queens-0.047
please-0.047
 cartridge-0.047
Token bird
Token ID6512
Feature activation-7.11e-01

Pos logit contributions
 cries+0.000
 screams+0.000
 shouts+0.000
 farewell+0.000
ulously+0.000
Neg logit contributions
 chefs-0.000
 ju-0.000
 which-0.000
Which-0.000
 cartridge-0.000
Token enjoyed
Token ID8359
Feature activation+1.87e+00

Pos logit contributions
 chefs+0.018
 ju+0.018
 which+0.017
 pigs+0.016
 ones+0.016
Neg logit contributions
 cries-0.019
 screams-0.019
 shouts-0.017
aned-0.017
ulously-0.016
Token the
Token ID262
Feature activation+1.90e+00

Pos logit contributions
 cries+0.045
 screams+0.044
 shouts+0.038
 farewell+0.037
ulously+0.036
Neg logit contributions
 chefs-0.054
 ju-0.054
Which-0.049
 cartridge-0.048
 builder-0.048
Token squirrel
Token ID33039
Feature activation+8.59e-03

Pos logit contributions
 cries+0.055
 screams+0.054
 shouts+0.048
 farewell+0.046
ulously+0.046
Neg logit contributions
 chefs-0.047
 ju-0.044
 which-0.042
Which-0.041
 pigs-0.040
Tokenâ
Token ID22940
Feature activation+6.07e+00

Pos logit contributions
 screams+0.000
 cries+0.000
aned+0.000
 shouts+0.000
ulously+0.000
Neg logit contributions
 ju-0.000
 chefs-0.000
 which-0.000
 pigs-0.000
 ones-0.000
Token
Token ID26391
Feature activation+1.06e+01

Pos logit contributions
 screams+0.131
 cries+0.129
 shouts+0.104
aned+0.100
 yells+0.097
Neg logit contributions
 ju-0.190
please-0.181
Why-0.179
 chefs-0.179
 ones-0.176
Token
Token ID8151
Feature activation-4.44e-01

Pos logit contributions
 cries+0.323
 screams+0.319
aned+0.286
ulously+0.285
 shouts+0.281
Neg logit contributions
 chefs-0.240
 ju-0.236
 which-0.224
 ones-0.208
 pigs-0.207
Tokens
Token ID82
Feature activation+3.45e-01

Pos logit contributions
 ju+0.012
 chefs+0.011
 which+0.011
ters+0.010
line+0.010
Neg logit contributions
 screams-0.012
 cries-0.012
 shouts-0.010
ulously-0.010
aned-0.010
Token nuts
Token ID14380
Feature activation-1.89e+00

Pos logit contributions
 cries+0.010
 screams+0.010
 shouts+0.009
aned+0.009
ulously+0.008
Neg logit contributions
 ju-0.008
 chefs-0.008
 which-0.008
 ones-0.008
 pigs-0.007
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
 chefs+0.055
 ju+0.054
 which+0.050
Which+0.050
 pigs+0.049
Neg logit contributions
 cries-0.045
 screams-0.044
 shouts-0.038
aned-0.037
night-0.036
Token
Token ID220
Feature activation+4.07e-01

Pos logit contributions
 cries+0.012
 screams+0.012
 shouts+0.010
aned+0.010
ulously+0.010
Neg logit contributions
 chefs-0.014
 ju-0.014
 which-0.012
Which-0.012
 pigs-0.012
Token then
Token ID788
Feature activation+2.31e+00

Pos logit contributions
 cries+0.034
 screams+0.033
 shouts+0.029
aned+0.028
ulously+0.027
Neg logit contributions
 chefs-0.038
 ju-0.038
 which-0.035
Which-0.034
 pigs-0.034
Token hopped
Token ID45230
Feature activation+5.47e-01

Pos logit contributions
 cries+0.061
 screams+0.060
 shouts+0.053
aned+0.051
night+0.050
Neg logit contributions
 chefs-0.063
 ju-0.062
 which-0.057
Which-0.055
 pigs-0.055
Token onto
Token ID4291
Feature activation+5.51e+00

Pos logit contributions
 screams+0.014
 cries+0.014
aned+0.013
ulously+0.012
 shouts+0.012
Neg logit contributions
 ju-0.015
 chefs-0.014
 which-0.014
 ones-0.013
ters-0.013
Token Alice
Token ID14862
Feature activation+7.39e+00

Pos logit contributions
aned+0.170
 cries+0.169
 screams+0.169
am+0.168
umbles+0.156
Neg logit contributions
 which-0.110
 ju-0.109
 chefs-0.105
 ones-0.100
 pigs-0.098
Tokenâ
Token ID22940
Feature activation+5.95e+00

Pos logit contributions
 screams+0.206
aned+0.204
ulously+0.203
 cries+0.193
 shouts+0.182
Neg logit contributions
 which-0.172
 ju-0.158
 but-0.150
 watering-0.149
 who-0.147
Token
Token ID26391
Feature activation+1.06e+01

Pos logit contributions
 screams+0.116
 cries+0.116
 shouts+0.087
 jaws+0.087
ulously+0.085
Neg logit contributions
 which-0.180
line-0.180
Why-0.179
 ju-0.179
please-0.178
Token
Token ID8151
Feature activation+4.96e-01

Pos logit contributions
 cries+0.313
 screams+0.311
ulously+0.292
aned+0.287
 shouts+0.279
Neg logit contributions
 which-0.234
 ju-0.219
 chefs-0.211
line-0.204
 ones-0.204
Tokens
Token ID82
Feature activation+1.03e+00

Pos logit contributions
 cries+0.013
 screams+0.013
 shouts+0.012
ulously+0.011
aned+0.011
Neg logit contributions
 ju-0.013
 chefs-0.013
 which-0.012
 ones-0.011
ters-0.011
Token shoulder
Token ID8163
Feature activation+3.71e+00

Pos logit contributions
 screams+0.024
 cries+0.024
aned+0.022
ulously+0.022
 shouts+0.022
Neg logit contributions
 ju-0.029
 which-0.028
 chefs-0.027
 ones-0.027
 pigs-0.026
Token.
Token ID13
Feature activation+7.41e-01

Pos logit contributions
 cries+0.092
 screams+0.090
 shouts+0.078
aned+0.077
ulously+0.075
Neg logit contributions
 chefs-0.106
 ju-0.105
 which-0.097
Which-0.094
 pigs-0.093
Token They
Token ID1119
Feature activation-1.49e+00

Pos logit contributions
 cries+0.020
 screams+0.020
aned+0.018
am+0.017
 shouts+0.017
Neg logit contributions
 ju-0.019
 which-0.018
 chefs-0.018
Which-0.017
Why-0.017
Token your
Token ID534
Feature activation-3.09e-01

Pos logit contributions
 ju+0.130
 chefs+0.129
please+0.118
 pigs+0.113
Which+0.113
Neg logit contributions
 cries-0.118
 screams-0.113
 shouts-0.101
 farewell-0.096
night-0.094
Token way
Token ID835
Feature activation+1.72e+00

Pos logit contributions
 chefs+0.008
 ju+0.008
 which+0.008
 ones+0.008
 pigs+0.007
Neg logit contributions
 cries-0.008
 screams-0.008
aned-0.007
 shouts-0.007
ulously-0.007
Token home
Token ID1363
Feature activation+3.41e+00

Pos logit contributions
 cries+0.043
 screams+0.043
 shouts+0.037
aned+0.037
ulously+0.036
Neg logit contributions
 chefs-0.048
 ju-0.048
 which-0.046
 ones-0.043
 pigs-0.043
Token again
Token ID757
Feature activation+5.08e+00

Pos logit contributions
 cries+0.081
 screams+0.080
 shouts+0.069
aned+0.068
ulously+0.066
Neg logit contributions
 chefs-0.100
 ju-0.099
 which-0.093
 ones-0.088
Which-0.088
Tokenâ
Token ID22940
Feature activation+5.95e+00

Pos logit contributions
 cries+0.111
 screams+0.109
 shouts+0.093
aned+0.090
ulously+0.088
Neg logit contributions
 chefs-0.159
 ju-0.157
 which-0.146
Which-0.143
 pigs-0.142
Token
Token ID26391
Feature activation+1.06e+01

Pos logit contributions
 screams+0.125
 cries+0.123
 shouts+0.095
aned+0.089
 jaws+0.088
Neg logit contributions
 ju-0.191
Why-0.191
please-0.181
 which-0.180
How-0.179
Token.
Token ID13
Feature activation+3.32e-01

Pos logit contributions
 cries+0.276
 screams+0.273
aned+0.249
ulously+0.247
 shouts+0.232
Neg logit contributions
 chefs-0.272
 which-0.268
 ju-0.265
 ones-0.248
line-0.244
Token
Token ID220
Feature activation+2.23e-01

Pos logit contributions
 cries+0.007
 screams+0.007
 shouts+0.006
 farewell+0.006
ulously+0.006
Neg logit contributions
 chefs-0.010
 ju-0.010
 which-0.009
 pigs-0.009
please-0.009
Token
Token ID198
Feature activation-1.92e+00

Pos logit contributions
 cries+0.007
 screams+0.006
 shouts+0.006
aned+0.006
night+0.006
Neg logit contributions
 chefs-0.005
 ju-0.005
 which-0.005
Which-0.005
 pigs-0.004
Token
Token ID198
Feature activation-2.22e+00

Pos logit contributions
 chefs+0.051
 ju+0.050
 which+0.045
 pigs+0.044
Which+0.044
Neg logit contributions
 cries-0.052
 screams-0.052
 shouts-0.045
aned-0.044
ulously-0.044
TokenThe
Token ID464
Feature activation-1.61e+00

Pos logit contributions
 chefs+0.056
 ju+0.049
 ones+0.047
 pigs+0.046
 builder+0.044
Neg logit contributions
 screams-0.062
 cries-0.061
 farewell-0.057
ulously-0.056
>-0.056
Token to
Token ID284
Feature activation+1.26e+00

Pos logit contributions
 ju+0.003
 chefs+0.003
Which+0.002
 pigs+0.002
please+0.002
Neg logit contributions
 cries-0.002
 screams-0.002
 shouts-0.002
night-0.002
 farewell-0.002
Token respect
Token ID2461
Feature activation-2.37e+00

Pos logit contributions
 cries+0.031
 screams+0.030
 shouts+0.027
ulously+0.026
ered+0.025
Neg logit contributions
 ju-0.037
 chefs-0.037
Which-0.033
 pigs-0.033
 queens-0.032
Token other
Token ID584
Feature activation+4.74e-01

Pos logit contributions
 ju+0.068
 chefs+0.066
please+0.063
 cartridge+0.060
Ros+0.060
Neg logit contributions
 cries-0.059
 screams-0.056
 shouts-0.051
ulously-0.049
 yells-0.047
Token people
Token ID661
Feature activation-1.41e+00

Pos logit contributions
 cries+0.014
 screams+0.013
 shouts+0.012
am+0.011
 yells+0.011
Neg logit contributions
 ju-0.012
 chefs-0.012
 cartridge-0.011
Which-0.011
 which-0.011
Tokenâ
Token ID22940
Feature activation+5.65e+00

Pos logit contributions
 chefs+0.046
 ju+0.045
Which+0.042
 which+0.041
 pigs+0.040
Neg logit contributions
 cries-0.031
 screams-0.030
 shouts-0.025
aned-0.023
night-0.023
Token
Token ID26391
Feature activation+1.06e+01

Pos logit contributions
 cries+0.124
 screams+0.122
 shouts+0.101
aned+0.099
ulously+0.097
Neg logit contributions
 chefs-0.175
 ju-0.174
 which-0.163
 ones-0.159
please-0.159
Token
Token ID8151
Feature activation-2.76e-01

Pos logit contributions
 cries+0.299
 screams+0.296
aned+0.261
ulously+0.260
 shouts+0.259
Neg logit contributions
 chefs-0.260
 ju-0.253
 which-0.239
 ones-0.226
 pigs-0.224
Tokens
Token ID82
Feature activation+4.55e-01

Pos logit contributions
 chefs+0.008
 ju+0.008
 which+0.007
Which+0.007
 pigs+0.007
Neg logit contributions
 cries-0.007
 screams-0.006
 shouts-0.006
aned-0.005
ulously-0.005
Token belongings
Token ID30985
Feature activation-1.91e+00

Pos logit contributions
 cries+0.012
 screams+0.012
 shouts+0.010
aned+0.010
ulously+0.010
Neg logit contributions
 chefs-0.012
 ju-0.012
 which-0.011
 ones-0.011
 pigs-0.011
Token so
Token ID523
Feature activation+3.36e+00

Pos logit contributions
 chefs+0.058
 ju+0.057
Which+0.052
please+0.052
 pigs+0.051
Neg logit contributions
 cries-0.045
 screams-0.044
 shouts-0.037
aned-0.036
 farewell-0.035
Token that
Token ID326
Feature activation-2.23e+00

Pos logit contributions
 cries+0.115
 screams+0.113
 shouts+0.101
 farewell+0.099
am+0.098
Neg logit contributions
 chefs-0.068
 ju-0.066
please-0.057
Which-0.056
 cartridge-0.055
Token present
Token ID1944
Feature activation+2.53e-01

Pos logit contributions
 cries+0.030
 screams+0.029
night+0.028
 farewell+0.027
 shouts+0.026
Neg logit contributions
 chefs-0.033
 ju-0.032
ters-0.031
Which-0.030
Ros-0.030
Token for
Token ID329
Feature activation+7.93e-02

Pos logit contributions
 cries+0.005
 screams+0.004
night+0.004
 shouts+0.004
ow+0.004
Neg logit contributions
 ju-0.008
 chefs-0.008
Which-0.008
Like-0.008
Why-0.008
Token her
Token ID607
Feature activation+2.05e+00

Pos logit contributions
 cries+0.002
 screams+0.002
 shouts+0.002
aned+0.002
 farewell+0.002
Neg logit contributions
 chefs-0.002
 ju-0.002
 which-0.002
Which-0.002
 pigs-0.002
Token mom
Token ID1995
Feature activation+2.85e+00

Pos logit contributions
 cries+0.062
 screams+0.062
 shouts+0.055
aned+0.053
night+0.053
Neg logit contributions
 chefs-0.047
 ju-0.046
 which-0.042
Which-0.041
 pigs-0.040
Tokenâ
Token ID22940
Feature activation+5.38e+00

Pos logit contributions
 cries+0.058
 screams+0.054
 shouts+0.050
ow+0.047
night+0.045
Neg logit contributions
 chefs-0.092
 ju-0.088
Which-0.085
Ros-0.082
 queens-0.082
Token
Token ID26391
Feature activation+1.05e+01

Pos logit contributions
 screams+0.107
 cries+0.106
 shouts+0.085
aned+0.079
ulously+0.078
Neg logit contributions
 ju-0.175
 chefs-0.170
Why-0.169
 which-0.169
please-0.168
Token
Token ID8151
Feature activation-5.74e-01

Pos logit contributions
 cries+0.292
 screams+0.287
 shouts+0.255
aned+0.248
night+0.244
Neg logit contributions
 chefs-0.268
 ju-0.266
 which-0.239
Which-0.236
 pigs-0.233
Tokens
Token ID82
Feature activation-1.96e-01

Pos logit contributions
 chefs+0.016
 ju+0.016
 which+0.015
Which+0.014
 pigs+0.014
Neg logit contributions
 cries-0.014
 screams-0.014
 shouts-0.012
aned-0.012
ulously-0.012
Token birthday
Token ID10955
Feature activation-1.02e+00

Pos logit contributions
 chefs+0.005
 ju+0.005
 which+0.005
 ones+0.004
 pigs+0.004
Neg logit contributions
 cries-0.005
 screams-0.005
aned-0.005
 shouts-0.005
ulously-0.005
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
 ju+0.032
 chefs+0.032
Which+0.031
 redd+0.030
Ros+0.030
Neg logit contributions
 cries-0.020
 screams-0.018
night-0.017
 shouts-0.016
am-0.015
Token
Token ID198
Feature activation-5.69e-01

Pos logit contributions
 cries+0.044
 screams+0.043
 shouts+0.038
aned+0.037
ulously+0.036
Neg logit contributions
 chefs-0.049
 ju-0.049
 which-0.046
Which-0.044
 pigs-0.044
Token She
Token ID1375
Feature activation-1.15e+00

Pos logit contributions
 cries+0.014
 screams+0.013
 shouts+0.011
 yells+0.010
 farewell+0.010
Neg logit contributions
 ju-0.022
 chefs-0.021
please-0.019
 richest-0.019
 queens-0.019
Token says
Token ID1139
Feature activation-7.81e-01

Pos logit contributions
 chefs+0.038
 ju+0.036
 which+0.035
Which+0.034
Why+0.034
Neg logit contributions
 cries-0.021
 screams-0.021
aned-0.019
night-0.018
ulously-0.018
Token.
Token ID13
Feature activation+9.49e-02

Pos logit contributions
 ju+0.025
 chefs+0.025
Which+0.023
please+0.023
 redd+0.023
Neg logit contributions
 cries-0.017
 screams-0.017
 shouts-0.014
 farewell-0.013
night-0.013
Token
Token ID198
Feature activation-2.29e+00

Pos logit contributions
 cries+0.002
 screams+0.002
 shouts+0.001
 From+0.001
 Tears+0.001
Neg logit contributions
 ju-0.004
 richest-0.003
 chefs-0.003
 redd-0.003
 captains-0.003
Token
Token ID198
Feature activation-2.49e+00

Pos logit contributions
 chefs+0.053
 ju+0.051
 which+0.049
Which+0.046
 pigs+0.045
Neg logit contributions
 cries-0.068
 screams-0.067
aned-0.060
 shouts-0.060
night-0.059
Token"
Token ID1
Feature activation-1.02e+01

Pos logit contributions
 chefs+0.056
 ju+0.056
 which+0.049
 pigs+0.047
Which+0.047
Neg logit contributions
 cries-0.078
 screams-0.077
 shouts-0.069
aned-0.067
ulously-0.066
TokenPlaying
Token ID36530
Feature activation-5.42e+00

Pos logit contributions
 ju+0.257
 chefs+0.242
 pigs+0.235
 which+0.228
 richest+0.226
Neg logit contributions
 screams-0.253
 cries-0.233
 shouts-0.204
 hurts-0.197
 yells-0.192
Token with
Token ID351
Feature activation-5.16e+00

Pos logit contributions
 ju+0.153
 chefs+0.152
 which+0.140
Which+0.136
 pigs+0.135
Neg logit contributions
 cries-0.137
 screams-0.135
 shouts-0.117
aned-0.114
ulously-0.112
Token the
Token ID262
Feature activation-8.64e-01

Pos logit contributions
 ju+0.154
 chefs+0.149
Which+0.135
please+0.135
 which+0.133
Neg logit contributions
 cries-0.128
 screams-0.125
 shouts-0.107
ulously-0.101
 yells-0.099
Token lab
Token ID2248
Feature activation-2.46e+00

Pos logit contributions
 ju+0.023
 chefs+0.022
please+0.021
 which+0.020
 queens+0.020
Neg logit contributions
 cries-0.024
 screams-0.023
 shouts-0.021
 yells-0.019
 hurts-0.019
Token set
Token ID900
Feature activation-1.33e+00

Pos logit contributions
 chefs+0.070
 ju+0.069
 which+0.064
Which+0.062
 pigs+0.062
Neg logit contributions
 cries-0.061
 screams-0.060
 shouts-0.052
aned-0.051
ulously-0.050
Token Mom
Token ID11254
Feature activation+2.65e-01

Pos logit contributions
 screams+0.109
 cries+0.109
aned+0.104
ulously+0.100
night+0.098
Neg logit contributions
 chefs-0.074
 ju-0.070
 which-0.068
Why-0.065
 pigs-0.064
Token says
Token ID1139
Feature activation+5.74e-01

Pos logit contributions
 farewell+0.006
 screams+0.006
ulously+0.006
 jaws+0.006
 cries+0.006
Neg logit contributions
 chefs-0.007
Why-0.007
 which-0.007
 pigs-0.007
 ju-0.006
Token.
Token ID13
Feature activation+4.51e-01

Pos logit contributions
 cries+0.015
 screams+0.015
 shouts+0.013
ulously+0.013
aned+0.013
Neg logit contributions
 chefs-0.016
 ju-0.015
 which-0.015
 pigs-0.014
 ones-0.014
Token
Token ID198
Feature activation-1.69e+00

Pos logit contributions
 cries+0.011
 screams+0.011
 shouts+0.010
 farewell+0.009
 yells+0.009
Neg logit contributions
 ju-0.013
 chefs-0.013
 which-0.011
Which-0.011
please-0.011
Token
Token ID198
Feature activation-2.07e+00

Pos logit contributions
 chefs+0.031
 ju+0.030
 which+0.030
Why+0.028
Which+0.028
Neg logit contributions
 cries-0.055
 screams-0.055
aned-0.052
night-0.051
ulously-0.050
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.034
 ju+0.034
 which+0.030
Which+0.028
 pigs+0.027
Neg logit contributions
 cries-0.077
 screams-0.076
 shouts-0.069
aned-0.068
ulously-0.067
TokenDeal
Token ID45776
Feature activation+1.79e+00

Pos logit contributions
 chefs+0.259
 ju+0.258
line+0.250
 which+0.241
 captains+0.240
Neg logit contributions
 screams-0.247
 cries-0.233
night-0.214
 shouts-0.208
 farewell-0.206
Token!
Token ID0
Feature activation-9.99e-01

Pos logit contributions
 cries+0.046
 screams+0.045
aned+0.045
ulously+0.044
|+0.040
Neg logit contributions
 chefs-0.050
 which-0.045
 ones-0.044
 ju-0.043
 pigs-0.042
Token Thank
Token ID6952
Feature activation-2.46e+00

Pos logit contributions
 chefs+0.025
 ju+0.025
 which+0.023
Which+0.023
 ones+0.022
Neg logit contributions
 cries-0.028
 screams-0.027
aned-0.024
 shouts-0.024
ulously-0.023
Token you
Token ID345
Feature activation+3.98e-01

Pos logit contributions
 chefs+0.066
 ju+0.063
 which+0.059
Why+0.057
 ones+0.057
Neg logit contributions
 cries-0.066
 screams-0.065
aned-0.059
 shouts-0.057
ulously-0.056
Token,
Token ID11
Feature activation-5.23e+00

Pos logit contributions
 cries+0.011
 screams+0.011
aned+0.011
ulously+0.011
 shouts+0.010
Neg logit contributions
 chefs-0.010
 ju-0.009
 which-0.009
 pigs-0.009
 queens-0.008
Tokenmy
Token ID1820
Feature activation-5.50e-01

Pos logit contributions
 chefs+0.024
 ju+0.024
 which+0.022
Which+0.021
 pigs+0.021
Neg logit contributions
 cries-0.021
 screams-0.021
 shouts-0.018
aned-0.017
ulously-0.017
Token explained
Token ID4893
Feature activation-2.06e+00

Pos logit contributions
 chefs+0.017
 ju+0.017
Which+0.015
 which+0.015
 pigs+0.015
Neg logit contributions
 cries-0.013
 screams-0.013
 shouts-0.011
aned-0.011
night-0.010
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
 chefs+0.056
 ju+0.055
 which+0.051
Which+0.049
 pigs+0.049
Neg logit contributions
 cries-0.054
 screams-0.053
 shouts-0.047
aned-0.045
night-0.045
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
 cries+0.004
 screams+0.004
 shouts+0.004
aned+0.004
ulously+0.004
Neg logit contributions
 chefs-0.003
 ju-0.003
 which-0.003
Which-0.003
 pigs-0.003
Token
Token ID198
Feature activation-2.35e+00

Pos logit contributions
 chefs+0.038
 ju+0.037
 which+0.036
Why+0.034
Ros+0.034
Neg logit contributions
 cries-0.066
 screams-0.066
night-0.061
aned-0.060
 shouts-0.059
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.036
 ju+0.036
 which+0.031
Which+0.029
 pigs+0.028
Neg logit contributions
 cries-0.089
 screams-0.088
 shouts-0.081
aned-0.080
ulously-0.079
TokenReally
Token ID26392
Feature activation-2.74e+00

Pos logit contributions
 chefs+0.250
 ju+0.229
 pigs+0.226
 which+0.218
bles+0.215
Neg logit contributions
 screams-0.247
 cries-0.234
night-0.216
 farewell-0.214
 shouts-0.212
Token?"
Token ID1701
Feature activation+2.82e+00

Pos logit contributions
 chefs+0.079
 ju+0.077
 which+0.072
Which+0.070
 ones+0.070
Neg logit contributions
 cries-0.067
 screams-0.066
 shouts-0.058
aned-0.058
ulously-0.056
Token Sara
Token ID24799
Feature activation+1.30e+00

Pos logit contributions
 cries+0.096
 screams+0.095
 shouts+0.086
aned+0.085
ulously+0.083
Neg logit contributions
 chefs-0.054
 ju-0.053
 which-0.047
Which-0.045
 pigs-0.044
Token asked
Token ID1965
Feature activation-1.80e+00

Pos logit contributions
 screams+0.039
 cries+0.038
 farewell+0.038
ulously+0.037
|+0.036
Neg logit contributions
 chefs-0.027
 ju-0.025
 which-0.024
please-0.023
 especially-0.023
Token.
Token ID13
Feature activation-3.43e-01

Pos logit contributions
 chefs+0.051
 ju+0.050
 which+0.047
 pigs+0.045
Which+0.045
Neg logit contributions
 cries-0.045
 screams-0.045
 shouts-0.039
aned-0.038
ulously-0.037
Token she
Token ID673
Feature activation-1.19e+00

Pos logit contributions
 cries+0.097
 screams+0.093
 shouts+0.083
aned+0.077
 yells+0.077
Neg logit contributions
 chefs-0.103
 ju-0.102
 which-0.091
Which-0.089
 pigs-0.089
Token said
Token ID531
Feature activation+6.14e-01

Pos logit contributions
 chefs+0.039
 ju+0.038
 which+0.035
Which+0.035
 ones+0.034
Neg logit contributions
 cries-0.027
 screams-0.026
 shouts-0.023
aned-0.021
 yells-0.021
Token.
Token ID13
Feature activation+5.17e-01

Pos logit contributions
 cries+0.015
 screams+0.014
 shouts+0.012
aned+0.012
night+0.012
Neg logit contributions
 chefs-0.019
 ju-0.019
Which-0.017
 which-0.017
 pigs-0.017
Token
Token ID198
Feature activation-1.77e+00

Pos logit contributions
 cries+0.010
 screams+0.010
 shouts+0.008
 yells+0.008
 farewell+0.007
Neg logit contributions
 ju-0.018
 chefs-0.017
 richest-0.016
 redd-0.016
 queens-0.016
Token
Token ID198
Feature activation-2.08e+00

Pos logit contributions
 chefs+0.034
 ju+0.034
 which+0.033
Ros+0.031
Which+0.031
Neg logit contributions
 cries-0.056
 screams-0.056
aned-0.052
night-0.051
 shouts-0.050
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.030
 ju+0.030
 which+0.023
 pigs+0.022
 ones+0.022
Neg logit contributions
 cries-0.082
 screams-0.081
 shouts-0.075
aned-0.073
ulously-0.073
TokenYes
Token ID5297
Feature activation-5.08e-02

Pos logit contributions
 chefs+0.261
 ju+0.251
 pigs+0.250
 which+0.238
 potatoes+0.224
Neg logit contributions
 screams-0.234
 cries-0.228
night-0.197
 shouts-0.193
 farewell-0.189
Token,
Token ID11
Feature activation-6.05e+00

Pos logit contributions
 chefs+0.001
 ju+0.001
 which+0.001
 pigs+0.001
 ones+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
aned-0.001
ulously-0.001
Token mom
Token ID1995
Feature activation-1.29e+00

Pos logit contributions
 chefs+0.169
 ju+0.164
please+0.159
ters+0.157
Like+0.149
Neg logit contributions
 cries-0.151
 screams-0.144
 shouts-0.126
 farewell-0.123
night-0.120
Tokenmy
Token ID1820
Feature activation-1.20e+00

Pos logit contributions
 chefs+0.032
 which+0.031
 ju+0.031
 ones+0.030
ters+0.028
Neg logit contributions
 screams-0.036
 cries-0.035
aned-0.032
 farewell-0.031
ulously-0.031
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
 chefs+0.028
 which+0.026
 ju+0.025
 ones+0.025
ters+0.024
Neg logit contributions
 screams-0.034
 cries-0.034
aned-0.033
ulously-0.033
|-0.032
Token Tom
Token ID4186
Feature activation+1.38e+00

Pos logit contributions
 screams+0.096
 cries+0.095
aned+0.092
ulously+0.088
 farewell+0.086
Neg logit contributions
 chefs-0.057
 ju-0.054
 which-0.052
 pigs-0.049
Why-0.048
Token said
Token ID531
Feature activation+9.58e-01

Pos logit contributions
 screams+0.040
 cries+0.038
 farewell+0.037
ulously+0.036
aned+0.036
Neg logit contributions
 chefs-0.031
 ju-0.030
 which-0.029
 pigs-0.027
 especially-0.026
Token.
Token ID13
Feature activation+5.82e-01

Pos logit contributions
 screams+0.025
 cries+0.025
 shouts+0.022
ulously+0.022
aned+0.022
Neg logit contributions
 chefs-0.025
 ju-0.025
 which-0.024
 ones-0.022
 pigs-0.022
Token
Token ID198
Feature activation-1.79e+00

Pos logit contributions
 cries+0.012
 screams+0.012
 shouts+0.010
 yells+0.009
 farewell+0.009
Neg logit contributions
 ju-0.020
 chefs-0.019
 richest-0.018
 redd-0.017
please-0.017
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
 chefs+0.039
 ju+0.038
 which+0.036
Which+0.034
 pigs+0.033
Neg logit contributions
 cries-0.055
 screams-0.055
aned-0.049
 shouts-0.048
night-0.048
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.041
 ju+0.041
 which+0.035
 pigs+0.034
Which+0.033
Neg logit contributions
 cries-0.075
 screams-0.075
 shouts-0.068
ulously-0.066
aned-0.066
TokenThank
Token ID10449
Feature activation-4.29e+00

Pos logit contributions
 pigs+0.282
 chefs+0.278
 ju+0.273
 which+0.261
 potatoes+0.248
Neg logit contributions
 screams-0.212
 cries-0.198
 shouts-0.174
night-0.170
 farewell-0.168
Token you
Token ID345
Feature activation+5.47e-02

Pos logit contributions
 chefs+0.116
 ju+0.110
 which+0.103
Why+0.102
 ones+0.101
Neg logit contributions
 cries-0.113
 screams-0.112
aned-0.102
 shouts-0.098
ulously-0.096
Token,
Token ID11
Feature activation-5.38e+00

Pos logit contributions
 screams+0.001
 cries+0.001
aned+0.001
 shouts+0.001
ulously+0.001
Neg logit contributions
 chefs-0.001
 ju-0.001
 which-0.001
 pigs-0.001
 ones-0.001
Token Tom
Token ID4186
Feature activation+8.31e-01

Pos logit contributions
 ju+0.143
 chefs+0.142
please+0.134
Which+0.133
 which+0.127
Neg logit contributions
 cries-0.148
 screams-0.145
 shouts-0.129
 yells-0.120
 farewell-0.116
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 screams+0.024
 cries+0.024
aned+0.023
 farewell+0.022
ulously+0.022
Neg logit contributions
 chefs-0.019
 ju-0.018
 which-0.018
 ones-0.017
 pigs-0.016
Token tree
Token ID5509
Feature activation-2.03e+00

Pos logit contributions
 ju+0.024
 chefs+0.024
 which+0.022
Which+0.021
please+0.020
Neg logit contributions
 cries-0.033
 screams-0.033
 shouts-0.029
 farewell-0.028
night-0.027
Token says
Token ID1139
Feature activation+4.00e-01

Pos logit contributions
 which+0.046
 ju+0.045
 chefs+0.044
Or+0.043
 ones+0.043
Neg logit contributions
 screams-0.051
AY-0.050
rum-0.049
 cries-0.049
ulously-0.049
Token.
Token ID13
Feature activation+6.26e-01

Pos logit contributions
 cries+0.010
 screams+0.010
 shouts+0.009
aned+0.009
ulously+0.009
Neg logit contributions
 chefs-0.011
 ju-0.011
 which-0.010
 pigs-0.009
Which-0.009
Token
Token ID198
Feature activation-1.80e+00

Pos logit contributions
 cries+0.014
 screams+0.014
 shouts+0.012
 farewell+0.011
 yells+0.011
Neg logit contributions
 ju-0.019
 chefs-0.019
please-0.017
 which-0.017
 richest-0.017
Token
Token ID198
Feature activation-2.14e+00

Pos logit contributions
 chefs+0.036
 ju+0.035
 which+0.034
Which+0.032
Ros+0.031
Neg logit contributions
 cries-0.057
 screams-0.057
aned-0.052
night-0.052
 shouts-0.050
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.039
 ju+0.038
 which+0.033
 pigs+0.031
 ones+0.031
Neg logit contributions
 cries-0.075
 screams-0.075
 shouts-0.068
ulously-0.066
 farewell-0.066
TokenYou
Token ID1639
Feature activation-1.47e+00

Pos logit contributions
 chefs+0.242
 ju+0.236
 which+0.235
 pigs+0.224
line+0.220
Neg logit contributions
 screams-0.253
 cries-0.231
 farewell-0.223
 shouts-0.215
night-0.210
Token have
Token ID423
Feature activation-3.35e+00

Pos logit contributions
 chefs+0.042
 ju+0.041
 which+0.039
Which+0.039
 pigs+0.038
Neg logit contributions
 cries-0.037
 screams-0.036
 shouts-0.031
 farewell-0.029
night-0.029
Token grown
Token ID7334
Feature activation-2.42e+00

Pos logit contributions
 chefs+0.081
 ju+0.080
 which+0.073
 ones+0.070
Which+0.069
Neg logit contributions
 cries-0.099
 screams-0.098
aned-0.089
 shouts-0.087
ulously-0.085
Token fond
Token ID16245
Feature activation-1.62e+00

Pos logit contributions
 chefs+0.071
 ju+0.070
 which+0.064
 ones+0.063
Which+0.062
Neg logit contributions
 cries-0.059
 screams-0.058
 shouts-0.050
aned-0.049
ulously-0.048
Token of
Token ID286
Feature activation-3.34e+00

Pos logit contributions
 chefs+0.039
 ju+0.038
 ones+0.036
 which+0.035
 queens+0.034
Neg logit contributions
 cries-0.045
 screams-0.045
aned-0.041
ulously-0.040
 shouts-0.040
Token Lily
Token ID20037
Feature activation+5.55e-01

Pos logit contributions
 cries+0.013
 screams+0.012
 shouts+0.011
aned+0.011
 farewell+0.011
Neg logit contributions
 chefs-0.012
 ju-0.012
 which-0.011
Which-0.010
 pigs-0.010
Token said
Token ID531
Feature activation+8.56e-01

Pos logit contributions
 screams+0.016
 cries+0.016
ulously+0.015
aned+0.015
rum+0.015
Neg logit contributions
 ju-0.012
 chefs-0.012
 which-0.012
 pigs-0.011
ters-0.011
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
 screams+0.024
 cries+0.024
ulously+0.022
 shouts+0.022
aned+0.021
Neg logit contributions
 which-0.019
 chefs-0.019
 ju-0.019
ters-0.018
 pigs-0.017
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
 cries+0.006
 screams+0.006
 shouts+0.005
 farewell+0.005
 yells+0.004
Neg logit contributions
 ju-0.010
 chefs-0.009
 richest-0.009
 redd-0.009
 queens-0.009
Token
Token ID198
Feature activation-2.45e+00

Pos logit contributions
 chefs+0.044
 which+0.043
 ju+0.042
Which+0.040
 pigs+0.039
Neg logit contributions
 cries-0.068
 screams-0.068
aned-0.062
night-0.062
 shouts-0.060
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 ju+0.049
 chefs+0.048
 which+0.040
 pigs+0.040
 ones+0.039
Neg logit contributions
 screams-0.082
 cries-0.082
 shouts-0.075
ulously-0.073
>-0.072
TokenBy
Token ID3886
Feature activation+2.44e+00

Pos logit contributions
 chefs+0.269
 pigs+0.244
 ju+0.241
 which+0.240
 potatoes+0.235
Neg logit contributions
 farewell-0.215
 screams-0.212
ulously-0.198
night-0.195
|-0.194
Tokene
Token ID68
Feature activation+1.31e+00

Pos logit contributions
 cries+0.038
 screams+0.037
 shouts+0.029
aned+0.029
night+0.026
Neg logit contributions
 chefs-0.093
 ju-0.090
 which-0.087
Which-0.085
 pigs-0.084
Token,
Token ID11
Feature activation-4.74e+00

Pos logit contributions
 screams+0.035
 cries+0.035
ulously+0.033
aned+0.032
 shouts+0.031
Neg logit contributions
 chefs-0.032
 pigs-0.030
 ju-0.030
 which-0.029
ters-0.029
Token Ben
Token ID3932
Feature activation+1.09e+00

Pos logit contributions
 ju+0.122
 chefs+0.122
please+0.117
Which+0.116
Why+0.110
Neg logit contributions
 screams-0.128
 cries-0.128
 shouts-0.116
 farewell-0.107
 yells-0.105
Token and
Token ID290
Feature activation-2.98e-01

Pos logit contributions
 cries+0.028
 screams+0.028
aned+0.025
ulously+0.025
 farewell+0.025
Neg logit contributions
 chefs-0.029
 ju-0.028
 which-0.027
 pigs-0.025
 ones-0.025
Token and
Token ID290
Feature activation-1.83e-02

Pos logit contributions
 screams+0.077
 cries+0.076
aned+0.068
 shouts+0.068
ulously+0.067
Neg logit contributions
 chefs-0.065
 ju-0.064
 which-0.062
 pigs-0.057
 ones-0.056
Token Mia
Token ID32189
Feature activation+1.81e+00

Pos logit contributions
 chefs+0.000
 ju+0.000
ters+0.000
 which+0.000
 pigs+0.000
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.000
 yells-0.000
night-0.000
Token.
Token ID13
Feature activation-7.69e-02

Pos logit contributions
 screams+0.051
 cries+0.049
aned+0.047
ulously+0.046
night+0.045
Neg logit contributions
 chefs-0.042
 which-0.042
 ju-0.041
 pigs-0.039
 ones-0.038
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
 ju+0.003
 chefs+0.003
please+0.003
 cartridge+0.003
 groom+0.003
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
 yells-0.001
am-0.001
Token
Token ID198
Feature activation-2.31e+00

Pos logit contributions
 chefs+0.044
 ju+0.043
 which+0.041
Which+0.039
Why+0.038
Neg logit contributions
 cries-0.062
 screams-0.061
aned-0.055
night-0.055
 shouts-0.054
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.055
 ju+0.054
 which+0.048
 pigs+0.047
 ones+0.046
Neg logit contributions
 cries-0.069
 screams-0.068
 shouts-0.062
aned-0.059
ulously-0.059
TokenI
Token ID40
Feature activation-3.09e+00

Pos logit contributions
 ju+0.240
 which+0.222
 pigs+0.219
 chefs+0.218
umes+0.215
Neg logit contributions
 screams-0.259
 cries-0.249
 shouts-0.232
 yells-0.227
ulously-0.226
Token am
Token ID716
Feature activation-7.49e-01

Pos logit contributions
 chefs+0.084
 ju+0.084
 which+0.078
Which+0.075
 pigs+0.075
Neg logit contributions
 cries-0.082
 screams-0.080
 shouts-0.070
aned-0.067
night-0.067
Token sorry
Token ID7926
Feature activation-8.45e-01

Pos logit contributions
 ju+0.022
 chefs+0.022
Which+0.020
 ones+0.020
 which+0.020
Neg logit contributions
 cries-0.018
 screams-0.018
 shouts-0.016
 yells-0.014
ow-0.014
Token,
Token ID11
Feature activation-5.16e+00

Pos logit contributions
 chefs+0.023
 ju+0.023
 which+0.022
 pigs+0.021
 ones+0.021
Neg logit contributions
 cries-0.021
 screams-0.021
aned-0.019
ulously-0.019
 shouts-0.018
Token Tom
Token ID4186
Feature activation+1.16e+00

Pos logit contributions
 ju+0.159
please+0.158
 chefs+0.154
Which+0.153
Ros+0.150
Neg logit contributions
 screams-0.121
 cries-0.119
 shouts-0.106
 yells-0.094
 hurts-0.083
Token She
Token ID1375
Feature activation-1.30e+00

Pos logit contributions
 cries+0.011
 screams+0.011
 shouts+0.010
 yells+0.008
 farewell+0.008
Neg logit contributions
 ju-0.016
 chefs-0.016
please-0.015
 richest-0.015
ters-0.015
Token says
Token ID1139
Feature activation-6.44e-01

Pos logit contributions
 chefs+0.047
 ju+0.046
 which+0.044
Which+0.043
 pigs+0.043
Neg logit contributions
 cries-0.022
 screams-0.022
aned-0.018
 shouts-0.017
ulously-0.017
Token:
Token ID25
Feature activation-3.05e+00

Pos logit contributions
 ju+0.026
 chefs+0.026
Which+0.024
 which+0.024
 ones+0.024
Neg logit contributions
 cries-0.009
 screams-0.009
 shouts-0.006
 farewell-0.006
night-0.006
Token
Token ID198
Feature activation-2.08e+00

Pos logit contributions
 ju+0.069
 chefs+0.068
 pigs+0.059
 which+0.057
ters+0.057
Neg logit contributions
 cries-0.094
 screams-0.092
 shouts-0.083
 farewell-0.081
>-0.080
Token
Token ID198
Feature activation-2.27e+00

Pos logit contributions
 chefs+0.044
 ju+0.042
 which+0.041
Which+0.039
Why+0.039
Neg logit contributions
 cries-0.064
 screams-0.063
aned-0.058
night-0.058
ulously-0.057
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.049
 ju+0.049
 which+0.044
Which+0.042
 pigs+0.042
Neg logit contributions
 cries-0.072
 screams-0.071
 shouts-0.064
aned-0.062
ulously-0.062
TokenThat
Token ID2504
Feature activation-3.13e+00

Pos logit contributions
 ju+0.258
 chefs+0.249
 pigs+0.234
 richest+0.226
 hammer+0.226
Neg logit contributions
 screams-0.226
 shouts-0.204
 cries-0.204
 farewell-0.199
night-0.190
Token's
Token ID338
Feature activation-2.68e+00

Pos logit contributions
 ones+0.072
 chefs+0.067
 which+0.064
 ju+0.063
 pigs+0.063
Neg logit contributions
aned-0.091
iously-0.087
rum-0.086
azel-0.084
 jaws-0.083
Token right
Token ID826
Feature activation-2.78e-02

Pos logit contributions
 chefs+0.051
 ju+0.050
 which+0.046
Which+0.043
Why+0.042
Neg logit contributions
 cries-0.094
 screams-0.093
aned-0.084
 shouts-0.084
night-0.080
Token.
Token ID13
Feature activation-8.22e-01

Pos logit contributions
 chefs+0.001
 which+0.001
 ones+0.001
Why+0.001
 pigs+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
aned-0.001
|-0.001
ulously-0.001
Token You
Token ID921
Feature activation-1.11e+00

Pos logit contributions
 ju+0.028
 chefs+0.028
 which+0.026
please+0.026
 pigs+0.025
Neg logit contributions
 cries-0.016
 screams-0.015
 shouts-0.013
night-0.012
 farewell-0.012
Token and
Token ID290
Feature activation+5.47e-02

Pos logit contributions
 cries+0.018
 screams+0.018
 shouts+0.016
aned+0.016
ulously+0.016
Neg logit contributions
 chefs-0.017
 ju-0.016
 which-0.015
 pigs-0.014
Which-0.014
Token said
Token ID531
Feature activation-4.29e-01

Pos logit contributions
 cries+0.001
 screams+0.001
 shouts+0.001
night+0.001
 farewell+0.001
Neg logit contributions
 chefs-0.002
 ju-0.002
Which-0.001
 which-0.001
 pigs-0.001
Token.
Token ID13
Feature activation-2.06e-03

Pos logit contributions
 chefs+0.012
 ju+0.011
 which+0.011
 ones+0.010
 pigs+0.010
Neg logit contributions
 cries-0.011
 screams-0.011
aned-0.010
ulously-0.010
 shouts-0.009
Token
Token ID198
Feature activation-2.34e+00

Pos logit contributions
 ju+0.000
 chefs+0.000
 richest+0.000
please+0.000
 redd+0.000
Neg logit contributions
 cries-0.000
 screams-0.000
 shouts-0.000
 farewell-0.000
>-0.000
Token
Token ID198
Feature activation-2.53e+00

Pos logit contributions
 chefs+0.052
 ju+0.051
 which+0.049
Which+0.046
 pigs+0.045
Neg logit contributions
 cries-0.071
 screams-0.070
aned-0.063
night-0.062
 shouts-0.062
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 ju+0.055
 chefs+0.055
 which+0.048
 pigs+0.046
 ones+0.045
Neg logit contributions
 cries-0.081
 screams-0.080
 shouts-0.072
aned-0.070
ulously-0.070
TokenThat
Token ID2504
Feature activation-3.26e+00

Pos logit contributions
 chefs+0.231
 pigs+0.216
 ju+0.206
 builder+0.206
 whether+0.205
Neg logit contributions
 screams-0.255
 cries-0.236
 shouts-0.222
 farewell-0.218
night-0.217
Token sounds
Token ID5238
Feature activation-4.31e+00

Pos logit contributions
 ju+0.090
 chefs+0.089
 ones+0.088
 which+0.083
 pigs+0.082
Neg logit contributions
 screams-0.078
aned-0.078
 cries-0.077
|-0.074
rum-0.072
Token great
Token ID1049
Feature activation-8.88e-01

Pos logit contributions
 chefs+0.087
 ju+0.083
please+0.076
 pigs+0.075
line+0.075
Neg logit contributions
 cries-0.144
 screams-0.141
 shouts-0.127
night-0.123
 farewell-0.121
Token,
Token ID11
Feature activation-4.81e+00

Pos logit contributions
 chefs+0.023
 ones+0.021
 ju+0.021
 which+0.021
 pigs+0.020
Neg logit contributions
 cries-0.024
 screams-0.024
aned-0.024
ulously-0.023
 farewell-0.022
Token Mom
Token ID11254
Feature activation+6.30e-01

Pos logit contributions
 ju+0.139
 chefs+0.138
please+0.136
Which+0.129
umber+0.128
Neg logit contributions
 cries-0.117
 screams-0.114
 shouts-0.101
 yells-0.093
ulously-0.091
Token said
Token ID531
Feature activation-7.09e-01

Pos logit contributions
 chefs+0.050
 ju+0.048
 pigs+0.046
 ones+0.046
line+0.045
Neg logit contributions
 cries-0.036
 screams-0.035
 shouts-0.030
aned-0.028
am-0.027
Token yes
Token ID3763
Feature activation+5.99e-01

Pos logit contributions
 chefs+0.021
 ju+0.021
 which+0.019
Which+0.019
 pigs+0.019
Neg logit contributions
 cries-0.017
 screams-0.017
 shouts-0.014
aned-0.014
 farewell-0.014
Token.
Token ID13
Feature activation+3.66e-01

Pos logit contributions
 screams+0.018
 cries+0.018
ulously+0.017
aned+0.017
|+0.016
Neg logit contributions
 which-0.013
 ju-0.012
 chefs-0.012
 ones-0.012
 but-0.011
Token
Token ID198
Feature activation-2.16e+00

Pos logit contributions
 cries+0.005
 screams+0.005
 shouts+0.004
 farewell+0.003
 From+0.003
Neg logit contributions
 ju-0.014
 chefs-0.014
please-0.013
 richest-0.013
 happiest-0.013
Token
Token ID198
Feature activation-2.41e+00

Pos logit contributions
 chefs+0.050
 ju+0.049
 which+0.046
Which+0.044
 pigs+0.043
Neg logit contributions
 cries-0.064
 screams-0.064
aned-0.056
 shouts-0.056
night-0.055
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
 chefs+0.065
 ju+0.063
 pigs+0.056
 which+0.056
 richest+0.055
Neg logit contributions
 cries-0.063
 screams-0.062
 shouts-0.057
>-0.054
ulously-0.053
TokenYes
Token ID5297
Feature activation-7.01e-02

Pos logit contributions
 chefs+0.268
 pigs+0.255
 ju+0.231
 which+0.224
 potatoes+0.220
Neg logit contributions
 screams-0.229
night-0.225
 farewell-0.223
 cries-0.222
bye-0.216
Token,
Token ID11
Feature activation-6.22e+00

Pos logit contributions
 chefs+0.002
 ju+0.002
 which+0.002
 pigs+0.002
 ones+0.002
Neg logit contributions
 cries-0.002
 screams-0.002
 shouts-0.002
aned-0.001
ulously-0.001
Token Lily
Token ID20037
Feature activation-1.75e-01

Pos logit contributions
please+0.186
 chefs+0.180
umber+0.174
iers+0.171
Pl+0.171
Neg logit contributions
 cries-0.145
 screams-0.136
 shouts-0.117
 hurts-0.107
 farewell-0.106
Token.
Token ID13
Feature activation-1.27e+00

Pos logit contributions
 chefs+0.004
 ju+0.004
 which+0.004
 ones+0.004
ters+0.004
Neg logit contributions
 screams-0.005
 cries-0.005
aned-0.005
ulously-0.005
 farewell-0.004
Token We
Token ID775
Feature activation-3.54e+00

Pos logit contributions
 ju+0.040
 chefs+0.040
please+0.038
 which+0.037
 especially+0.037
Neg logit contributions
 cries-0.027
 screams-0.026
 shouts-0.022
night-0.022
 farewell-0.021
Token he
Token ID339
Feature activation-1.52e+00

Pos logit contributions
 screams+0.083
 cries+0.083
aned+0.078
ulously+0.075
night+0.074
Neg logit contributions
 chefs-0.062
 ju-0.059
 which-0.057
 pigs-0.054
Why-0.054
Token said
Token ID531
Feature activation+5.64e-01

Pos logit contributions
 chefs+0.042
 ju+0.041
 which+0.038
Which+0.037
 pigs+0.037
Neg logit contributions
 cries-0.039
 screams-0.038
 shouts-0.033
aned-0.033
ulously-0.032
Token.
Token ID13
Feature activation+4.85e-01

Pos logit contributions
 cries+0.014
 screams+0.014
 shouts+0.012
aned+0.011
 farewell+0.011
Neg logit contributions
 chefs-0.016
 ju-0.016
 which-0.015
Which-0.015
 pigs-0.015
Token
Token ID198
Feature activation-1.78e+00

Pos logit contributions
 cries+0.013
 screams+0.012
 shouts+0.011
aned+0.011
 farewell+0.010
Neg logit contributions
 ju-0.013
 chefs-0.013
 which-0.012
Which-0.012
 pigs-0.012
Token
Token ID198
Feature activation-2.15e+00

Pos logit contributions
 chefs+0.037
 ju+0.036
 which+0.035
Which+0.033
Why+0.033
Neg logit contributions
 cries-0.056
 screams-0.055
aned-0.050
night-0.050
 shouts-0.049
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.033
 ju+0.032
 which+0.027
 pigs+0.025
Which+0.025
Neg logit contributions
 cries-0.082
 screams-0.082
 shouts-0.075
aned-0.073
ulously-0.073
TokenYes
Token ID5297
Feature activation-4.10e-02

Pos logit contributions
 ju+0.250
 chefs+0.232
 which+0.229
 pigs+0.227
 redd+0.214
Neg logit contributions
 screams-0.251
 cries-0.236
night-0.210
 shouts-0.208
 farewell-0.208
Token,
Token ID11
Feature activation-6.18e+00

Pos logit contributions
 chefs+0.001
 ju+0.001
 which+0.001
 pigs+0.001
 ones+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
aned-0.001
ulously-0.001
Token Mr
Token ID1770
Feature activation-2.05e-01

Pos logit contributions
please+0.179
 chefs+0.173
 ju+0.172
Like+0.166
Ros+0.165
Neg logit contributions
 cries-0.145
 screams-0.140
 shouts-0.124
 farewell-0.116
 yells-0.113
Token.
Token ID13
Feature activation-1.92e+00

Pos logit contributions
 chefs+0.006
 ju+0.006
 which+0.005
 ones+0.005
 pigs+0.005
Neg logit contributions
 cries-0.005
 screams-0.005
aned-0.004
 shouts-0.004
ulously-0.004
Token Lee
Token ID5741
Feature activation-1.22e+00

Pos logit contributions
 ju+0.061
 which+0.054
 redd+0.053
 chefs+0.053
Which+0.052
Neg logit contributions
 screams-0.044
 cries-0.043
 shouts-0.039
 farewell-0.035
am-0.035
Token she
Token ID673
Feature activation-1.21e+00

Pos logit contributions
 cries+0.110
 screams+0.110
aned+0.101
ulously+0.098
night+0.097
Neg logit contributions
 chefs-0.086
 ju-0.083
 which-0.079
Why-0.074
 pigs-0.074
Token says
Token ID1139
Feature activation+5.27e-01

Pos logit contributions
 chefs+0.035
 ju+0.034
 which+0.032
 pigs+0.031
Which+0.031
Neg logit contributions
 cries-0.029
 screams-0.029
aned-0.025
 shouts-0.025
ulously-0.024
Token.
Token ID13
Feature activation+4.60e-01

Pos logit contributions
 cries+0.013
 screams+0.013
 shouts+0.011
aned+0.011
ulously+0.011
Neg logit contributions
 chefs-0.015
 ju-0.015
 which-0.014
Which-0.013
 pigs-0.013
Token
Token ID198
Feature activation-1.67e+00

Pos logit contributions
 cries+0.010
 screams+0.009
 shouts+0.008
 yells+0.007
 farewell+0.007
Neg logit contributions
 ju-0.015
 chefs-0.015
 richest-0.014
 redd-0.014
Which-0.013
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
 chefs+0.033
 ju+0.031
 which+0.031
Why+0.029
Ros+0.029
Neg logit contributions
 cries-0.053
 screams-0.052
aned-0.049
night-0.048
ulously-0.047
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.034
 ju+0.034
 which+0.029
Which+0.027
 pigs+0.027
Neg logit contributions
 cries-0.074
 screams-0.074
 shouts-0.067
aned-0.065
ulously-0.065
TokenYes
Token ID5297
Feature activation-6.01e-02

Pos logit contributions
 ju+0.244
 chefs+0.239
 which+0.231
 pigs+0.226
line+0.217
Neg logit contributions
 screams-0.261
 cries-0.254
 hurts-0.215
 shouts-0.213
night-0.207
Token,
Token ID11
Feature activation-6.21e+00

Pos logit contributions
 chefs+0.001
 ju+0.001
 which+0.001
 pigs+0.001
 ones+0.001
Neg logit contributions
 screams-0.002
 cries-0.002
aned-0.002
ulously-0.001
 shouts-0.001
Token lady
Token ID10846
Feature activation-1.97e+00

Pos logit contributions
 chefs+0.163
 ju+0.163
please+0.158
ters+0.153
 ones+0.150
Neg logit contributions
 cries-0.163
 screams-0.159
 shouts-0.139
 farewell-0.132
night-0.128
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
 chefs+0.051
 which+0.046
 ju+0.046
 ones+0.045
 pigs+0.044
Neg logit contributions
 cries-0.054
 screams-0.054
aned-0.051
ulously-0.049
 farewell-0.047
Token I
Token ID314
Feature activation-3.82e+00

Pos logit contributions
 chefs+0.034
 ju+0.033
 which+0.031
please+0.030
Which+0.030
Neg logit contributions
 cries-0.032
 screams-0.031
 shouts-0.027
night-0.026
 farewell-0.026
Token their
Token ID511
Feature activation+3.32e-01

Pos logit contributions
 ju+0.039
 chefs+0.039
Which+0.036
 which+0.036
please+0.035
Neg logit contributions
 cries-0.035
 screams-0.035
 shouts-0.030
aned-0.029
ulously-0.028
Token sandbox
Token ID35204
Feature activation-9.79e-01

Pos logit contributions
 cries+0.010
 screams+0.010
aned+0.010
 shouts+0.010
ulously+0.009
Neg logit contributions
 chefs-0.007
 ju-0.007
 ones-0.006
 which-0.006
 pigs-0.006
Token.
Token ID13
Feature activation+6.92e-01

Pos logit contributions
 chefs+0.030
 ju+0.030
Which+0.029
please+0.028
 pigs+0.028
Neg logit contributions
 cries-0.022
 screams-0.021
 shouts-0.018
am-0.017
aned-0.017
Token
Token ID198
Feature activation-1.57e+00

Pos logit contributions
 cries+0.016
 screams+0.016
 shouts+0.014
 yells+0.013
ulously+0.013
Neg logit contributions
 ju-0.021
 chefs-0.020
please-0.019
 which-0.019
 ones-0.018
Token
Token ID198
Feature activation-1.91e+00

Pos logit contributions
 chefs+0.037
 ju+0.036
 which+0.034
Which+0.033
 pigs+0.032
Neg logit contributions
 cries-0.046
 screams-0.045
aned-0.040
 shouts-0.040
night-0.040
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.034
 ju+0.034
 which+0.028
 pigs+0.027
 ones+0.027
Neg logit contributions
 screams-0.067
 cries-0.067
 shouts-0.062
ulously-0.061
>-0.060
TokenM
Token ID44
Feature activation-3.38e+00

Pos logit contributions
 which+0.255
line+0.243
 ju+0.230
 chefs+0.226
 builder+0.225
Neg logit contributions
 screams-0.228
ulously-0.221
 cries-0.209
|-0.198
 shouts-0.188
Tokenia
Token ID544
Feature activation-7.48e-01

Pos logit contributions
 chefs+0.100
 ju+0.100
 which+0.093
Which+0.090
 pigs+0.089
Neg logit contributions
 cries-0.080
 screams-0.079
 shouts-0.068
aned-0.066
ulously-0.065
Token,
Token ID11
Feature activation-6.56e+00

Pos logit contributions
 chefs+0.018
 ju+0.017
 which+0.017
 pigs+0.016
 ones+0.016
Neg logit contributions
 cries-0.021
 screams-0.020
aned-0.019
 farewell-0.019
ulously-0.019
Token look
Token ID804
Feature activation-2.76e+00

Pos logit contributions
 ju+0.176
 chefs+0.175
please+0.164
 pigs+0.158
Which+0.157
Neg logit contributions
 cries-0.173
 screams-0.172
 shouts-0.148
 farewell-0.143
night-0.139
Token!"
Token ID2474
Feature activation+2.06e+00

Pos logit contributions
 chefs+0.069
 ju+0.068
 which+0.063
Which+0.059
 pigs+0.059
Neg logit contributions
 cries-0.078
 screams-0.078
aned-0.069
 shouts-0.069
ulously-0.068
Token Ben
Token ID3932
Feature activation+1.07e+00

Pos logit contributions
 screams+0.095
aned+0.094
 cries+0.094
ulously+0.088
night+0.087
Neg logit contributions
 chefs-0.055
 ju-0.052
 which-0.050
Why-0.048
 ones-0.047
Token said
Token ID531
Feature activation+1.09e+00

Pos logit contributions
 screams+0.030
 cries+0.029
 farewell+0.028
ulously+0.028
aned+0.028
Neg logit contributions
 chefs-0.025
 ju-0.023
 which-0.022
 especially-0.021
 pigs-0.021
Token.
Token ID13
Feature activation+7.05e-01

Pos logit contributions
 screams+0.029
 cries+0.029
ulously+0.026
 shouts+0.026
aned+0.026
Neg logit contributions
 chefs-0.028
 ju-0.027
 which-0.026
ters-0.024
 ones-0.024
Token
Token ID198
Feature activation-1.73e+00

Pos logit contributions
 cries+0.016
 screams+0.016
 shouts+0.014
 yells+0.013
 farewell+0.012
Neg logit contributions
 ju-0.022
 chefs-0.022
 which-0.020
 richest-0.020
please-0.019
Token
Token ID198
Feature activation-2.08e+00

Pos logit contributions
 chefs+0.035
 ju+0.033
 which+0.032
Which+0.031
Why+0.030
Neg logit contributions
 cries-0.055
 screams-0.055
aned-0.050
night-0.049
 shouts-0.049
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.041
 ju+0.041
 which+0.036
 pigs+0.034
Which+0.033
Neg logit contributions
 cries-0.070
 screams-0.070
 shouts-0.063
aned-0.062
ulously-0.061
TokenMore
Token ID5167
Feature activation-2.73e+00

Pos logit contributions
 pigs+0.289
 chefs+0.286
 ju+0.269
 which+0.262
 queens+0.256
Neg logit contributions
 screams-0.214
 cries-0.200
ulously-0.184
 shouts-0.182
appointed-0.172
Token blocks
Token ID7021
Feature activation-3.40e+00

Pos logit contributions
 ju+0.074
 chefs+0.070
Which+0.066
please+0.064
Ros+0.064
Neg logit contributions
 cries-0.074
 screams-0.073
 shouts-0.064
am-0.060
 yells-0.059
Token?
Token ID30
Feature activation+7.20e-02

Pos logit contributions
 chefs+0.093
 ju+0.092
 which+0.086
Which+0.082
 pigs+0.082
Neg logit contributions
 cries-0.087
 screams-0.086
 shouts-0.075
aned-0.074
ulously-0.072
Token That
Token ID1320
Feature activation-3.98e+00

Pos logit contributions
 cries+0.001
 screams+0.001
 shouts+0.001
ow+0.001
 yells+0.001
Neg logit contributions
 chefs-0.002
 ju-0.002
please-0.002
 richest-0.002
 queens-0.002
Token sounds
Token ID5238
Feature activation-4.42e+00

Pos logit contributions
 chefs+0.125
 ju+0.125
 which+0.117
 ones+0.114
Which+0.113
Neg logit contributions
 cries-0.086
 screams-0.085
aned-0.072
 shouts-0.072
 farewell-0.069
Token Mom
Token ID11254
Feature activation+5.65e-01

Pos logit contributions
aned+0.107
 screams+0.100
 cries+0.098
aced+0.095
rum+0.094
Neg logit contributions
 chefs-0.048
 ju-0.045
 which-0.042
Which-0.042
 ones-0.042
Token said
Token ID531
Feature activation+1.03e+00

Pos logit contributions
 screams+0.015
 cries+0.015
 farewell+0.013
ulously+0.013
aned+0.013
Neg logit contributions
 chefs-0.014
 ju-0.014
 which-0.013
 pigs-0.013
Why-0.013
Token.
Token ID13
Feature activation+6.52e-01

Pos logit contributions
 screams+0.028
 cries+0.027
ulously+0.025
 shouts+0.024
aned+0.024
Neg logit contributions
 chefs-0.026
 ju-0.025
 which-0.025
ters-0.023
 pigs-0.022
Token
Token ID198
Feature activation-1.92e+00

Pos logit contributions
 cries+0.014
 screams+0.014
 shouts+0.012
 yells+0.011
 farewell+0.011
Neg logit contributions
 ju-0.021
 chefs-0.021
 richest-0.019
please-0.019
 redd-0.019
Token
Token ID198
Feature activation-2.25e+00

Pos logit contributions
 chefs+0.037
 which+0.035
 ju+0.034
Which+0.032
Why+0.032
Neg logit contributions
 cries-0.062
 screams-0.061
aned-0.058
night-0.057
ulously-0.056
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.035
 ju+0.034
 which+0.030
Which+0.028
 pigs+0.027
Neg logit contributions
 cries-0.085
 screams-0.085
 shouts-0.077
aned-0.076
ulously-0.075
TokenOK
Token ID11380
Feature activation+1.91e+00

Pos logit contributions
 chefs+0.247
 ju+0.235
line+0.227
 builder+0.220
 pigs+0.219
Neg logit contributions
 screams-0.266
 cries-0.242
 farewell-0.220
 shouts-0.218
ulously-0.207
Token,
Token ID11
Feature activation-5.63e+00

Pos logit contributions
 cries+0.040
 screams+0.038
 shouts+0.033
night+0.030
 farewell+0.029
Neg logit contributions
 ju-0.064
 chefs-0.064
Which-0.059
please-0.058
 which-0.058
Token mom
Token ID1995
Feature activation-6.17e-01

Pos logit contributions
please+0.162
Ros+0.153
 chefs+0.152
 ju+0.151
umber+0.150
Neg logit contributions
 cries-0.145
 screams-0.143
 shouts-0.123
 yells-0.111
 farewell-0.110
Token.
Token ID13
Feature activation-9.92e-01

Pos logit contributions
 chefs+0.018
 ju+0.017
 which+0.016
 ones+0.016
 pigs+0.016
Neg logit contributions
 cries-0.015
 screams-0.015
aned-0.013
 shouts-0.013
ulously-0.013
Token We
Token ID775
Feature activation-3.35e+00

Pos logit contributions
 chefs+0.028
 ju+0.028
please+0.026
 which+0.026
 pigs+0.025
Neg logit contributions
 cries-0.025
 screams-0.024
 shouts-0.021
night-0.020
 farewell-0.020
Token said
Token ID531
Feature activation-2.54e-01

Pos logit contributions
 cries+0.013
 screams+0.013
 shouts+0.011
aned+0.011
ulously+0.011
Neg logit contributions
 chefs-0.014
 ju-0.014
 which-0.013
Which-0.012
 pigs-0.012
Token sorry
Token ID7926
Feature activation-1.65e+00

Pos logit contributions
 ju+0.006
 chefs+0.006
 which+0.005
Which+0.005
please+0.005
Neg logit contributions
 cries-0.007
 screams-0.007
 shouts-0.006
 farewell-0.006
night-0.006
Token.
Token ID13
Feature activation+5.26e-01

Pos logit contributions
 chefs+0.048
 ju+0.048
 which+0.044
Which+0.043
 pigs+0.043
Neg logit contributions
 cries-0.041
 screams-0.040
 shouts-0.034
aned-0.033
night-0.033
Token
Token ID198
Feature activation-2.06e+00

Pos logit contributions
 cries+0.012
 screams+0.012
 shouts+0.010
 farewell+0.010
night+0.009
Neg logit contributions
 ju-0.017
 chefs-0.016
 richest-0.015
please-0.015
 queens-0.015
Token
Token ID198
Feature activation-2.34e+00

Pos logit contributions
 chefs+0.046
 ju+0.044
 which+0.043
Which+0.041
Why+0.040
Neg logit contributions
 cries-0.062
 screams-0.062
aned-0.055
 shouts-0.055
night-0.055
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 ju+0.047
 chefs+0.046
 which+0.039
 pigs+0.038
 ones+0.038
Neg logit contributions
 cries-0.079
 screams-0.078
 shouts-0.071
aned-0.069
ulously-0.069
TokenI
Token ID40
Feature activation-2.91e+00

Pos logit contributions
 ju+0.222
 chefs+0.202
 which+0.199
 pigs+0.197
line+0.191
Neg logit contributions
 screams-0.281
 cries-0.277
night-0.245
 hurts-0.240
ulously-0.237
Token am
Token ID716
Feature activation-5.78e-01

Pos logit contributions
 chefs+0.077
 ju+0.077
 which+0.071
 pigs+0.069
Which+0.069
Neg logit contributions
 cries-0.079
 screams-0.078
 shouts-0.068
night-0.065
aned-0.065
Token sorry
Token ID7926
Feature activation-7.96e-01

Pos logit contributions
 ju+0.018
 chefs+0.017
Which+0.017
 ones+0.017
 which+0.016
Neg logit contributions
 cries-0.013
 screams-0.013
 shouts-0.011
ow-0.010
>-0.010
Token,
Token ID11
Feature activation-4.85e+00

Pos logit contributions
 chefs+0.023
 ju+0.023
 which+0.021
Which+0.021
 pigs+0.021
Neg logit contributions
 cries-0.019
 screams-0.019
 shouts-0.016
aned-0.016
ulously-0.016
Token Ben
Token ID3932
Feature activation+8.88e-01

Pos logit contributions
please+0.142
 ju+0.142
 chefs+0.139
Anything+0.128
Which+0.127
Neg logit contributions
 cries-0.121
 screams-0.120
 shouts-0.104
 yells-0.094
 farewell-0.085
Token Lily
Token ID20037
Feature activation+1.05e+00

Pos logit contributions
 cries+0.113
 screams+0.110
 shouts+0.099
 farewell+0.093
night+0.093
Neg logit contributions
 chefs-0.088
 ju-0.087
 which-0.078
Which-0.074
ters-0.074
Token said
Token ID531
Feature activation+1.34e+00

Pos logit contributions
 cries+0.028
 screams+0.028
 shouts+0.025
aned+0.024
ulously+0.023
Neg logit contributions
 chefs-0.028
 ju-0.028
 which-0.025
Which-0.025
 pigs-0.024
Token.
Token ID13
Feature activation+5.66e-01

Pos logit contributions
 cries+0.033
 screams+0.032
 shouts+0.028
aned+0.027
ulously+0.027
Neg logit contributions
 chefs-0.039
 ju-0.038
 which-0.036
Which-0.035
 pigs-0.034
Token
Token ID198
Feature activation-1.71e+00

Pos logit contributions
 cries+0.010
 screams+0.009
 shouts+0.008
 farewell+0.007
 yells+0.007
Neg logit contributions
 ju-0.021
 chefs-0.020
 richest-0.019
 redd-0.019
 captains-0.019
Token
Token ID198
Feature activation-2.05e+00

Pos logit contributions
 chefs+0.033
 ju+0.032
 which+0.031
 pigs+0.030
Which+0.029
Neg logit contributions
 cries-0.054
 screams-0.054
aned-0.050
night-0.049
ulously-0.049
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.038
 ju+0.038
 which+0.033
Which+0.031
 pigs+0.031
Neg logit contributions
 cries-0.071
 screams-0.071
 shouts-0.064
 farewell-0.062
ulously-0.062
TokenOK
Token ID11380
Feature activation+2.00e+00

Pos logit contributions
 chefs+0.288
 pigs+0.264
 potatoes+0.246
 ju+0.244
 onions+0.242
Neg logit contributions
 screams-0.200
 cries-0.183
 farewell-0.182
bye-0.174
 shouts-0.172
Token,
Token ID11
Feature activation-5.49e+00

Pos logit contributions
 cries+0.045
 screams+0.044
 shouts+0.038
aned+0.036
night+0.035
Neg logit contributions
 chefs-0.063
 ju-0.062
 which-0.057
Which-0.057
 pigs-0.056
Token I
Token ID314
Feature activation-3.31e+00

Pos logit contributions
please+0.160
umber+0.156
 chefs+0.151
iers+0.148
Pl+0.147
Neg logit contributions
 cries-0.129
 screams-0.123
 shouts-0.111
 goodbye-0.104
 farewell-0.103
Token'll
Token ID1183
Feature activation+1.78e+00

Pos logit contributions
 chefs+0.106
 ju+0.104
 queens+0.101
 pigs+0.098
ters+0.096
Neg logit contributions
 cries-0.070
 screams-0.067
 shouts-0.058
 farewell-0.056
night-0.055
Token try
Token ID1949
Feature activation+5.48e-01

Pos logit contributions
 cries+0.044
 screams+0.043
 shouts+0.038
 farewell+0.035
aned+0.035
Neg logit contributions
 ju-0.053
 chefs-0.052
Which-0.049
 pigs-0.047
 queens-0.046
Token Dad
Token ID17415
Feature activation-8.75e-01

Pos logit contributions
 screams+0.097
 cries+0.095
aned+0.092
ulously+0.086
night+0.086
Neg logit contributions
 chefs-0.063
 ju-0.059
 which-0.059
Why-0.056
 pigs-0.055
Token said
Token ID531
Feature activation+7.49e-01

Pos logit contributions
 chefs+0.020
 which+0.019
 ju+0.019
Why+0.018
 especially+0.018
Neg logit contributions
 screams-0.024
 cries-0.024
ulously-0.022
aned-0.022
 jaws-0.022
Token.
Token ID13
Feature activation+7.92e-01

Pos logit contributions
 cries+0.019
 screams+0.019
 shouts+0.017
aned+0.016
ulously+0.016
Neg logit contributions
 chefs-0.020
 ju-0.020
 which-0.019
Which-0.018
 pigs-0.018
Token
Token ID198
Feature activation-1.65e+00

Pos logit contributions
 cries+0.022
 screams+0.022
 shouts+0.019
aned+0.019
 farewell+0.018
Neg logit contributions
 chefs-0.020
 ju-0.020
 which-0.018
Which-0.018
 pigs-0.018
Token
Token ID198
Feature activation-2.05e+00

Pos logit contributions
 chefs+0.036
 ju+0.035
 which+0.033
Which+0.032
Why+0.031
Neg logit contributions
 cries-0.051
 screams-0.051
aned-0.046
night-0.045
 shouts-0.045
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 chefs+0.038
 ju+0.037
 which+0.033
 pigs+0.031
Which+0.031
Neg logit contributions
 cries-0.071
 screams-0.070
 shouts-0.064
aned-0.063
ulously-0.062
TokenA
Token ID32
Feature activation-3.26e+00

Pos logit contributions
 chefs+0.242
 ju+0.234
 pigs+0.220
 which+0.214
bles+0.212
Neg logit contributions
 screams-0.244
 cries-0.222
 farewell-0.218
 shouts-0.214
night-0.205
Token promise
Token ID6991
Feature activation+3.94e-01

Pos logit contributions
 chefs+0.076
 ju+0.075
 which+0.068
Which+0.066
 pigs+0.065
Neg logit contributions
 cries-0.098
 screams-0.097
aned-0.086
 shouts-0.086
ulously-0.084
Token?"
Token ID1701
Feature activation+3.00e+00

Pos logit contributions
 cries+0.010
 screams+0.010
aned+0.009
ulously+0.009
 shouts+0.009
Neg logit contributions
 chefs-0.011
 which-0.010
 ju-0.010
 ones-0.010
 pigs-0.009
Token Tim
Token ID5045
Feature activation+2.18e-01

Pos logit contributions
 cries+0.091
 screams+0.090
 shouts+0.080
aned+0.079
ulously+0.077
Neg logit contributions
 chefs-0.069
 ju-0.068
 which-0.062
Which-0.059
 pigs-0.059
Token asked
Token ID1965
Feature activation-1.65e+00

Pos logit contributions
 screams+0.008
 farewell+0.007
 cries+0.007
zed+0.007
ulously+0.007
Neg logit contributions
please-0.003
 which-0.003
 especially-0.003
 chefs-0.003
 ju-0.003
Token Lily
Token ID20037
Feature activation+8.38e-01

Pos logit contributions
 screams+0.092
aned+0.091
 cries+0.089
ulously+0.085
night+0.084
Neg logit contributions
 chefs-0.049
 ju-0.046
 which-0.044
 pigs-0.042
Why-0.041
Token said
Token ID531
Feature activation+9.62e-01

Pos logit contributions
 farewell+0.027
|+0.026
 screams+0.026
ulously+0.026
aned+0.026
Neg logit contributions
 chefs-0.016
 ju-0.014
 which-0.014
 especially-0.013
 but-0.013
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
 screams+0.026
 cries+0.026
ulously+0.023
 shouts+0.023
aned+0.023
Neg logit contributions
 chefs-0.025
 ju-0.024
 which-0.023
 pigs-0.021
ters-0.021
Token
Token ID198
Feature activation-1.94e+00

Pos logit contributions
 cries+0.013
 screams+0.012
 shouts+0.011
 yells+0.010
aned+0.010
Neg logit contributions
 ju-0.016
 chefs-0.015
 richest-0.014
 which-0.014
Which-0.014
Token
Token ID198
Feature activation-2.27e+00

Pos logit contributions
 chefs+0.037
 which+0.036
 ju+0.034
Ros+0.033
Which+0.033
Neg logit contributions
 cries-0.063
 screams-0.062
aned-0.057
night-0.057
 shouts-0.056
Token"
Token ID1
Feature activation-1.00e+01

Pos logit contributions
 ju+0.050
 chefs+0.049
 which+0.043
 pigs+0.042
Which+0.041
Neg logit contributions
 cries-0.072
 screams-0.071
 shouts-0.064
aned-0.063
ulously-0.062
TokenCan
Token ID6090
Feature activation-2.54e+00

Pos logit contributions
 chefs+0.255
 pigs+0.250
 which+0.231
bles+0.228
 ju+0.228
Neg logit contributions
 screams-0.215
 cries-0.195
 farewell-0.189
ulously-0.188
night-0.188
Token we
Token ID356
Feature activation-3.00e+00

Pos logit contributions
 chefs+0.058
 ju+0.056
 which+0.050
 pigs+0.049
Which+0.048
Neg logit contributions
 cries-0.079
 screams-0.077
 shouts-0.069
ulously-0.067
aned-0.067
Token play
Token ID711
Feature activation-2.51e+00

Pos logit contributions
 ju+0.086
 chefs+0.085
Which+0.082
 which+0.078
 pigs+0.078
Neg logit contributions
 cries-0.071
 screams-0.068
 shouts-0.058
ow-0.058
night-0.058
Token with
Token ID351
Feature activation-3.76e+00

Pos logit contributions
 ju+0.070
 pigs+0.063
 basil+0.063
 chefs+0.062
 redd+0.062
Neg logit contributions
 cries-0.060
 screams-0.056
night-0.053
 shouts-0.050
>-0.050
Token it
Token ID340
Feature activation+8.98e-01

Pos logit contributions
 ju+0.113
 chefs+0.110
please+0.101
Which+0.099
 which+0.099
Neg logit contributions
 cries-0.089
 screams-0.087
 shouts-0.074
ulously-0.071
night-0.069
Token silly
Token ID14397
Feature activation-5.09e-01

Pos logit contributions
 cries+0.008
 screams+0.008
 shouts+0.007
ulously+0.007
aned+0.007
Neg logit contributions
 chefs-0.007
 ju-0.007
 which-0.006
Which-0.006
 pigs-0.006
Token that
Token ID326
Feature activation-2.21e+00

Pos logit contributions
 ju+0.015
 chefs+0.014
Which+0.013
please+0.013
Ros+0.013
Neg logit contributions
 cries-0.013
 screams-0.013
 shouts-0.011
night-0.011
aned-0.010
Token they
Token ID484
Feature activation-1.30e+00

Pos logit contributions
 chefs+0.055
 ju+0.054
please+0.049
Ros+0.048
Which+0.048
Neg logit contributions
 cries-0.063
 screams-0.062
 shouts-0.055
 hurts-0.051
ulously-0.051
Token couldn
Token ID3521
Feature activation+4.66e+00

Pos logit contributions
 chefs+0.037
 ju+0.036
Which+0.034
 basil+0.032
 which+0.032
Neg logit contributions
 cries-0.034
 screams-0.033
 shouts-0.029
aned-0.028
 yells-0.027
Tokenâ
Token ID22940
Feature activation+4.89e+00

Pos logit contributions
 screams+0.130
 cries+0.130
night+0.123
 farewell+0.121
 shouts+0.118
Neg logit contributions
 chefs-0.101
 which-0.099
 ju-0.098
 especially-0.097
Why-0.097
Token
Token ID26391
Feature activation+9.51e+00

Pos logit contributions
 screams+0.121
 cries+0.120
 shouts+0.105
 yells+0.097
aned+0.095
Neg logit contributions
 ju-0.130
 chefs-0.130
Why-0.128
 which-0.125
please-0.125
Token
Token ID8151
Feature activation-8.42e-01

Pos logit contributions
 cries+0.310
 screams+0.308
 shouts+0.276
aned+0.276
ulously+0.274
Neg logit contributions
 chefs-0.191
 ju-0.184
 which-0.175
 ones-0.161
 pigs-0.158
Tokent
Token ID83
Feature activation+7.79e-01

Pos logit contributions
 ju+0.021
 chefs+0.021
 which+0.020
 pigs+0.018
ters+0.018
Neg logit contributions
 cries-0.023
 screams-0.023
 shouts-0.021
ulously-0.020
night-0.020
Token agree
Token ID4236
Feature activation-5.80e-01

Pos logit contributions
 cries+0.020
 screams+0.019
 shouts+0.016
 cry+0.016
ered+0.016
Neg logit contributions
 ju-0.024
 chefs-0.024
 redd-0.021
Which-0.021
 basil-0.021
Token.
Token ID13
Feature activation+8.70e-01

Pos logit contributions
 ju+0.020
 chefs+0.018
 redd+0.017
 basil+0.017
 pigs+0.017
Neg logit contributions
 cries-0.012
 screams-0.011
 shouts-0.010
am-0.009
rum-0.009
Token He
Token ID679
Feature activation-1.22e+00

Pos logit contributions
 cries+0.021
 screams+0.020
 shouts+0.017
aned+0.017
night+0.017
Neg logit contributions
 chefs-0.026
 ju-0.026
 which-0.024
Which-0.023
 pigs-0.023
Token Let
Token ID3914
Feature activation-1.27e+00

Pos logit contributions
 cries+0.007
 screams+0.007
 shouts+0.006
 farewell+0.006
ulously+0.006
Neg logit contributions
 chefs-0.011
 ju-0.011
please-0.010
 which-0.010
 ones-0.010
Token's
Token ID338
Feature activation-9.24e-01

Pos logit contributions
 chefs+0.045
 ju+0.044
 which+0.042
Which+0.041
 pigs+0.041
Neg logit contributions
 cries-0.023
 screams-0.022
 shouts-0.018
aned-0.017
ulously-0.017
Token go
Token ID467
Feature activation-5.26e-01

Pos logit contributions
 chefs+0.024
 ju+0.023
 which+0.022
Which+0.020
 pigs+0.020
Neg logit contributions
 cries-0.026
 screams-0.025
 shouts-0.022
aned-0.022
night-0.021
Token inside
Token ID2641
Feature activation+5.55e-01

Pos logit contributions
 chefs+0.015
 ju+0.015
Which+0.013
 which+0.013
 pigs+0.013
Neg logit contributions
 cries-0.013
 screams-0.013
 shouts-0.011
 farewell-0.011
aned-0.011
Tokenâ
Token ID22940
Feature activation+4.19e+00

Pos logit contributions
 cries+0.016
 screams+0.016
 shouts+0.014
aned+0.014
ulously+0.014
Neg logit contributions
 chefs-0.014
 ju-0.013
 which-0.012
Which-0.012
 pigs-0.012
Token
Token ID26391
Feature activation+8.99e+00

Pos logit contributions
 screams+0.084
 cries+0.083
 shouts+0.065
 yells+0.059
 jaws+0.058
Neg logit contributions
 ju-0.137
Why-0.132
 which-0.132
line-0.130
please-0.129
Token.
Token ID13
Feature activation+2.23e-02

Pos logit contributions
 cries+0.262
 screams+0.260
 shouts+0.230
aned+0.229
ulously+0.225
Neg logit contributions
 chefs-0.216
 ju-0.213
 which-0.197
Which-0.186
 pigs-0.186
Token
Token ID220
Feature activation+1.85e-01

Pos logit contributions
 cries+0.000
 screams+0.000
 shouts+0.000
 farewell+0.000
ulously+0.000
Neg logit contributions
 chefs-0.001
 ju-0.001
 which-0.001
please-0.001
 ones-0.001
Token
Token ID198
Feature activation-1.92e+00

Pos logit contributions
 cries+0.005
 screams+0.005
 shouts+0.005
aned+0.004
ulously+0.004
Neg logit contributions
 chefs-0.005
 ju-0.005
 which-0.004
Which-0.004
 pigs-0.004
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
 chefs+0.051
 ju+0.050
 which+0.046
 ones+0.044
 pigs+0.044
Neg logit contributions
 cries-0.052
 screams-0.051
 shouts-0.045
aned-0.044
ulously-0.043
TokenAnd
Token ID1870
Feature activation-1.38e+00

Pos logit contributions
 chefs+0.052
 ju+0.047
 ones+0.046
 pigs+0.043
 cartridge+0.043
Neg logit contributions
 screams-0.062
 cries-0.060
 farewell-0.057
ulously-0.057
|-0.057
Tokens
Token ID82
Feature activation-1.47e+00

Pos logit contributions
 ju+0.059
 which+0.058
 chefs+0.055
line+0.053
ters+0.052
Neg logit contributions
 screams-0.072
 cries-0.072
 shouts-0.063
night-0.061
aned-0.061
Token encouragement
Token ID27529
Feature activation-9.09e-01

Pos logit contributions
 chefs+0.040
 ju+0.039
 which+0.036
Which+0.035
 pigs+0.035
Neg logit contributions
 cries-0.039
 screams-0.039
 shouts-0.034
aned-0.033
 farewell-0.033
Token he
Token ID339
Feature activation-4.82e-01

Pos logit contributions
 chefs+0.026
 ju+0.025
 which+0.023
Which+0.023
 pigs+0.023
Neg logit contributions
 cries-0.023
 screams-0.023
 shouts-0.020
aned-0.019
 farewell-0.019
Token didn
Token ID1422
Feature activation+3.39e+00

Pos logit contributions
 chefs+0.011
 ju+0.011
 which+0.010
Which+0.009
 ones+0.009
Neg logit contributions
 cries-0.015
 screams-0.014
 shouts-0.013
aned-0.013
ulously-0.012
Tokenâ
Token ID22940
Feature activation+4.60e+00

Pos logit contributions
 cries+0.095
 screams+0.094
night+0.089
ulously+0.085
 shouts+0.084
Neg logit contributions
 which-0.076
 ju-0.074
 chefs-0.072
 especially-0.071
Why-0.069
Token
Token ID26391
Feature activation+9.21e+00

Pos logit contributions
 screams+0.104
 cries+0.100
 shouts+0.083
 jaws+0.078
 yells+0.077
Neg logit contributions
 ju-0.134
Why-0.132
please-0.126
ters-0.125
line-0.124
Token
Token ID8151
Feature activation-1.55e+00

Pos logit contributions
 cries+0.294
 screams+0.291
 shouts+0.261
aned+0.258
ulously+0.256
Neg logit contributions
 chefs-0.194
 ju-0.193
 which-0.179
 ones-0.165
please-0.163
Tokent
Token ID83
Feature activation+1.73e-01

Pos logit contributions
 ju+0.037
 chefs+0.035
 which+0.035
line+0.032
ters+0.032
Neg logit contributions
 cries-0.046
 screams-0.046
 shouts-0.040
ulously-0.039
night-0.039
Token give
Token ID1577
Feature activation-4.62e+00

Pos logit contributions
 cries+0.005
 screams+0.004
 shouts+0.004
aned+0.004
 farewell+0.004
Neg logit contributions
 chefs-0.005
 ju-0.005
Which-0.004
 pigs-0.004
 basil-0.004
Token up
Token ID510
Feature activation+1.12e+00

Pos logit contributions
 ju+0.155
 chefs+0.154
 which+0.146
 ones+0.141
Which+0.140
Neg logit contributions
 screams-0.089
 cries-0.089
aned-0.073
 shouts-0.073
ulously-0.069
Token.
Token ID13
Feature activation+6.20e-01

Pos logit contributions
 cries+0.025
 screams+0.025
 shouts+0.021
 farewell+0.020
aned+0.020
Neg logit contributions
 chefs-0.035
 ju-0.034
Which-0.031
please-0.031
 pigs-0.031
Token connected
Token ID5884
Feature activation-1.81e+00

Pos logit contributions
 cries+0.073
 screams+0.072
 shouts+0.064
aned+0.062
ulously+0.062
Neg logit contributions
 ju-0.077
 chefs-0.076
 which-0.073
 pigs-0.069
 ones-0.068
Token with
Token ID351
Feature activation-3.28e+00

Pos logit contributions
 ju+0.048
 chefs+0.047
 which+0.045
 ones+0.043
Which+0.042
Neg logit contributions
 cries-0.047
 screams-0.047
 shouts-0.041
aned-0.041
ulously-0.039
Token the
Token ID262
Feature activation+2.73e-01

Pos logit contributions
 chefs+0.097
 ju+0.095
 which+0.087
Which+0.086
please+0.085
Neg logit contributions
 cries-0.081
 screams-0.080
 shouts-0.068
 farewell-0.066
ulously-0.065
Token mosquito
Token ID35446
Feature activation+1.89e+00

Pos logit contributions
 cries+0.009
 screams+0.008
 shouts+0.008
aned+0.008
ulously+0.007
Neg logit contributions
 chefs-0.006
 ju-0.006
 which-0.005
 pigs-0.005
Which-0.005
Tokenâ
Token ID22940
Feature activation+4.83e+00

Pos logit contributions
 cries+0.048
 screams+0.048
aned+0.043
 shouts+0.042
ulously+0.042
Neg logit contributions
 ju-0.049
 chefs-0.049
 which-0.047
 ones-0.044
 pigs-0.044
Token
Token ID26391
Feature activation+9.33e+00

Pos logit contributions
 screams+0.107
 cries+0.106
 shouts+0.090
 yells+0.086
aned+0.083
Neg logit contributions
 ju-0.140
Why-0.135
ters-0.134
please-0.133
 cartridge-0.133
Token
Token ID8151
Feature activation-1.77e+00

Pos logit contributions
 cries+0.266
 screams+0.262
ulously+0.235
 shouts+0.235
aned+0.234
Neg logit contributions
 chefs-0.223
 ju-0.220
 which-0.210
 ones-0.195
please-0.193
Tokens
Token ID82
Feature activation-6.97e-01

Pos logit contributions
 ju+0.046
 which+0.044
 chefs+0.044
ters+0.041
line+0.040
Neg logit contributions
 screams-0.047
 cries-0.047
 shouts-0.041
night-0.040
ulously-0.040
Token body
Token ID1767
Feature activation-4.65e-02

Pos logit contributions
 ju+0.019
 chefs+0.019
 which+0.019
 ones+0.017
 pigs+0.017
Neg logit contributions
 cries-0.017
 screams-0.016
 shouts-0.015
aned-0.014
ulously-0.014
Token.
Token ID13
Feature activation+4.45e-01

Pos logit contributions
 chefs+0.001
 ju+0.001
 which+0.001
 pigs+0.001
 ones+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
aned-0.001
ulously-0.001
Token
Token ID198
Feature activation-1.66e+00

Pos logit contributions
 cries+0.012
 screams+0.012
 shouts+0.010
aned+0.010
night+0.010
Neg logit contributions
 chefs-0.012
 ju-0.012
 which-0.011
Which-0.011
 pigs-0.010
Token comfortable
Token ID6792
Feature activation+1.53e+00

Pos logit contributions
 chefs+0.062
 ju+0.061
Which+0.055
 which+0.054
 pigs+0.053
Neg logit contributions
 cries-0.082
 screams-0.082
 shouts-0.073
night-0.070
 farewell-0.069
Token princess
Token ID21752
Feature activation-1.81e+00

Pos logit contributions
 cries+0.043
 screams+0.043
 shouts+0.038
aned+0.037
night+0.037
Neg logit contributions
 chefs-0.038
 ju-0.038
 which-0.034
Which-0.034
 pigs-0.033
Token of
Token ID286
Feature activation-2.93e+00

Pos logit contributions
 chefs+0.055
 ju+0.055
 which+0.051
Which+0.049
 pigs+0.049
Neg logit contributions
 cries-0.041
 screams-0.040
 shouts-0.034
aned-0.034
ulously-0.033
Token all
Token ID477
Feature activation-2.21e-02

Pos logit contributions
 chefs+0.072
 ju+0.072
 which+0.066
Which+0.063
 pigs+0.063
Neg logit contributions
 cries-0.083
 screams-0.082
 shouts-0.073
aned-0.072
ulously-0.070
Tokenâ
Token ID22940
Feature activation+4.69e+00

Pos logit contributions
 ju+0.001
 chefs+0.001
 which+0.001
 ones+0.001
 pigs+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
aned-0.001
 shouts-0.001
am-0.001
Token
Token ID26391
Feature activation+9.49e+00

Pos logit contributions
 cries+0.103
 screams+0.102
 shouts+0.084
 yells+0.078
aned+0.076
Neg logit contributions
 ju-0.146
 chefs-0.138
please-0.138
ters-0.136
Why-0.135
Token
Token ID126
Feature activation+3.99e+00

Pos logit contributions
 cries+0.244
 screams+0.240
ulously+0.208
aned+0.207
 shouts+0.207
Neg logit contributions
 chefs-0.257
 ju-0.252
 which-0.244
please-0.231
 pigs-0.230
Token
Token ID99
Feature activation-1.48e+00

Pos logit contributions
 cries+0.105
 screams+0.103
ulously+0.093
 shouts+0.091
 yells+0.087
Neg logit contributions
 ju-0.102
 which-0.099
 chefs-0.093
 especially-0.093
please-0.092
Tokenif
Token ID361
Feature activation-2.58e+00

Pos logit contributions
 chefs+0.037
 ju+0.036
 which+0.033
Which+0.032
 pigs+0.032
Neg logit contributions
 cries-0.042
 screams-0.042
 shouts-0.037
aned-0.036
ulously-0.036
Token she
Token ID673
Feature activation-3.69e-01

Pos logit contributions
 chefs+0.065
 ju+0.065
 which+0.060
Which+0.057
 pigs+0.057
Neg logit contributions
 cries-0.072
 screams-0.071
 shouts-0.062
aned-0.061
ulously-0.060
Token only
Token ID691
Feature activation+4.04e-01

Pos logit contributions
 ju+0.009
 chefs+0.009
 which+0.009
 ones+0.008
 especially+0.008
Neg logit contributions
 cries-0.010
 screams-0.009
aned-0.009
ulously-0.008
 shouts-0.008
Token an
Token ID281
Feature activation-1.04e+00

Pos logit contributions
 ju+0.066
 chefs+0.066
 pigs+0.059
please+0.058
 which+0.058
Neg logit contributions
 cries-0.062
 screams-0.061
 shouts-0.053
ulously-0.051
 farewell-0.050
Token elderly
Token ID13830
Feature activation+3.34e+00

Pos logit contributions
 chefs+0.023
 ju+0.022
 which+0.021
 pigs+0.019
 especially+0.019
Neg logit contributions
 cries-0.032
 screams-0.032
aned-0.029
night-0.029
 shouts-0.029
Token person
Token ID1048
Feature activation-2.31e+00

Pos logit contributions
 cries+0.094
 screams+0.094
 shouts+0.082
night+0.078
child+0.077
Neg logit contributions
 ju-0.083
 chefs-0.081
Which-0.078
Or-0.072
Like-0.071
Token walking
Token ID6155
Feature activation+3.45e-01

Pos logit contributions
 chefs+0.045
 which+0.042
 ju+0.042
Why+0.037
 pigs+0.037
Neg logit contributions
 cries-0.077
 screams-0.077
aned-0.070
night-0.069
 farewell-0.069
Token by
Token ID416
Feature activation+4.27e+00

Pos logit contributions
 screams+0.011
 cries+0.011
aned+0.010
night+0.010
azel+0.010
Neg logit contributions
 which-0.007
 ju-0.007
 chefs-0.007
Why-0.007
 ones-0.007
Token on
Token ID319
Feature activation+4.28e+00

Pos logit contributions
 cries+0.121
 screams+0.119
aned+0.108
night+0.108
 shouts+0.105
Neg logit contributions
 chefs-0.103
 which-0.102
 ju-0.095
Why-0.093
 ones-0.093
Token the
Token ID262
Feature activation+1.88e+00

Pos logit contributions
 cries+0.120
 screams+0.119
aned+0.108
 shouts+0.106
night+0.103
Neg logit contributions
 chefs-0.107
 ju-0.105
 which-0.100
 ones-0.094
 pigs-0.094
Token street
Token ID4675
Feature activation+1.68e+00

Pos logit contributions
 cries+0.050
 screams+0.050
aned+0.045
ulously+0.044
 shouts+0.044
Neg logit contributions
 ju-0.049
 chefs-0.048
 which-0.046
 pigs-0.043
 ones-0.043
Token.
Token ID13
Feature activation+1.77e+00

Pos logit contributions
 cries+0.045
 screams+0.045
aned+0.040
night+0.040
ulously+0.039
Neg logit contributions
 chefs-0.042
 which-0.042
 ju-0.041
 ones-0.038
Why-0.038
Token The
Token ID383
Feature activation-1.54e+00

Pos logit contributions
 screams+0.048
 cries+0.047
aned+0.045
night+0.045
unct+0.044
Neg logit contributions
 which-0.044
 chefs-0.042
 ju-0.042
Why-0.039
 pigs-0.039
Token person
Token ID1048
Feature activation-5.23e+00

Pos logit contributions
 chefs+0.036
 ju+0.036
 which+0.033
Which+0.032
 pigs+0.031
Neg logit contributions
 cries-0.047
 screams-0.046
 shouts-0.041
aned-0.039
 farewell-0.039
Token a
Token ID257
Feature activation-4.50e-01

Pos logit contributions
 ju+0.091
 chefs+0.088
 which+0.080
 pigs+0.079
Which+0.079
Neg logit contributions
 cries-0.078
 screams-0.076
 shouts-0.066
night-0.062
ulously-0.062
Token big
Token ID1263
Feature activation+5.14e-02

Pos logit contributions
 chefs+0.011
 ju+0.011
ters+0.010
please+0.009
Why+0.009
Neg logit contributions
 cries-0.013
 screams-0.013
 shouts-0.011
 yells-0.011
 farewell-0.010
Token model
Token ID2746
Feature activation-3.69e+00

Pos logit contributions
 cries+0.002
 screams+0.002
 shouts+0.001
aned+0.001
night+0.001
Neg logit contributions
 chefs-0.001
 ju-0.001
 which-0.001
Which-0.001
 pigs-0.001
Token car
Token ID1097
Feature activation-1.12e+00

Pos logit contributions
 chefs+0.091
 ju+0.088
 which+0.083
Which+0.078
 pigs+0.078
Neg logit contributions
 cries-0.106
 screams-0.105
 shouts-0.093
aned-0.092
ulously-0.090
Token in
Token ID287
Feature activation+3.34e+00

Pos logit contributions
 which+0.023
 chefs+0.021
Why+0.020
 ju+0.019
 ones+0.018
Neg logit contributions
 screams-0.037
 cries-0.037
 farewell-0.034
aned-0.034
ulously-0.033
Token the
Token ID262
Feature activation+2.71e+00

Pos logit contributions
 cries+0.101
 screams+0.099
aned+0.098
night+0.094
 farewell+0.091
Neg logit contributions
 chefs-0.077
 which-0.071
 ones-0.069
 ju-0.068
Why-0.067
Token shop
Token ID6128
Feature activation+8.29e-01

Pos logit contributions
 screams+0.088
aned+0.088
 cries+0.087
iously+0.085
rum+0.083
Neg logit contributions
 ju-0.055
 chefs-0.054
 ones-0.053
 which-0.051
Which-0.051
Token window
Token ID4324
Feature activation+3.15e+00

Pos logit contributions
 screams+0.025
 cries+0.025
ulously+0.024
 farewell+0.024
aned+0.024
Neg logit contributions
 chefs-0.019
 which-0.018
line-0.018
 ones-0.017
 ju-0.016
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
 cries+0.103
 screams+0.103
azel+0.097
 farewell+0.095
aned+0.094
Neg logit contributions
 which-0.065
 chefs-0.059
Why-0.058
line-0.055
 ones-0.053
Token It
Token ID632
Feature activation-9.13e-01

Pos logit contributions
 screams+0.046
 cries+0.046
aned+0.043
ulously+0.041
 shouts+0.039
Neg logit contributions
 ju-0.047
 chefs-0.046
 which-0.043
Which-0.040
 ones-0.039
Token is
Token ID318
Feature activation+1.13e+00

Pos logit contributions
 which+0.026
 ju+0.025
 ones+0.025
Which+0.024
 chefs+0.023
Neg logit contributions
night-0.021
aned-0.020
 screams-0.020
 cries-0.020
 farewell-0.019
Token really
Token ID1107
Feature activation+3.45e+00

Pos logit contributions
 cries+0.100
 screams+0.099
 shouts+0.088
aned+0.087
ulously+0.085
Neg logit contributions
 chefs-0.069
 ju-0.068
 which-0.062
Which-0.059
 pigs-0.058
Token boring
Token ID14262
Feature activation+2.13e+00

Pos logit contributions
 cries+0.102
 screams+0.101
 shouts+0.090
aned+0.088
ulously+0.087
Neg logit contributions
 chefs-0.082
 ju-0.081
 which-0.074
Which-0.071
 pigs-0.070
Token things
Token ID1243
Feature activation-1.83e+00

Pos logit contributions
 cries+0.062
 screams+0.061
 shouts+0.054
aned+0.053
ulously+0.052
Neg logit contributions
 chefs-0.052
 ju-0.051
 which-0.047
 ones-0.045
Which-0.045
Token all
Token ID477
Feature activation+7.51e-01

Pos logit contributions
 chefs+0.059
 ju+0.059
Which+0.055
 pigs+0.054
 basil+0.054
Neg logit contributions
 cries-0.038
 screams-0.036
 shouts-0.032
ow-0.029
am-0.028
Token day
Token ID1110
Feature activation+5.74e+00

Pos logit contributions
 screams+0.022
 cries+0.022
aned+0.021
 farewell+0.020
ulously+0.019
Neg logit contributions
 which-0.018
 ju-0.017
 ones-0.017
 chefs-0.016
Why-0.016
Token.
Token ID13
Feature activation+2.44e+00

Pos logit contributions
 cries+0.166
 screams+0.166
ulously+0.148
aned+0.146
 shouts+0.146
Neg logit contributions
 ju-0.136
 chefs-0.135
 which-0.131
 ones-0.120
 pigs-0.117
Token One
Token ID1881
Feature activation-3.76e+00

Pos logit contributions
 cries+0.067
 screams+0.067
aned+0.060
 shouts+0.059
night+0.056
Neg logit contributions
 ju-0.062
 chefs-0.062
 which-0.059
Which-0.056
 ones-0.056
Token day
Token ID1110
Feature activation+2.88e+00

Pos logit contributions
 ju+0.099
 which+0.097
 chefs+0.096
 especially+0.092
 ones+0.091
Neg logit contributions
 cries-0.101
 screams-0.100
aned-0.094
 shouts-0.089
 yells-0.085
Token,
Token ID11
Feature activation-3.52e+00

Pos logit contributions
 cries+0.086
 screams+0.085
aned+0.082
ulously+0.077
 shouts+0.077
Neg logit contributions
 chefs-0.069
 which-0.064
 ju-0.064
 ones-0.062
Which-0.058
Token the
Token ID262
Feature activation-5.64e-01

Pos logit contributions
 chefs+0.097
 ju+0.096
 which+0.088
Which+0.086
 pigs+0.085
Neg logit contributions
 cries-0.091
 screams-0.090
 shouts-0.078
aned-0.076
ulously-0.075
Token crane
Token ID41175
Feature activation-5.22e+00

Pos logit contributions
 ju+0.012
 chefs+0.012
Which+0.012
 basil+0.012
Ros+0.011
Neg logit contributions
 screams-0.017
 cries-0.017
 shouts-0.015
am-0.015
ulously-0.015
Tokenopard
Token ID15478
Feature activation-2.91e+00

Pos logit contributions
 ju+0.110
Which+0.110
 chefs+0.106
 especially+0.098
 which+0.098
Neg logit contributions
 screams-0.116
 cries-0.113
ow-0.106
am-0.103
 shouts-0.101
Token was
Token ID373
Feature activation+1.91e+00

Pos logit contributions
 chefs+0.078
 ju+0.077
 which+0.071
 pigs+0.068
Which+0.068
Neg logit contributions
 cries-0.077
 screams-0.076
 shouts-0.067
aned-0.066
ulously-0.064
Token brave
Token ID14802
Feature activation+5.90e-01

Pos logit contributions
 cries+0.054
 screams+0.054
 shouts+0.048
aned+0.045
 yells+0.045
Neg logit contributions
 ju-0.048
 chefs-0.048
Which-0.044
 ones-0.042
 which-0.042
Token and
Token ID290
Feature activation+1.62e+00

Pos logit contributions
 cries+0.016
 screams+0.015
 shouts+0.014
aned+0.013
ulously+0.013
Neg logit contributions
 chefs-0.016
 ju-0.016
 which-0.014
 pigs-0.014
Which-0.014
Token ready
Token ID3492
Feature activation+2.78e+00

Pos logit contributions
 cries+0.047
 screams+0.047
 shouts+0.042
 farewell+0.040
aned+0.040
Neg logit contributions
 chefs-0.039
 ju-0.038
 which-0.035
Which-0.034
 ones-0.033
Token to
Token ID284
Feature activation+2.85e+00

Pos logit contributions
 screams+0.090
 cries+0.089
aned+0.083
ulously+0.082
azel+0.080
Neg logit contributions
 which-0.057
 chefs-0.054
 ju-0.054
 ones-0.050
 pigs-0.047
Token protect
Token ID1805
Feature activation-2.67e+00

Pos logit contributions
 cries+0.074
 screams+0.073
aned+0.067
 shouts+0.064
night+0.064
Neg logit contributions
 chefs-0.075
 ju-0.073
 which-0.069
 pigs-0.066
 ones-0.065
Token his
Token ID465
Feature activation+1.41e+00

Pos logit contributions
 chefs+0.063
 ju+0.062
 which+0.057
Which+0.055
 pigs+0.054
Neg logit contributions
 cries-0.079
 screams-0.078
 shouts-0.070
aned-0.069
ulously-0.067
Token friends
Token ID2460
Feature activation-1.87e-01

Pos logit contributions
 cries+0.045
 screams+0.045
aned+0.043
ulously+0.041
 shouts+0.041
Neg logit contributions
 chefs-0.029
 ju-0.027
 pigs-0.025
 ones-0.025
 which-0.024
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
 which+0.004
 chefs+0.004
 ju+0.004
ters+0.004
 pigs+0.004
Neg logit contributions
 screams-0.005
 cries-0.005
aned-0.005
ulously-0.005
night-0.005
Token
Token ID198
Feature activation-1.12e+00

Pos logit contributions
 cries+0.044
 screams+0.044
aned+0.039
 shouts+0.038
night+0.038
Neg logit contributions
 chefs-0.033
 ju-0.033
 which-0.030
 pigs-0.029
Which-0.029
Token in
Token ID287
Feature activation+2.99e+00

Pos logit contributions
 cries+0.021
 screams+0.020
 shouts+0.018
aned+0.017
night+0.017
Neg logit contributions
 chefs-0.019
 ju-0.019
 which-0.017
Which-0.017
 pigs-0.017
Token her
Token ID607
Feature activation+3.73e+00

Pos logit contributions
 cries+0.084
 screams+0.083
aned+0.077
night+0.075
 shouts+0.074
Neg logit contributions
 chefs-0.074
 ju-0.072
 which-0.070
 ones-0.067
Which-0.066
Token room
Token ID2119
Feature activation+3.55e+00

Pos logit contributions
 screams+0.102
 cries+0.101
aned+0.093
 shouts+0.091
 farewell+0.087
Neg logit contributions
 chefs-0.097
 ju-0.093
 which-0.090
 ones-0.085
Which-0.085
Token.
Token ID13
Feature activation+2.54e+00

Pos logit contributions
 cries+0.089
 screams+0.088
 shouts+0.076
aned+0.075
ulously+0.073
Neg logit contributions
 chefs-0.100
 ju-0.099
 which-0.093
Which-0.089
 pigs-0.088
Token She
Token ID1375
Feature activation-9.06e-01

Pos logit contributions
 cries+0.063
 screams+0.062
 shouts+0.054
aned+0.053
ulously+0.052
Neg logit contributions
 chefs-0.072
 ju-0.071
 which-0.066
 pigs-0.064
Which-0.064
Token did
Token ID750
Feature activation+4.95e+00

Pos logit contributions
 chefs+0.020
 ju+0.019
 which+0.018
Which+0.017
please+0.017
Neg logit contributions
 cries-0.028
 screams-0.028
 shouts-0.025
 farewell-0.025
aned-0.025
Token not
Token ID407
Feature activation-4.05e-01

Pos logit contributions
 cries+0.140
 screams+0.138
 shouts+0.122
aned+0.119
ulously+0.117
Neg logit contributions
 chefs-0.124
 ju-0.123
 pigs-0.110
 which-0.109
Which-0.108
Token know
Token ID760
Feature activation-5.50e-01

Pos logit contributions
 chefs+0.009
 ju+0.009
Which+0.008
 pigs+0.008
 which+0.008
Neg logit contributions
 cries-0.012
 screams-0.012
 shouts-0.011
night-0.010
aned-0.010
Token what
Token ID644
Feature activation-5.71e+00

Pos logit contributions
 ju+0.017
please+0.016
 chefs+0.015
 cartridge+0.015
Ros+0.015
Neg logit contributions
 cries-0.014
 screams-0.013
 shouts-0.011
ered-0.011
ow-0.010
Token was
Token ID373
Feature activation+1.34e+00

Pos logit contributions
 ju+0.169
 chefs+0.165
ters+0.150
 pigs+0.150
line+0.149
Neg logit contributions
 cries-0.135
 screams-0.131
 shouts-0.116
night-0.108
 hurts-0.108
Token on
Token ID319
Feature activation+2.64e+00

Pos logit contributions
 cries+0.040
 screams+0.040
 shouts+0.035
aned+0.035
ulously+0.034
Neg logit contributions
 chefs-0.032
 ju-0.031
 which-0.029
Which-0.027
 pigs-0.027
Token a
Token ID257
Feature activation+4.01e-01

Pos logit contributions
 screams+0.090
 cries+0.088
aned+0.081
 shouts+0.079
 farewell+0.077
Neg logit contributions
 chefs-0.079
 which-0.077
 ju-0.074
 ones-0.072
Why-0.070
Token house
Token ID2156
Feature activation+8.70e-01

Pos logit contributions
 cries+0.011
 screams+0.011
 shouts+0.010
 farewell+0.010
night+0.009
Neg logit contributions
 chefs-0.010
 ju-0.009
ters-0.009
Which-0.009
 which-0.009
Token.
Token ID13
Feature activation+2.84e+00

Pos logit contributions
 cries+0.020
 screams+0.019
 shouts+0.017
aned+0.016
night+0.016
Neg logit contributions
 ju-0.026
 chefs-0.026
Which-0.024
 pigs-0.023
please-0.023
Token He
Token ID679
Feature activation-9.49e-02

Pos logit contributions
 cries+0.065
 screams+0.065
 shouts+0.055
aned+0.055
ulously+0.053
Neg logit contributions
 ju-0.086
 chefs-0.086
 which-0.080
Which-0.077
 ones-0.077
Token sn
Token ID3013
Feature activation+1.15e-01

Pos logit contributions
 chefs+0.002
 ju+0.002
 which+0.002
 pigs+0.002
Which+0.002
Neg logit contributions
 cries-0.003
 screams-0.003
 shouts-0.003
aned-0.003
 farewell-0.002
Tokenuck
Token ID1347
Feature activation+6.44e-01

Pos logit contributions
 cries+0.003
 screams+0.003
 shouts+0.002
aned+0.002
 yells+0.002
Neg logit contributions
 chefs-0.003
 ju-0.003
 which-0.003
Which-0.003
 ones-0.003
Token around
Token ID1088
Feature activation+2.83e+00

Pos logit contributions
 screams+0.018
 cries+0.018
 shouts+0.016
aned+0.016
azel+0.015
Neg logit contributions
 chefs-0.016
 which-0.015
 ju-0.015
 ones-0.014
 pigs-0.014
Token the
Token ID262
Feature activation+2.18e+00

Pos logit contributions
 screams+0.084
 cries+0.083
aned+0.075
 shouts+0.075
ulously+0.073
Neg logit contributions
 chefs-0.068
 ju-0.064
 which-0.063
 ones-0.058
 pigs-0.058
Token house
Token ID2156
Feature activation-3.12e-02

Pos logit contributions
 cries+0.058
 screams+0.057
aned+0.051
 shouts+0.051
ulously+0.050
Neg logit contributions
 chefs-0.059
 ju-0.058
 which-0.053
 pigs-0.051
 ones-0.051
Token and
Token ID290
Feature activation+2.67e+00

Pos logit contributions
 chefs+0.001
 ju+0.001
 which+0.001
Which+0.001
 pigs+0.001
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
aned-0.001
ulously-0.001
Token tried
Token ID3088
Feature activation+1.47e+00

Pos logit contributions
 cries+0.074
 screams+0.072
 shouts+0.064
aned+0.061
night+0.060
Neg logit contributions
 chefs-0.069
 ju-0.067
Which-0.062
 which-0.061
 pigs-0.060
Token to
Token ID284
Feature activation+1.71e+00

Pos logit contributions
 cries+0.021
 screams+0.020
 shouts+0.018
aned+0.017
 farewell+0.017
Neg logit contributions
 chefs-0.023
 ju-0.022
 which-0.020
 pigs-0.020
Which-0.020
Token keep
Token ID1394
Feature activation-1.15e+00

Pos logit contributions
 cries+0.049
 screams+0.048
 shouts+0.043
aned+0.042
night+0.041
Neg logit contributions
 chefs-0.042
 ju-0.042
 which-0.039
Which-0.036
 pigs-0.036
Token it
Token ID340
Feature activation+2.14e+00

Pos logit contributions
 ju+0.034
 chefs+0.034
Which+0.031
 pigs+0.030
please+0.030
Neg logit contributions
 cries-0.028
 screams-0.027
 shouts-0.024
 farewell-0.023
ulously-0.023
Token forever
Token ID8097
Feature activation+6.62e+00

Pos logit contributions
 cries+0.057
 screams+0.055
 shouts+0.048
 farewell+0.048
night+0.048
Neg logit contributions
 chefs-0.057
 ju-0.055
Which-0.051
 pigs-0.050
please-0.050
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
 cries+0.159
 screams+0.156
 shouts+0.134
aned+0.130
 farewell+0.128
Neg logit contributions
 chefs-0.195
 ju-0.192
 which-0.176
Which-0.174
 pigs-0.173
Token
Token ID220
Feature activation+7.31e-01

Pos logit contributions
 screams+0.044
 cries+0.042
aned+0.042
rum+0.038
unct+0.038
Neg logit contributions
 ju-0.042
 which-0.041
Of-0.037
 chefs-0.037
Anything-0.036
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
 cries+0.022
 screams+0.022
night+0.020
 shouts+0.019
aned+0.019
Neg logit contributions
 chefs-0.016
 ju-0.016
 which-0.015
Which-0.014
ters-0.014
Token
Token ID198
Feature activation-1.56e+00

Pos logit contributions
 ju+0.028
 chefs+0.028
 which+0.026
Which+0.024
Why+0.024
Neg logit contributions
 cries-0.038
 screams-0.037
 shouts-0.033
aned-0.033
night-0.032
TokenThe
Token ID464
Feature activation-9.52e-01

Pos logit contributions
 chefs+0.038
 ju+0.037
 pigs+0.033
 which+0.033
 ones+0.033
Neg logit contributions
 cries-0.044
 screams-0.044
ulously-0.039
 shouts-0.039
 farewell-0.039
Token key
Token ID1994
Feature activation-3.90e+00

Pos logit contributions
 chefs+0.023
 ju+0.023
 which+0.020
 pigs+0.020
please+0.020
Neg logit contributions
 cries-0.028
 screams-0.028
 farewell-0.024
 shouts-0.024
night-0.024
Token was
Token ID373
Feature activation+1.76e+00

Pos logit contributions
 ju+0.101
 chefs+0.100
 which+0.097
 ones+0.089
Which+0.088
Neg logit contributions
 cries-0.104
 screams-0.102
 shouts-0.090
aned-0.087
night-0.086
Token to
Token ID284
Feature activation+3.50e+00

Pos logit contributions
 screams+0.042
 cries+0.042
aned+0.041
ulously+0.040
night+0.040
Neg logit contributions
 chefs-0.032
 which-0.032
 pigs-0.031
 watering-0.030
 ju-0.029
Token swim
Token ID9422
Feature activation+1.88e-02

Pos logit contributions
 screams+0.103
 cries+0.102
aned+0.100
ulously+0.095
night+0.094
Neg logit contributions
 ju-0.078
 chefs-0.075
 which-0.073
 pigs-0.071
 especially-0.068
Token away
Token ID1497
Feature activation+5.43e+00

Pos logit contributions
 cries+0.000
 screams+0.000
 shouts+0.000
aned+0.000
ulously+0.000
Neg logit contributions
 chefs-0.001
 ju-0.001
 which-0.000
Which-0.000
 pigs-0.000
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
 screams+0.151
 cries+0.151
ulously+0.137
aned+0.136
 shouts+0.132
Neg logit contributions
 chefs-0.134
 ju-0.134
 which-0.130
 ones-0.119
 pigs-0.117
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
 cries+0.037
 screams+0.037
 shouts+0.032
aned+0.032
ulously+0.032
Neg logit contributions
 chefs-0.032
 ju-0.032
 which-0.030
Which-0.028
 pigs-0.028
Token
Token ID198
Feature activation-1.94e+00

Pos logit contributions
 chefs+0.029
 ju+0.029
 which+0.028
Ros+0.026
Which+0.026
Neg logit contributions
 cries-0.054
 screams-0.054
aned-0.048
 shouts-0.048
night-0.047
TokenJoe
Token ID19585
Feature activation-1.50e+00

Pos logit contributions
 chefs+0.045
 ju+0.043
 ones+0.039
 pigs+0.039
 which+0.038
Neg logit contributions
 screams-0.056
 cries-0.056
aned-0.051
ulously-0.051
 farewell-0.051
Tokeny
Token ID88
Feature activation-9.29e-01

Pos logit contributions
 ju+0.031
 chefs+0.031
 which+0.031
 pigs+0.029
ters+0.028
Neg logit contributions
 cries-0.046
 screams-0.046
 shouts-0.041
night-0.039
 farewell-0.039
Token waved
Token ID26834
Feature activation-5.04e-02

Pos logit contributions
 chefs+0.022
 ju+0.022
 which+0.021
 especially+0.020
 pigs+0.020
Neg logit contributions
 cries-0.025
 screams-0.025
aned-0.022
 shouts-0.022
ulously-0.022
Token goodbye
Token ID24829
Feature activation+5.23e+00

Pos logit contributions
 chefs+0.002
 ju+0.002
 which+0.002
Which+0.002
 pigs+0.002
Neg logit contributions
 cries-0.001
 screams-0.001
 shouts-0.001
aned-0.001
ulously-0.001
Token to
Token ID284
Feature activation+1.87e+00

Pos logit contributions
 cries+0.148
 screams+0.148
 shouts+0.131
ulously+0.129
aned+0.129
Neg logit contributions
 ju-0.127
 chefs-0.127
 which-0.121
 ones-0.112
 pigs-0.111
Token was
Token ID373
Feature activation+2.14e+00

Pos logit contributions
 cries+0.053
 screams+0.052
 shouts+0.046
aned+0.045
ulously+0.044
Neg logit contributions
 chefs-0.048
 ju-0.047
 which-0.044
Which-0.042
 pigs-0.042
Token ready
Token ID3492
Feature activation+3.36e+00

Pos logit contributions
 cries+0.063
 screams+0.062
 shouts+0.055
aned+0.054
ulously+0.053
Neg logit contributions
 chefs-0.051
 ju-0.050
 which-0.046
Which-0.044
 pigs-0.044
Token to
Token ID284
Feature activation+3.24e+00

Pos logit contributions
 cries+0.090
 screams+0.089
 shouts+0.078
aned+0.077
ulously+0.075
Neg logit contributions
 chefs-0.089
 ju-0.088
 which-0.082
Which-0.078
 pigs-0.077
Token start
Token ID923
Feature activation+1.92e+00

Pos logit contributions
 cries+0.094
 screams+0.092
aned+0.084
 shouts+0.082
night+0.080
Neg logit contributions
 chefs-0.076
 ju-0.075
 which-0.072
 pigs-0.065
Why-0.064
Token reading
Token ID3555
Feature activation+3.24e-01

Pos logit contributions
 cries+0.053
 screams+0.053
aned+0.047
 shouts+0.047
ulously+0.045
Neg logit contributions
 chefs-0.049
 ju-0.048
 which-0.045
 ones-0.043
Which-0.042
Token and
Token ID290
Feature activation+1.78e+00

Pos logit contributions
 cries+0.008
 screams+0.008
 shouts+0.007
aned+0.007
 farewell+0.007
Neg logit contributions
 chefs-0.009
 ju-0.009
 which-0.008
Which-0.008
 pigs-0.008
Token learning
Token ID4673
Feature activation-1.54e+00

Pos logit contributions
 cries+0.052
 screams+0.051
aned+0.046
 shouts+0.045
ulously+0.044
Neg logit contributions
 chefs-0.043
 ju-0.042
 which-0.039
 ones-0.037
Which-0.037
Token new
Token ID649
Feature activation-1.33e+00

Pos logit contributions
 chefs+0.039
 ju+0.039
 which+0.035
Which+0.034
 pigs+0.034
Neg logit contributions
 cries-0.043
 screams-0.042
 shouts-0.037
aned-0.036
 farewell-0.036
Token words
Token ID2456
Feature activation-8.41e-01

Pos logit contributions
 chefs+0.032
 ju+0.031
 which+0.029
 ones+0.028
Which+0.028
Neg logit contributions
 cries-0.039
 screams-0.038
 shouts-0.034
aned-0.034
ulously-0.033
Token.
Token ID13
Feature activation+1.66e+00

Pos logit contributions
 chefs+0.029
 ju+0.028
please+0.026
 pigs+0.026
Which+0.026
Neg logit contributions
 cries-0.016
 screams-0.015
 shouts-0.013
 farewell-0.012
night-0.012
Token She
Token ID1375
Feature activation-8.66e-01

Pos logit contributions
 screams+0.046
 cries+0.046
aned+0.041
 shouts+0.040
night+0.039
Neg logit contributions
 ju-0.041
 chefs-0.040
 which-0.038
Which-0.037
 pigs-0.036
Token them
Token ID606
Feature activation-3.08e-01

Pos logit contributions
 ju+0.056
 chefs+0.056
please+0.051
Ros+0.049
Which+0.048
Neg logit contributions
 cries-0.088
 screams-0.085
 shouts-0.077
 farewell-0.074
ulously-0.074
Token around
Token ID1088
Feature activation+3.36e+00

Pos logit contributions
 chefs+0.008
 ju+0.008
 which+0.008
 ones+0.007
 pigs+0.007
Neg logit contributions
 screams-0.008
 cries-0.008
 shouts-0.007
aned-0.007
ulously-0.007
Token,
Token ID11
Feature activation-2.48e+00

Pos logit contributions
 cries+0.082
 screams+0.081
 shouts+0.069
aned+0.065
ulously+0.065
Neg logit contributions
 ju-0.099
 chefs-0.097
Which-0.089
please-0.088
 which-0.087
Token breaking
Token ID7163
Feature activation-1.26e+00

Pos logit contributions
 ju+0.058
 chefs+0.058
Which+0.052
please+0.052
Ros+0.050
Neg logit contributions
 cries-0.077
 screams-0.076
 shouts-0.068
 yells-0.063
aned-0.063
Token them
Token ID606
Feature activation+1.67e-01

Pos logit contributions
 ju+0.034
 chefs+0.032
please+0.031
Which+0.030
Ros+0.030
Neg logit contributions
 cries-0.035
 screams-0.034
 shouts-0.031
 yells-0.029
aned-0.029
Token and
Token ID290
Feature activation+1.58e+00

Pos logit contributions
 cries+0.004
 screams+0.004
night+0.004
 farewell+0.004
ulously+0.004
Neg logit contributions
 chefs-0.004
 which-0.004
 ju-0.004
ters-0.004
 ones-0.003
Token making
Token ID1642
Feature activation-3.02e+00

Pos logit contributions
 cries+0.044
 screams+0.043
 shouts+0.038
 yells+0.035
aned+0.035
Neg logit contributions
 ju-0.043
 chefs-0.042
Which-0.039
 redd-0.037
umber-0.037
Token them
Token ID606
Feature activation-2.08e-01

Pos logit contributions
 chefs+0.068
 ju+0.065
 which+0.061
 pigs+0.057
 ones+0.056
Neg logit contributions
 cries-0.088
 screams-0.088
aned-0.083
night-0.081
 shouts-0.079
Token dirty
Token ID11841
Feature activation+1.10e+00

Pos logit contributions
 chefs+0.005
 ju+0.005
 which+0.005
ters+0.004
 if+0.004
Neg logit contributions
 screams-0.005
 cries-0.005
night-0.005
azel-0.005
aned-0.005
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
 cries+0.027
 screams+0.027
 shouts+0.023
aned+0.023
ulously+0.022
Neg logit contributions
 chefs-0.031
 ju-0.031
 which-0.029
Which-0.028
 pigs-0.028
Token Tom
Token ID4186
Feature activation+1.12e+00

Pos logit contributions
 cries+0.027
 screams+0.027
 shouts+0.023
aned+0.022
ulously+0.022
Neg logit contributions
 chefs-0.028
 ju-0.028
 which-0.025
Which-0.025
 pigs-0.025
Token trucks
Token ID13960
Feature activation-2.98e+00

Pos logit contributions
 cries+0.036
 screams+0.035
 shouts+0.032
 yells+0.030
ulously+0.028
Neg logit contributions
 ju-0.035
 chefs-0.035
umber-0.032
please-0.031
 cartridge-0.031
Token in
Token ID287
Feature activation+2.54e+00

Pos logit contributions
 ju+0.093
 chefs+0.091
Which+0.083
please+0.081
 pigs+0.080
Neg logit contributions
 cries-0.069
 screams-0.067
 shouts-0.059
am-0.056
aned-0.055
Token their
Token ID511
Feature activation+2.14e+00

Pos logit contributions
 cries+0.048
 screams+0.047
ulously+0.041
 shouts+0.039
|+0.037
Neg logit contributions
 ju-0.090
 chefs-0.085
please-0.083
 thy-0.079
 cartridge-0.077
Token room
Token ID2119
Feature activation+2.94e+00

Pos logit contributions
 cries+0.051
 screams+0.050
 shouts+0.043
aned+0.041
ulously+0.041
Neg logit contributions
 chefs-0.063
 ju-0.063
 which-0.058
Which-0.057
 pigs-0.056
Token.
Token ID13
Feature activation+2.21e+00

Pos logit contributions
 cries+0.070
 screams+0.069
 shouts+0.059
aned+0.058
ulously+0.056
Neg logit contributions
 chefs-0.086
 ju-0.086
 which-0.079
Which-0.077
 pigs-0.077
Token Some
Token ID2773
Feature activation-5.14e+00

Pos logit contributions
 cries+0.044
 screams+0.042
 shouts+0.040
 yells+0.035
am+0.035
Neg logit contributions
 ju-0.075
 chefs-0.075
 queens-0.070
 cartridge-0.068
please-0.067
Token are
Token ID389
Feature activation-1.07e+00

Pos logit contributions
 ju+0.135
 chefs+0.129
 basil+0.115
 redd+0.114
please+0.114
Neg logit contributions
 cries-0.151
 screams-0.148
 shouts-0.134
am-0.126
 yells-0.126
Token big
Token ID1263
Feature activation-1.36e+00

Pos logit contributions
 ju+0.027
 chefs+0.026
Anything+0.024
Which+0.024
 thy+0.024
Neg logit contributions
 cries-0.029
 screams-0.028
 shouts-0.027
 yells-0.025
am-0.025
Token,
Token ID11
Feature activation-3.53e+00

Pos logit contributions
 ju+0.040
 chefs+0.038
please+0.036
Which+0.035
Ros+0.035
Neg logit contributions
 cries-0.035
 screams-0.034
 shouts-0.030
 yells-0.027
 hurts-0.026
Token some
Token ID617
Feature activation-3.89e+00

Pos logit contributions
please+0.118
umber+0.111
 groom+0.110
 cartridge+0.106
Anything+0.104
Neg logit contributions
 cries-0.066
 screams-0.060
ulously-0.057
 shouts-0.055
 opens-0.055
Token are
Token ID389
Feature activation-5.71e-01

Pos logit contributions
 ju+0.122
 chefs+0.118
please+0.110
Which+0.107
 redd+0.106
Neg logit contributions
 cries-0.096
 screams-0.092
 shouts-0.082
 yells-0.076
 hurts-0.075
Token Lily
Token ID20037
Feature activation+7.74e-01

Pos logit contributions
 ju+0.080
 chefs+0.079
 pigs+0.069
please+0.068
ters+0.067
Neg logit contributions
 cries-0.108
 screams-0.104
night-0.093
 shouts-0.092
ulously-0.090
Token's
Token ID338
Feature activation-1.07e+00

Pos logit contributions
 screams+0.022
rum+0.021
 cries+0.021
 farewell+0.021
aned+0.021
Neg logit contributions
 chefs-0.019
 ju-0.017
 which-0.017
 especially-0.016
please-0.016
Token friend
Token ID1545
Feature activation-5.13e-01

Pos logit contributions
 ju+0.027
 chefs+0.027
Which+0.024
 which+0.024
please+0.024
Neg logit contributions
 cries-0.030
 screams-0.029
night-0.025
 shouts-0.025
 farewell-0.024
Token,
Token ID11
Feature activation-3.46e+00

Pos logit contributions
 ju+0.015
 chefs+0.014
 which+0.013
Which+0.013
Or+0.013
Neg logit contributions
 cries-0.013
 screams-0.012
 shouts-0.011
night-0.011
am-0.010
Token Tim
Token ID5045
Feature activation+6.70e-02

Pos logit contributions
 ju+0.087
 chefs+0.085
 which+0.077
Which+0.076
 pigs+0.075
Neg logit contributions
 cries-0.097
 screams-0.095
 shouts-0.085
night-0.081
 farewell-0.080
Token,
Token ID11
Feature activation-4.14e+00

Pos logit contributions
 cries+0.002
 screams+0.002
 shouts+0.002
aned+0.002
 farewell+0.002
Neg logit contributions
 chefs-0.002
 ju-0.002
 which-0.001
Which-0.001
 pigs-0.001
Token came
Token ID1625
Feature activation-2.48e+00

Pos logit contributions
 chefs+0.094
 ju+0.090
 which+0.085
Which+0.079
 pigs+0.079
Neg logit contributions
 cries-0.128
 screams-0.128
aned-0.115
 shouts-0.113
 farewell-0.111
Token to
Token ID284
Feature activation+2.38e+00

Pos logit contributions
 chefs+0.052
 which+0.046
please+0.045
 especially+0.045
 ju+0.044
Neg logit contributions
 screams-0.081
 cries-0.079
aned-0.073
 shouts-0.071
ulously-0.070
Token play
Token ID711
Feature activation-5.46e-01

Pos logit contributions
 cries+0.061
 screams+0.059
 shouts+0.053
night+0.051
 farewell+0.051
Neg logit contributions
 ju-0.066
 chefs-0.064
 which-0.059
ters-0.058
Which-0.057
Token with
Token ID351
Feature activation-2.07e+00

Pos logit contributions
 ju+0.015
 chefs+0.014
 pigs+0.013
Which+0.013
 redd+0.013
Neg logit contributions
 cries-0.015
 screams-0.014
 shouts-0.013
night-0.012
am-0.012
Token her
Token ID607
Feature activation+2.00e+00

Pos logit contributions
 chefs+0.060
 ju+0.059
 which+0.055
Which+0.053
 pigs+0.053
Neg logit contributions
 cries-0.051
 screams-0.050
 shouts-0.044
aned-0.043
ulously-0.042
Token calm
Token ID9480
Feature activation+3.31e+00

Pos logit contributions
 cries+0.053
 screams+0.051
 shouts+0.044
ered+0.043
 cry+0.043
Neg logit contributions
 ju-0.059
 chefs-0.058
Which-0.056
 redd-0.053
 basil-0.052
Token down
Token ID866
Feature activation+1.77e+00

Pos logit contributions
 cries+0.078
 screams+0.078
aned+0.069
 shouts+0.066
ulously+0.066
Neg logit contributions
 chefs-0.095
 ju-0.092
 which-0.090
 ones-0.087
 pigs-0.086
Token the
Token ID262
Feature activation+1.65e+00

Pos logit contributions
 cries+0.049
 screams+0.048
 shouts+0.042
aned+0.042
ulously+0.041
Neg logit contributions
 chefs-0.045
 ju-0.045
 which-0.042
 pigs-0.040
Which-0.040
Token animals
Token ID4695
Feature activation-1.75e+00

Pos logit contributions
 cries+0.055
 screams+0.054
aned+0.051
night+0.050
ulously+0.050
Neg logit contributions
 chefs-0.031
 ju-0.030
 pigs-0.028
 which-0.027
 ones-0.027
Token and
Token ID290
Feature activation+1.82e+00

Pos logit contributions
 chefs+0.045
 ju+0.044
 which+0.042
 pigs+0.039
 ones+0.039
Neg logit contributions
 cries-0.047
 screams-0.047
 shouts-0.042
aned-0.041
ulously-0.041
Token put
Token ID1234
Feature activation-3.94e+00

Pos logit contributions
 cries+0.052
 screams+0.051
 shouts+0.045
 farewell+0.042
night+0.042
Neg logit contributions
 chefs-0.046
 ju-0.046
Which-0.042
 which-0.041
Ros-0.040
Token them
Token ID606
Feature activation-1.11e+00

Pos logit contributions
 chefs+0.110
 ju+0.108
please+0.101
Which+0.100
Ros+0.100
Neg logit contributions
 cries-0.099
 screams-0.095
 shouts-0.085
 farewell-0.082
ulously-0.082
Token back
Token ID736
Feature activation+2.87e+00

Pos logit contributions
 chefs+0.029
 ju+0.029
 which+0.027
 pigs+0.026
 ones+0.025
Neg logit contributions
 cries-0.030
 screams-0.030
 shouts-0.026
aned-0.026
ulously-0.025
Token in
Token ID287
Feature activation+1.76e+00

Pos logit contributions
 screams+0.091
 cries+0.091
 shouts+0.081
aned+0.079
ulously+0.078
Neg logit contributions
 chefs-0.062
 ju-0.060
 which-0.059
 ones-0.053
 pigs-0.053
Token the
Token ID262
Feature activation+1.73e+00

Pos logit contributions
 cries+0.041
 screams+0.041
 shouts+0.035
ulously+0.034
 farewell+0.034
Neg logit contributions
 ju-0.052
 chefs-0.052
Which-0.047
please-0.047
 which-0.047
Token cages
Token ID37933
Feature activation-2.05e+00

Pos logit contributions
 cries+0.046
 screams+0.046
aned+0.044
rum+0.041
ulously+0.040
Neg logit contributions
 ju-0.044
 chefs-0.044
 pigs-0.041
 ones-0.041
 which-0.040
Token on
Token ID319
Feature activation+3.92e+00

Pos logit contributions
 cries+0.042
 screams+0.042
 shouts+0.038
aned+0.037
ulously+0.036
Neg logit contributions
 chefs-0.033
 ju-0.033
 which-0.031
 pigs-0.029
Which-0.029
Token her
Token ID607
Feature activation+3.28e+00

Pos logit contributions
 cries+0.107
 screams+0.106
 shouts+0.095
aned+0.094
night+0.092
Neg logit contributions
 chefs-0.100
 ju-0.098
 which-0.093
 ones-0.088
 pigs-0.088
Token hips
Token ID21497
Feature activation+5.79e+00

Pos logit contributions
 screams+0.082
ulously+0.081
 cries+0.080
aned+0.079
 shouts+0.075
Neg logit contributions
 which-0.087
 ju-0.082
 chefs-0.079
 pigs-0.077
 ones-0.077
Token and
Token ID290
Feature activation+8.79e-01

Pos logit contributions
 cries+0.152
 screams+0.148
aned+0.129
 shouts+0.129
night+0.126
Neg logit contributions
 chefs-0.157
 ju-0.155
Which-0.140
 which-0.137
 pigs-0.136
Token said
Token ID531
Feature activation+9.71e-01

Pos logit contributions
 cries+0.024
 screams+0.023
 shouts+0.021
aned+0.020
night+0.019
Neg logit contributions
 chefs-0.023
 ju-0.023
 which-0.021
Which-0.021
 pigs-0.020
Token,
Token ID11
Feature activation-4.12e+00

Pos logit contributions
 cries+0.022
 screams+0.022
 shouts+0.018
 farewell+0.018
night+0.018
Neg logit contributions
 chefs-0.030
 ju-0.030
Which-0.027
 which-0.027
 pigs-0.027
Token "
Token ID366
Feature activation-8.10e+00

Pos logit contributions
 chefs+0.098
 ju+0.094
 richest+0.085
 queens+0.084
Which+0.083
Neg logit contributions
 cries-0.125
 screams-0.123
 shouts-0.111
 farewell-0.107
aned-0.107
TokenIt
Token ID1026
Feature activation-9.86e-01

Pos logit contributions
 chefs+0.188
 ju+0.160
 pigs+0.154
 captains+0.144
 builder+0.144
Neg logit contributions
 screams-0.243
 cries-0.243
ulously-0.231
night-0.225
 farewell-0.220
Token's
Token ID338
Feature activation-1.27e+00

Pos logit contributions
 ju+0.030
 chefs+0.030
 which+0.029
 ones+0.028
Which+0.028
Neg logit contributions
 screams-0.021
 cries-0.021
aned-0.018
 shouts-0.017
 farewell-0.017
Token time
Token ID640
Feature activation+3.34e+00

Pos logit contributions
 chefs+0.025
 ju+0.025
 which+0.023
Which+0.021
 pigs+0.021
Neg logit contributions
 cries-0.043
 screams-0.043
 shouts-0.038
aned-0.038
 farewell-0.037
Token for
Token ID329
Feature activation-6.27e-01

Pos logit contributions
 screams+0.112
 cries+0.111
ulously+0.109
aned+0.107
|+0.103
Neg logit contributions
 which-0.062
 chefs-0.059
 if-0.053
 but-0.052
 ju-0.050
Token again
Token ID757
Feature activation+4.14e+00

Pos logit contributions
 cries+0.116
 screams+0.114
 shouts+0.098
 farewell+0.098
ulously+0.097
Neg logit contributions
 chefs-0.113
 ju-0.110
Which-0.101
 which-0.099
please-0.098
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
 cries+0.100
 screams+0.098
 shouts+0.085
aned+0.083
ulously+0.081
Neg logit contributions
 chefs-0.120
 ju-0.119
 which-0.111
Which-0.107
 pigs-0.107
Token He
Token ID679
Feature activation-1.03e+00

Pos logit contributions
 screams+0.029
 cries+0.029
aned+0.027
 shouts+0.026
night+0.025
Neg logit contributions
 ju-0.026
 chefs-0.025
 which-0.024
Anything-0.023
Which-0.023
Token was
Token ID373
Feature activation+1.50e+00

Pos logit contributions
 ju+0.023
 which+0.022
 chefs+0.021
 especially+0.021
Or+0.020
Neg logit contributions
 cries-0.030
 screams-0.029
aned-0.027
 shouts-0.027
rum-0.027
Token never
Token ID1239
Feature activation+8.14e-01

Pos logit contributions
 cries+0.047
 screams+0.046
 shouts+0.041
aned+0.040
night+0.040
Neg logit contributions
 ju-0.033
 chefs-0.033
 which-0.031
Which-0.029
 pigs-0.028
Token put
Token ID1234
Feature activation-4.38e+00

Pos logit contributions
 cries+0.025
 screams+0.025
aned+0.023
 shouts+0.022
ulously+0.022
Neg logit contributions
 ju-0.018
 chefs-0.018
 which-0.017
please-0.015
 queens-0.015
Token in
Token ID287
Feature activation+5.93e-01

Pos logit contributions
 chefs+0.133
 ju+0.129
Which+0.122
 pigs+0.121
please+0.121
Neg logit contributions
 cries-0.100
 screams-0.095
 shouts-0.083
 farewell-0.081
night-0.080
Token a
Token ID257
Feature activation-6.70e-01

Pos logit contributions
 cries+0.015
 screams+0.014
 shouts+0.012
aned+0.012
ulously+0.012
Neg logit contributions
 chefs-0.017
 ju-0.017
 which-0.015
Which-0.015
 pigs-0.015
Token cage
Token ID17186
Feature activation-4.46e-01

Pos logit contributions
 chefs+0.016
 ju+0.015
 which+0.014
Which+0.014
 pigs+0.013
Neg logit contributions
 cries-0.020
 screams-0.020
 shouts-0.017
 farewell-0.017
night-0.017
Token ever
Token ID1683
Feature activation+3.60e+00

Pos logit contributions
 chefs+0.012
 ju+0.012
 pigs+0.011
Which+0.011
 basil+0.011
Neg logit contributions
 cries-0.011
 screams-0.011
night-0.010
 shouts-0.010
 farewell-0.010
Token again
Token ID757
Feature activation+4.51e+00

Pos logit contributions
 cries+0.100
 screams+0.098
 shouts+0.087
aned+0.085
ulously+0.083
Neg logit contributions
 chefs-0.092
 ju-0.091
 which-0.084
Which-0.081
 pigs-0.080