TOP ACTIVATIONS
MAX = 8.937

the park . Dad showed mom and the 3 year old
own shoe and showed his brother that he had a toe
Grand mother would give her granddaughter a file . The file
S ara and Ben are brother and sister . They live
<|endoftext|> Anna and Ben are sister and brother . They like
and trucks and showed their mom and dad their signs and
her feet and handed the woman a piece . They both
very excited and showed her mom . Her mom said ,
living room and showed her mom her bag . " Look
<|endoftext|> Tom and Lily are brother and sister . They like
S ara and Ben are brother and sister . They are
<|endoftext|> Tom and Anna are brother and sister . They like
turned around and showed his mom the pastry . She quickly
<|endoftext|> Tom and Lily are brother and sister . They like
<|endoftext|> Tom and Jen are brother and sister . They like
their room and showed their mom . She was very happy
went home and showed his mom the rock . His mom
L ily and Ben are brother and sister . They like
home and Lisa showed her mom all the things she could
her house and showed her mom the bad boo - bo

MIN ACTIVATIONS
MIN = -14.561

another wand . " A br ac ad ab ra !"
. How about oil or marg arine ?" Anna
the air . " A br ac ad ab ra !"
did not like oil or marg arine . But she did
Look , Lily , a che et ah !" Sam said
She said , " A br ac ad ab ra !"
felt as fast as a che et ah ! Her life
and said , " A br ac ad ab ra !"
But when she che wed her nails , she
it around . " A br ac ad ab ra !"
and saying , " A br ac ad ab ra !"
and said , " A br ac ad ab ra ,
said together , " A br ac ad ab ra !"
soon nothing but a small spe ck in the sky .
fun . Lily realized that pic n ics were not so
and said , " A br ac ad ab ra ,
and said , " A br ac ad ab ra !
and said , " A br ac ad ab ra !"
that he had used the squee gee to good use !
them feel secure . The pers istant love of their parents

INTERVAL 3.062 - 8.937
CONTAINS 6.146%

explore !" said Jake 's mom . " I
outside in the sun and feel the earth under her feet
looked in the mirror and felt so proud . He had
, it seemed to make people smile . One
the direction and saw a little girl . She was looking

INTERVAL -2.812 - 3.062
CONTAINS 85.522%

doll inside . She was so happy and hugged her grandma
not dry . The ball was still flat and useless .
urge to touch the knife and play with it . She
dad , because they knew they would say no .
perfect hidden place for my surprise !" Tim put his uniform

INTERVAL -8.686 - -2.812
CONTAINS 8.229%

climbed into the car and drove back home .
her toys sort just as she wants . It 's her
sun was setting and the adventurous whale went home . He
had been so ignorant that he had not noticed his own
look for something sweet and y ummy .

INTERVAL -14.561 - -8.686
CONTAINS 0.104%

! It is dirty and st inky ! I don 't
and she stepped into the p uddle . The
said , Of course ! Let
my 's mom . She st itched the small tear in
she would promise him a sc ooter if he was good
Token the
Token ID262
Feature activation+3.22e+00

Pos logit contributions
iding+0.071
oving+0.065
inn+0.065
gh+0.064
 som+0.063
Neg logit contributions
 sky-0.019
 nowhere-0.017
 woman-0.016
 pieces-0.014
 old-0.012
Token park
Token ID3952
Feature activation+6.76e-01

Pos logit contributions
 nowhere+0.060
Someone+0.053
 pieces+0.053
 woman+0.052
 sky+0.050
Neg logit contributions
iding-0.097
 som-0.097
inn-0.092
gh-0.089
 margin-0.089
Token.
Token ID13
Feature activation+5.78e-01

Pos logit contributions
 sky+0.014
 nowhere+0.013
 woman+0.012
s+0.011
 pieces+0.011
Neg logit contributions
iding-0.023
 som-0.021
inn-0.021
gh-0.021
heit-0.021
Token Dad
Token ID17415
Feature activation+2.41e+00

Pos logit contributions
 sky+0.015
 nowhere+0.014
 woman+0.014
Someone+0.013
 pieces+0.013
Neg logit contributions
iding-0.017
 som-0.015
inn-0.015
gh-0.015
oving-0.014
Token showed
Token ID3751
Feature activation+1.92e+00

Pos logit contributions
 sky+0.043
 nowhere+0.041
 woman+0.039
Someone+0.037
 pieces+0.035
Neg logit contributions
iding-0.086
 som-0.079
inn-0.078
gh-0.077
oving-0.076
Token mom
Token ID1995
Feature activation+8.94e+00

Pos logit contributions
 sky+0.055
 nowhere+0.054
Someone+0.052
 woman+0.052
 nearest+0.047
Neg logit contributions
iding-0.044
inn-0.041
 som-0.040
gh-0.038
oving-0.037
Token and
Token ID290
Feature activation+3.24e+00

Pos logit contributions
Someone+0.192
 nowhere+0.191
 sky+0.191
 woman+0.177
 nearest+0.161
Neg logit contributions
iding-0.276
inn-0.248
 som-0.240
oy-0.231
oving-0.226
Token the
Token ID262
Feature activation+3.29e+00

Pos logit contributions
 sky+0.073
 nowhere+0.066
Someone+0.060
actus+0.059
 nearest+0.058
Neg logit contributions
iding-0.094
 som-0.087
oy-0.084
inn-0.083
oving-0.082
Token 3
Token ID513
Feature activation+1.65e+00

Pos logit contributions
 nowhere+0.052
 sky+0.045
Someone+0.045
s+0.042
 woman+0.040
Neg logit contributions
iding-0.110
 som-0.109
gh-0.101
 appetite-0.101
oving-0.100
Token year
Token ID614
Feature activation+1.10e+00

Pos logit contributions
 sky+0.040
 nowhere+0.038
 woman+0.036
Someone+0.035
 pieces+0.033
Neg logit contributions
iding-0.048
gh-0.044
 som-0.044
inn-0.044
oving-0.043
Token old
Token ID1468
Feature activation+3.85e+00

Pos logit contributions
 sky+0.007
 nowhere+0.006
 woman+0.005
Someone+0.004
 pieces+0.003
Neg logit contributions
iding-0.052
 som-0.049
inn-0.049
gh-0.048
oving-0.048
Token own
Token ID898
Feature activation+7.68e-01

Pos logit contributions
 sky+0.001
 nowhere+0.001
 woman+0.001
Someone+0.001
 pieces+0.001
Neg logit contributions
iding-0.001
 som-0.001
inn-0.001
gh-0.001
oving-0.001
Token shoe
Token ID17292
Feature activation+5.90e-01

Pos logit contributions
 sky+0.017
 nowhere+0.017
 woman+0.016
 pieces+0.015
Someone+0.015
Neg logit contributions
iding-0.024
 som-0.022
inn-0.022
oving-0.021
gh-0.021
Token and
Token ID290
Feature activation+1.96e+00

Pos logit contributions
 sky+0.010
 nowhere+0.009
 woman+0.009
Someone+0.009
 pieces+0.008
Neg logit contributions
iding-0.021
inn-0.019
gh-0.019
 som-0.019
oving-0.019
Token showed
Token ID3751
Feature activation+1.33e+00

Pos logit contributions
 nowhere+0.037
 sky+0.036
 woman+0.035
 pieces+0.032
Someone+0.031
Neg logit contributions
iding-0.072
inn-0.065
gh-0.063
 som-0.062
oving-0.061
Token his
Token ID465
Feature activation+2.15e+00

Pos logit contributions
 sky+0.042
 nowhere+0.039
 woman+0.038
Someone+0.038
actus+0.035
Neg logit contributions
iding-0.030
inn-0.027
 som-0.027
gh-0.027
oving-0.026
Token brother
Token ID3956
Feature activation+8.91e+00

Pos logit contributions
 sky+0.052
Someone+0.048
 nowhere+0.046
 woman+0.046
armac+0.041
Neg logit contributions
iding-0.060
gh-0.058
 som-0.057
inn-0.054
 appetite-0.054
Token that
Token ID326
Feature activation+2.53e+00

Pos logit contributions
 sky+0.172
 nowhere+0.166
 woman+0.157
Someone+0.145
 pieces+0.144
Neg logit contributions
iding-0.309
 som-0.281
inn-0.279
gh-0.276
oving-0.274
Token he
Token ID339
Feature activation-1.90e+00

Pos logit contributions
 sky+0.054
 nowhere+0.051
 woman+0.050
Someone+0.048
 pieces+0.045
Neg logit contributions
iding-0.080
 som-0.075
gh-0.073
inn-0.072
oving-0.071
Token had
Token ID550
Feature activation+1.75e+00

Pos logit contributions
iding+0.061
 som+0.058
oving+0.058
gh+0.058
inn+0.056
Neg logit contributions
 sky-0.040
 woman-0.036
 nowhere-0.033
Someone-0.033
 curtains-0.030
Token a
Token ID257
Feature activation+2.16e-01

Pos logit contributions
 sky+0.028
 nowhere+0.026
 woman+0.025
Someone+0.023
 pieces+0.022
Neg logit contributions
iding-0.066
 som-0.062
gh-0.061
inn-0.061
oving-0.060
Token toe
Token ID21189
Feature activation-2.19e-01

Pos logit contributions
 sky+0.004
 nowhere+0.004
 woman+0.004
 pieces+0.003
Someone+0.003
Neg logit contributions
iding-0.008
inn-0.007
oving-0.007
 som-0.007
gh-0.007
Token Grand
Token ID5675
Feature activation-2.38e+00

Pos logit contributions
iding+0.009
 som+0.009
 avail+0.008
gh+0.008
inn+0.008
Neg logit contributions
 nowhere-0.005
 sky-0.005
actus-0.004
Someone-0.004
 pieces-0.004
Tokenmother
Token ID13552
Feature activation+3.42e+00

Pos logit contributions
iding+0.057
gh+0.054
icious+0.049
 appetite+0.048
uing+0.047
Neg logit contributions
 sky-0.064
 nowhere-0.062
Someone-0.061
 bushes-0.060
 nearest-0.057
Token would
Token ID561
Feature activation-3.99e-01

Pos logit contributions
 sky+0.075
 nowhere+0.075
 woman+0.069
Someone+0.068
 pieces+0.065
Neg logit contributions
iding-0.105
 som-0.094
gh-0.092
inn-0.091
oving-0.091
Token give
Token ID1577
Feature activation+1.78e+00

Pos logit contributions
iding+0.012
inn+0.012
oving+0.011
gh+0.011
heit+0.011
Neg logit contributions
 sky-0.010
 woman-0.009
 nowhere-0.008
 old-0.008
 she-0.008
Token her
Token ID607
Feature activation+2.17e+00

Pos logit contributions
 sky+0.036
 nowhere+0.035
Someone+0.032
 woman+0.032
 pieces+0.029
Neg logit contributions
iding-0.055
gh-0.052
 som-0.052
inn-0.051
oy-0.049
Token granddaughter
Token ID46458
Feature activation+8.90e+00

Pos logit contributions
 nowhere+0.038
 sky+0.037
Someone+0.036
 woman+0.032
s+0.030
Neg logit contributions
iding-0.070
 som-0.066
 appetite-0.063
gh-0.063
 dive-0.061
Token a
Token ID257
Feature activation+1.96e+00

Pos logit contributions
 sky+0.125
 nowhere+0.115
 woman+0.107
Someone+0.104
 pieces+0.088
Neg logit contributions
iding-0.348
 som-0.323
gh-0.317
inn-0.312
oving-0.306
Token file
Token ID2393
Feature activation+2.61e+00

Pos logit contributions
 nowhere+0.041
 sky+0.041
Someone+0.038
 woman+0.036
 pieces+0.036
Neg logit contributions
iding-0.061
 som-0.057
gh-0.056
inn-0.054
 appetite-0.053
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
 sky+0.047
 nowhere+0.044
 woman+0.042
 pieces+0.037
Someone+0.037
Neg logit contributions
iding-0.096
 som-0.088
inn-0.087
oving-0.086
gh-0.086
Token The
Token ID383
Feature activation+1.47e+00

Pos logit contributions
iding+0.000
inn+0.000
 som+0.000
gh+0.000
oving+0.000
Neg logit contributions
 nowhere-0.000
 sky-0.000
 woman-0.000
Someone-0.000
 pieces-0.000
Token file
Token ID2393
Feature activation+8.27e-01

Pos logit contributions
 nowhere+0.027
s+0.025
Someone+0.023
pill+0.023
actus+0.023
Neg logit contributions
 appetite-0.042
iding-0.042
gh-0.041
 insist-0.041
icious-0.040
TokenS
Token ID50
Feature activation-4.20e+00

Pos logit contributions
 nowhere+0.040
 woman+0.040
 sky+0.040
Someone+0.035
 pieces+0.031
Neg logit contributions
iding-0.131
inn-0.124
gh-0.122
 som-0.121
oving-0.116
Tokenara
Token ID3301
Feature activation-5.91e-01

Pos logit contributions
iding+0.086
inn+0.082
gh+0.079
 som+0.074
oy+0.072
Neg logit contributions
Someone-0.129
 nowhere-0.129
 woman-0.126
 sky-0.124
 pieces-0.118
Token and
Token ID290
Feature activation+2.33e+00

Pos logit contributions
iding+0.022
 som+0.020
inn+0.020
gh+0.020
oving+0.020
Neg logit contributions
 sky-0.009
 nowhere-0.009
 woman-0.008
Someone-0.008
 pieces-0.007
Token Ben
Token ID3932
Feature activation-1.29e+00

Pos logit contributions
 sky+0.048
 nowhere+0.044
 pieces+0.042
 woman+0.040
Someone+0.040
Neg logit contributions
iding-0.071
 som-0.068
gh-0.064
inn-0.064
 dive-0.063
Token are
Token ID389
Feature activation+2.71e+00

Pos logit contributions
iding+0.049
oving+0.045
inn+0.045
gh+0.044
 som+0.044
Neg logit contributions
 sky-0.023
 woman-0.021
 nowhere-0.020
 lost-0.019
 pieces-0.019
Token brother
Token ID3956
Feature activation+8.84e+00

Pos logit contributions
 sky+0.061
 nowhere+0.058
 woman+0.056
Someone+0.053
 pieces+0.052
Neg logit contributions
iding-0.086
 som-0.077
inn-0.077
gh-0.076
oving-0.075
Token and
Token ID290
Feature activation+3.09e+00

Pos logit contributions
 sky+0.138
 woman+0.126
 nowhere+0.119
s+0.119
 pieces+0.109
Neg logit contributions
iding-0.359
 som-0.336
gh-0.335
oving-0.332
inn-0.329
Token sister
Token ID6621
Feature activation+7.64e+00

Pos logit contributions
 sky+0.048
 woman+0.046
 nowhere+0.045
Someone+0.040
 pieces+0.037
Neg logit contributions
iding-0.122
inn-0.111
oving-0.110
 som-0.109
gh-0.108
Token.
Token ID13
Feature activation+4.40e-01

Pos logit contributions
 sky+0.139
 woman+0.130
 nowhere+0.126
s+0.121
 old+0.112
Neg logit contributions
iding-0.287
inn-0.263
 som-0.262
oving-0.260
gh-0.260
Token They
Token ID1119
Feature activation-1.24e+00

Pos logit contributions
 sky+0.008
s+0.007
+0.007
 woman+0.007
 she+0.006
Neg logit contributions
iding-0.018
gh-0.017
oving-0.017
heit-0.017
 som-0.016
Token live
Token ID2107
Feature activation-1.20e-01

Pos logit contributions
iding+0.044
gh+0.041
oving+0.040
inn+0.040
 avail+0.039
Neg logit contributions
 sky-0.026
 woman-0.023
 lost-0.022
 flowers-0.021
 living-0.021
Token<|endoftext|>
Token ID50256
Feature activation+3.35e+00

Pos logit contributions
iding+0.040
 som+0.037
inn+0.037
gh+0.036
oving+0.036
Neg logit contributions
 sky-0.014
 nowhere-0.013
 woman-0.012
Someone-0.011
 pieces-0.011
TokenAnna
Token ID31160
Feature activation-8.94e-01

Pos logit contributions
 nowhere+0.041
 sky+0.040
 woman+0.040
Someone+0.034
 pieces+0.031
Neg logit contributions
iding-0.134
inn-0.126
 som-0.123
gh-0.123
oving-0.119
Token and
Token ID290
Feature activation+1.31e+00

Pos logit contributions
iding+0.035
 som+0.032
inn+0.032
oving+0.032
gh+0.032
Neg logit contributions
 sky-0.014
 nowhere-0.012
 woman-0.012
 pieces-0.011
Someone-0.010
Token Ben
Token ID3932
Feature activation-1.56e+00

Pos logit contributions
 sky+0.029
 nowhere+0.028
 woman+0.027
Someone+0.025
 pieces+0.025
Neg logit contributions
iding-0.041
 som-0.037
inn-0.037
gh-0.037
oving-0.036
Token are
Token ID389
Feature activation+2.50e+00

Pos logit contributions
iding+0.057
oving+0.051
inn+0.051
gh+0.051
 som+0.051
Neg logit contributions
 sky-0.031
 woman-0.028
 nowhere-0.028
 pieces-0.025
Someone-0.025
Token sister
Token ID6621
Feature activation+8.82e+00

Pos logit contributions
 sky+0.056
 nowhere+0.053
 woman+0.052
Someone+0.049
 pieces+0.047
Neg logit contributions
iding-0.080
 som-0.072
inn-0.072
gh-0.071
oving-0.070
Token and
Token ID290
Feature activation+2.54e+00

Pos logit contributions
 sky+0.147
 nowhere+0.134
 woman+0.134
s+0.120
 pieces+0.118
Neg logit contributions
iding-0.341
 som-0.318
gh-0.317
inn-0.312
oving-0.312
Token brother
Token ID3956
Feature activation+7.34e+00

Pos logit contributions
 sky+0.046
 woman+0.045
 she+0.041
 nowhere+0.040
 lost+0.039
Neg logit contributions
iding-0.098
inn-0.089
oving-0.087
 som-0.084
gh-0.083
Token.
Token ID13
Feature activation+3.98e-02

Pos logit contributions
 sky+0.140
 woman+0.130
 nowhere+0.126
s+0.120
 pieces+0.114
Neg logit contributions
iding-0.271
inn-0.246
 som-0.245
gh-0.245
oving-0.243
Token They
Token ID1119
Feature activation-1.53e+00

Pos logit contributions
 sky+0.001
s+0.001
 nowhere+0.001
 woman+0.001
 she+0.001
Neg logit contributions
iding-0.001
gh-0.001
oving-0.001
 som-0.001
heit-0.001
Token like
Token ID588
Feature activation+2.29e+00

Pos logit contributions
iding+0.053
gh+0.048
oving+0.048
inn+0.047
 avail+0.046
Neg logit contributions
 sky-0.033
 woman-0.029
 lost-0.029
 flowers-0.027
 old-0.027
Token and
Token ID290
Feature activation+1.43e+00

Pos logit contributions
 sky+0.028
 nowhere+0.027
Someone+0.026
 woman+0.026
 pieces+0.021
Neg logit contributions
iding-0.061
inn-0.055
 som-0.055
gh-0.054
oving-0.053
Token trucks
Token ID13960
Feature activation+1.20e+00

Pos logit contributions
 sky+0.033
 nowhere+0.032
 woman+0.031
 pieces+0.029
Someone+0.028
Neg logit contributions
iding-0.045
inn-0.040
 som-0.040
gh-0.040
oving-0.039
Token and
Token ID290
Feature activation+7.10e-01

Pos logit contributions
 sky+0.022
 nowhere+0.020
 woman+0.019
Someone+0.018
 pieces+0.017
Neg logit contributions
iding-0.043
 som-0.039
inn-0.039
gh-0.039
oving-0.038
Token showed
Token ID3751
Feature activation+8.99e-01

Pos logit contributions
 sky+0.017
 nowhere+0.016
 woman+0.016
 pieces+0.014
Someone+0.014
Neg logit contributions
iding-0.022
inn-0.020
 som-0.020
gh-0.020
oving-0.019
Token their
Token ID511
Feature activation+1.30e+00

Pos logit contributions
 sky+0.022
 nowhere+0.021
 woman+0.021
 pieces+0.020
Someone+0.019
Neg logit contributions
iding-0.027
inn-0.023
 som-0.023
gh-0.023
oving-0.023
Token mom
Token ID1995
Feature activation+8.75e+00

Pos logit contributions
 sky+0.022
 nowhere+0.022
Someone+0.021
 woman+0.020
keeper+0.017
Neg logit contributions
iding-0.046
 som-0.043
gh-0.043
oving-0.041
inn-0.041
Token and
Token ID290
Feature activation+2.09e+00

Pos logit contributions
 sky+0.180
Someone+0.180
 nowhere+0.177
 woman+0.155
 nearest+0.150
Neg logit contributions
iding-0.277
 som-0.249
inn-0.243
gh-0.238
oy-0.228
Token dad
Token ID9955
Feature activation+5.93e+00

Pos logit contributions
 sky+0.042
 nowhere+0.039
Someone+0.036
 woman+0.033
actus+0.032
Neg logit contributions
iding-0.068
 som-0.064
inn-0.060
gh-0.059
oving-0.059
Token their
Token ID511
Feature activation-5.10e-01

Pos logit contributions
 sky+0.150
 nowhere+0.145
Someone+0.137
 woman+0.134
 pieces+0.121
Neg logit contributions
iding-0.174
 som-0.155
inn-0.149
gh-0.149
oving-0.145
Token signs
Token ID5895
Feature activation+1.84e+00

Pos logit contributions
iding+0.019
 som+0.018
inn+0.017
gh+0.017
oving+0.017
Neg logit contributions
 sky-0.008
 nowhere-0.008
 woman-0.008
Someone-0.007
 pieces-0.007
Token and
Token ID290
Feature activation+2.07e+00

Pos logit contributions
 sky+0.037
 woman+0.033
 nowhere+0.033
 pieces+0.030
s+0.030
Neg logit contributions
iding-0.064
inn-0.059
 som-0.059
oving-0.058
gh-0.058
Token her
Token ID607
Feature activation+1.33e+00

Pos logit contributions
iding+0.028
inn+0.025
 som+0.025
gh+0.025
oving+0.025
Neg logit contributions
 sky-0.009
 nowhere-0.009
 woman-0.008
Someone-0.007
 pieces-0.007
Token feet
Token ID3625
Feature activation+8.06e-01

Pos logit contributions
Someone+0.027
 sky+0.027
 nowhere+0.027
 woman+0.024
 pieces+0.022
Neg logit contributions
iding-0.041
 som-0.038
 appetite-0.038
gh-0.036
inn-0.036
Token and
Token ID290
Feature activation+2.49e+00

Pos logit contributions
 sky+0.010
 nowhere+0.009
 woman+0.008
 pieces+0.007
s+0.006
Neg logit contributions
iding-0.035
 som-0.032
oving-0.032
heit-0.032
gh-0.032
Token handed
Token ID10158
Feature activation+1.05e+00

Pos logit contributions
 sky+0.051
 nowhere+0.049
 woman+0.048
 pieces+0.044
s+0.043
Neg logit contributions
iding-0.090
gh-0.079
inn-0.079
oving-0.078
 som-0.075
Token the
Token ID262
Feature activation+3.70e+00

Pos logit contributions
 sky+0.025
 nowhere+0.024
Someone+0.024
 nearest+0.022
actus+0.022
Neg logit contributions
inn-0.026
 avail-0.023
 som-0.023
gh-0.023
iding-0.023
Token woman
Token ID2415
Feature activation+8.75e+00

Pos logit contributions
pill+0.070
 nowhere+0.067
anes+0.064
ons+0.063
s+0.059
Neg logit contributions
 insist-0.097
iding-0.096
 som-0.093
rated-0.092
 tug-0.092
Token a
Token ID257
Feature activation+2.11e+00

Pos logit contributions
 sky+0.160
 nowhere+0.148
 woman+0.141
Someone+0.138
 pieces+0.118
Neg logit contributions
iding-0.310
inn-0.281
 som-0.280
gh-0.274
oving-0.266
Token piece
Token ID3704
Feature activation+2.84e+00

Pos logit contributions
 sky+0.042
 nowhere+0.040
 woman+0.038
Someone+0.036
 pieces+0.035
Neg logit contributions
iding-0.072
 som-0.065
inn-0.065
gh-0.064
oving-0.063
Token.
Token ID13
Feature activation-1.84e-01

Pos logit contributions
 sky+0.021
 nowhere+0.017
 woman+0.013
 pieces+0.012
 old+0.009
Neg logit contributions
iding-0.135
oving-0.129
heit-0.128
 som-0.127
gh-0.125
Token They
Token ID1119
Feature activation-1.60e+00

Pos logit contributions
iding+0.006
 som+0.006
inn+0.006
oving+0.005
gh+0.005
Neg logit contributions
 nowhere-0.004
 sky-0.003
 woman-0.003
Someone-0.003
 pieces-0.003
Token both
Token ID1111
Feature activation-1.08e+00

Pos logit contributions
iding+0.051
 som+0.045
gh+0.045
inn+0.045
oving+0.045
Neg logit contributions
 sky-0.036
 nowhere-0.035
 woman-0.033
 pieces-0.031
Someone-0.031
Token very
Token ID845
Feature activation+8.63e-01

Pos logit contributions
 sky+0.030
 woman+0.027
 nowhere+0.027
Someone+0.026
s+0.025
Neg logit contributions
iding-0.053
 som-0.049
inn-0.048
oving-0.048
gh-0.047
Token excited
Token ID6568
Feature activation+3.25e+00

Pos logit contributions
 sky+0.016
 nowhere+0.015
 woman+0.014
 old+0.013
Someone+0.013
Neg logit contributions
iding-0.031
 som-0.028
gh-0.028
inn-0.028
oving-0.027
Token and
Token ID290
Feature activation+2.91e+00

Pos logit contributions
 sky+0.063
Someone+0.060
 nowhere+0.060
 woman+0.059
 pieces+0.052
Neg logit contributions
iding-0.110
 som-0.100
gh-0.099
inn-0.098
oving-0.096
Token showed
Token ID3751
Feature activation+1.53e+00

Pos logit contributions
 sky+0.048
 nowhere+0.046
 woman+0.044
Someone+0.039
 old+0.039
Neg logit contributions
iding-0.112
inn-0.103
gh-0.100
 som-0.099
oving-0.098
Token her
Token ID607
Feature activation+3.21e+00

Pos logit contributions
 sky+0.041
Someone+0.039
 nowhere+0.039
 woman+0.037
 nearest+0.035
Neg logit contributions
 som-0.037
gh-0.035
inn-0.034
bit-0.034
iding-0.034
Token mom
Token ID1995
Feature activation+8.75e+00

Pos logit contributions
 sky+0.082
Someone+0.082
 nowhere+0.072
 woman+0.071
pill+0.070
Neg logit contributions
 som-0.074
 appetite-0.071
 dive-0.071
 splash-0.068
gh-0.068
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
 sky+0.213
Someone+0.210
 nowhere+0.202
 woman+0.198
 nearest+0.179
Neg logit contributions
iding-0.249
inn-0.227
 som-0.223
gh-0.213
oving-0.205
Token Her
Token ID2332
Feature activation+1.24e-01

Pos logit contributions
iding+0.006
 som+0.005
gh+0.005
inn+0.005
oving+0.005
Neg logit contributions
 sky-0.002
 nowhere-0.002
 woman-0.002
Someone-0.002
 pieces-0.002
Token mom
Token ID1995
Feature activation+5.10e+00

Pos logit contributions
 sky+0.003
 nowhere+0.003
Someone+0.003
pill+0.002
 woman+0.002
Neg logit contributions
gh-0.003
 appetite-0.003
iding-0.003
 som-0.003
omo-0.003
Token said
Token ID531
Feature activation+7.21e-01

Pos logit contributions
 sky+0.114
 nowhere+0.105
Someone+0.101
 woman+0.100
 pieces+0.093
Neg logit contributions
iding-0.155
 som-0.142
inn-0.141
oving-0.140
gh-0.138
Token,
Token ID11
Feature activation+7.53e-02

Pos logit contributions
 sky+0.017
 nowhere+0.016
 woman+0.016
Someone+0.015
 pieces+0.014
Neg logit contributions
iding-0.022
 som-0.020
inn-0.020
gh-0.020
oving-0.020
Token living
Token ID2877
Feature activation-5.44e+00

Pos logit contributions
 sky+0.051
 woman+0.046
 nowhere+0.044
 pieces+0.041
Someone+0.040
Neg logit contributions
iding-0.087
inn-0.079
gh-0.077
oving-0.077
 som-0.077
Token room
Token ID2119
Feature activation+1.46e+00

Pos logit contributions
iding+0.216
 som+0.203
inn+0.201
gh+0.197
oving+0.196
Neg logit contributions
 sky-0.066
 nowhere-0.061
 woman-0.058
Someone-0.058
s-0.045
Token and
Token ID290
Feature activation+1.82e+00

Pos logit contributions
 sky+0.024
 nowhere+0.023
 woman+0.022
Someone+0.019
 pieces+0.019
Neg logit contributions
iding-0.055
 som-0.050
inn-0.050
gh-0.049
oving-0.049
Token showed
Token ID3751
Feature activation+1.28e+00

Pos logit contributions
 sky+0.039
 nowhere+0.037
 woman+0.036
Someone+0.034
 pieces+0.033
Neg logit contributions
iding-0.059
 som-0.054
inn-0.053
gh-0.052
oving-0.052
Token her
Token ID607
Feature activation+3.10e+00

Pos logit contributions
 sky+0.028
 nowhere+0.027
Someone+0.026
 woman+0.025
 pieces+0.022
Neg logit contributions
iding-0.038
 som-0.037
inn-0.036
gh-0.035
oving-0.033
Token mom
Token ID1995
Feature activation+8.75e+00

Pos logit contributions
 sky+0.059
Someone+0.056
 nowhere+0.054
 woman+0.050
 nearest+0.044
Neg logit contributions
iding-0.101
 som-0.097
gh-0.092
inn-0.091
 dive-0.090
Token her
Token ID607
Feature activation+2.71e+00

Pos logit contributions
 sky+0.198
 nowhere+0.188
Someone+0.182
 woman+0.179
 pieces+0.162
Neg logit contributions
iding-0.271
inn-0.243
 som-0.242
gh-0.236
oving-0.230
Token bag
Token ID6131
Feature activation+2.18e+00

Pos logit contributions
 sky+0.051
 nowhere+0.049
 woman+0.047
 pieces+0.044
Someone+0.042
Neg logit contributions
iding-0.097
inn-0.088
 som-0.087
oving-0.087
gh-0.086
Token.
Token ID13
Feature activation-2.66e-01

Pos logit contributions
 sky+0.044
 nowhere+0.042
 woman+0.040
 pieces+0.038
s+0.036
Neg logit contributions
iding-0.074
 som-0.069
oving-0.068
heit-0.067
inn-0.067
Token "
Token ID366
Feature activation+1.79e+00

Pos logit contributions
iding+0.010
 som+0.009
inn+0.009
gh+0.009
oving+0.009
Neg logit contributions
 sky-0.005
 nowhere-0.004
 woman-0.004
Someone-0.004
 pieces-0.004
TokenLook
Token ID8567
Feature activation-2.17e+00

Pos logit contributions
 sky+0.040
 nowhere+0.039
 woman+0.037
 pieces+0.035
Someone+0.034
Neg logit contributions
iding-0.055
inn-0.050
 som-0.049
gh-0.048
oving-0.047
Token<|endoftext|>
Token ID50256
Feature activation+3.34e+00

Pos logit contributions
iding+0.034
inn+0.031
 som+0.031
gh+0.031
oving+0.030
Neg logit contributions
 sky-0.014
 nowhere-0.013
 woman-0.012
Someone-0.011
 pieces-0.011
TokenTom
Token ID13787
Feature activation-1.04e+00

Pos logit contributions
 woman+0.041
 nowhere+0.041
 sky+0.040
Someone+0.035
 pieces+0.031
Neg logit contributions
iding-0.131
inn-0.124
gh-0.121
 som-0.121
oving-0.116
Token and
Token ID290
Feature activation+2.30e+00

Pos logit contributions
iding+0.043
 som+0.040
inn+0.039
oving+0.039
gh+0.039
Neg logit contributions
 sky-0.014
 nowhere-0.013
 woman-0.012
 pieces-0.010
Someone-0.010
Token Lily
Token ID20037
Feature activation+1.72e-01

Pos logit contributions
 sky+0.058
 nowhere+0.056
 woman+0.054
Someone+0.051
 pieces+0.051
Neg logit contributions
iding-0.065
 som-0.059
inn-0.058
gh-0.058
oving-0.056
Token are
Token ID389
Feature activation+2.56e+00

Pos logit contributions
 sky+0.003
 nowhere+0.003
 woman+0.003
 pieces+0.002
s+0.002
Neg logit contributions
iding-0.007
inn-0.006
gh-0.006
 som-0.006
oving-0.006
Token brother
Token ID3956
Feature activation+8.72e+00

Pos logit contributions
 sky+0.066
 woman+0.063
 nowhere+0.063
Someone+0.061
 pieces+0.058
Neg logit contributions
iding-0.072
inn-0.063
 som-0.062
gh-0.062
 appetite-0.061
Token and
Token ID290
Feature activation+2.81e+00

Pos logit contributions
 sky+0.146
 woman+0.135
 nowhere+0.134
s+0.121
 pieces+0.117
Neg logit contributions
iding-0.341
 som-0.314
gh-0.313
oving-0.310
inn-0.308
Token sister
Token ID6621
Feature activation+7.59e+00

Pos logit contributions
 woman+0.057
 sky+0.056
 nowhere+0.052
 she+0.049
Someone+0.048
Neg logit contributions
iding-0.101
inn-0.089
oving-0.088
 som-0.086
gh-0.085
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
 sky+0.151
 woman+0.141
 nowhere+0.140
s+0.128
 pieces+0.123
Neg logit contributions
iding-0.269
 som-0.244
inn-0.244
gh-0.242
oving-0.240
Token They
Token ID1119
Feature activation-1.37e+00

Pos logit contributions
 sky+0.003
 woman+0.003
s+0.003
 nowhere+0.003
 grandma+0.003
Neg logit contributions
iding-0.006
 som-0.006
heit-0.006
gh-0.006
oving-0.006
Token like
Token ID588
Feature activation+2.43e+00

Pos logit contributions
iding+0.049
gh+0.044
oving+0.044
inn+0.043
 avail+0.043
Neg logit contributions
 sky-0.029
 woman-0.025
 lost-0.025
 flowers-0.024
 living-0.023
TokenS
Token ID50
Feature activation-4.26e+00

Pos logit contributions
 woman+0.054
 nowhere+0.050
 sky+0.047
Someone+0.046
keeper+0.044
Neg logit contributions
iding-0.122
inn-0.119
gh-0.114
 som-0.112
 Finn-0.106
Tokenara
Token ID3301
Feature activation-6.47e-01

Pos logit contributions
iding+0.053
gh+0.048
inn+0.047
oy+0.041
 som+0.041
Neg logit contributions
 nowhere-0.164
 woman-0.164
Someone-0.162
 sky-0.159
 pieces-0.154
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
iding+0.024
 som+0.022
inn+0.022
gh+0.022
oving+0.022
Neg logit contributions
 sky-0.010
 nowhere-0.010
 woman-0.009
Someone-0.009
 pieces-0.008
Token Ben
Token ID3932
Feature activation-1.39e+00

Pos logit contributions
 sky+0.043
 nowhere+0.041
 pieces+0.039
 woman+0.038
Someone+0.037
Neg logit contributions
iding-0.055
 som-0.052
gh-0.050
inn-0.050
oving-0.048
Token are
Token ID389
Feature activation+2.63e+00

Pos logit contributions
iding+0.050
inn+0.045
oving+0.045
 som+0.045
gh+0.045
Neg logit contributions
 sky-0.027
 nowhere-0.025
 woman-0.024
 pieces-0.022
Someone-0.022
Token brother
Token ID3956
Feature activation+8.70e+00

Pos logit contributions
 sky+0.063
 nowhere+0.060
 woman+0.059
Someone+0.057
 pieces+0.054
Neg logit contributions
iding-0.078
inn-0.070
 som-0.069
gh-0.068
oving-0.067
Token and
Token ID290
Feature activation+2.85e+00

Pos logit contributions
 sky+0.134
 nowhere+0.123
 woman+0.123
s+0.105
 pieces+0.105
Neg logit contributions
iding-0.345
 som-0.320
gh-0.317
inn-0.315
oving-0.312
Token sister
Token ID6621
Feature activation+7.47e+00

Pos logit contributions
 sky+0.056
 woman+0.055
 nowhere+0.052
Someone+0.048
 bird+0.045
Neg logit contributions
iding-0.102
inn-0.092
oving-0.090
 som-0.089
gh-0.088
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
 sky+0.163
 nowhere+0.155
 woman+0.152
Someone+0.138
 pieces+0.137
Neg logit contributions
iding-0.244
 som-0.221
inn-0.219
gh-0.217
oving-0.215
Token They
Token ID1119
Feature activation-1.45e+00

Pos logit contributions
 sky+0.003
s+0.002
 woman+0.002
+0.002
 she+0.002
Neg logit contributions
iding-0.005
oving-0.005
gh-0.005
 som-0.005
heit-0.005
Token are
Token ID389
Feature activation+2.20e+00

Pos logit contributions
iding+0.050
gh+0.045
oving+0.045
inn+0.045
 som+0.044
Neg logit contributions
 sky-0.031
 woman-0.027
 lost-0.026
 nowhere-0.025
 flowers-0.025
Token<|endoftext|>
Token ID50256
Feature activation+3.12e+00

Pos logit contributions
iding+0.036
inn+0.033
 som+0.032
oving+0.031
gh+0.031
Neg logit contributions
 sky-0.033
 nowhere-0.033
 woman-0.032
 pieces-0.030
Someone-0.030
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 woman+0.043
 nowhere+0.042
 sky+0.040
Someone+0.036
keeper+0.033
Neg logit contributions
iding-0.118
inn-0.113
gh-0.109
 som-0.108
oving-0.103
Token and
Token ID290
Feature activation+2.30e+00

Pos logit contributions
iding+0.039
 som+0.036
inn+0.036
gh+0.036
oving+0.035
Neg logit contributions
 sky-0.015
 nowhere-0.014
 woman-0.013
Someone-0.012
 pieces-0.011
Token Anna
Token ID11735
Feature activation-1.51e+00

Pos logit contributions
 sky+0.061
 nowhere+0.058
 woman+0.055
Someone+0.053
 pieces+0.053
Neg logit contributions
iding-0.062
 som-0.056
inn-0.056
gh-0.055
oving-0.053
Token are
Token ID389
Feature activation+2.55e+00

Pos logit contributions
iding+0.058
 som+0.052
inn+0.052
gh+0.052
oving+0.052
Neg logit contributions
 sky-0.025
 nowhere-0.023
 woman-0.022
Someone-0.020
 pieces-0.020
Token brother
Token ID3956
Feature activation+8.70e+00

Pos logit contributions
 sky+0.067
 woman+0.064
 nowhere+0.063
Someone+0.063
keeper+0.059
Neg logit contributions
iding-0.069
inn-0.061
 appetite-0.060
gh-0.059
 som-0.058
Token and
Token ID290
Feature activation+2.81e+00

Pos logit contributions
 sky+0.146
 woman+0.134
 nowhere+0.133
s+0.121
 pieces+0.117
Neg logit contributions
iding-0.339
 som-0.314
gh-0.310
inn-0.308
oving-0.308
Token sister
Token ID6621
Feature activation+7.38e+00

Pos logit contributions
 woman+0.054
 sky+0.052
 nowhere+0.047
 she+0.047
 lost+0.045
Neg logit contributions
iding-0.106
inn-0.094
oving-0.093
 som-0.091
heit-0.089
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
 sky+0.149
 woman+0.139
 nowhere+0.138
s+0.127
 pieces+0.121
Neg logit contributions
iding-0.259
inn-0.236
 som-0.235
gh-0.232
oving-0.231
Token They
Token ID1119
Feature activation-1.32e+00

Pos logit contributions
 sky+0.005
 woman+0.004
 nowhere+0.004
s+0.004
Someone+0.004
Neg logit contributions
iding-0.006
 som-0.006
gh-0.006
oving-0.006
heit-0.005
Token like
Token ID588
Feature activation+2.49e+00

Pos logit contributions
iding+0.046
oving+0.041
gh+0.041
inn+0.040
 avail+0.040
Neg logit contributions
 sky-0.029
 woman-0.026
 lost-0.025
 flowers-0.024
 nowhere-0.023
Token turned
Token ID2900
Feature activation+1.81e+00

Pos logit contributions
 sky+0.032
 nowhere+0.030
 woman+0.030
 lost+0.027
s+0.026
Neg logit contributions
iding-0.096
inn-0.088
 som-0.085
 accompl-0.084
oving-0.083
Token around
Token ID1088
Feature activation+2.25e+00

Pos logit contributions
 sky+0.034
 nowhere+0.032
 woman+0.030
 pieces+0.029
s+0.028
Neg logit contributions
iding-0.067
 som-0.059
oving-0.059
gh-0.058
inn-0.058
Token and
Token ID290
Feature activation+3.37e+00

Pos logit contributions
 sky+0.024
 nowhere+0.021
 woman+0.018
 pieces+0.016
 old+0.016
Neg logit contributions
iding-0.105
oving-0.100
inn-0.096
gh-0.095
 som-0.095
Token showed
Token ID3751
Feature activation+1.58e+00

Pos logit contributions
 sky+0.053
 nowhere+0.052
 woman+0.049
Someone+0.041
 pieces+0.040
Neg logit contributions
iding-0.137
inn-0.122
gh-0.121
oving-0.120
 som-0.119
Token his
Token ID465
Feature activation+2.33e+00

Pos logit contributions
 sky+0.028
 woman+0.027
 nowhere+0.026
 pieces+0.024
 old+0.024
Neg logit contributions
iding-0.058
oving-0.052
 som-0.051
inn-0.051
 appetite-0.050
Token mom
Token ID1995
Feature activation+8.70e+00

Pos logit contributions
 sky+0.036
 nowhere+0.033
 woman+0.031
Someone+0.030
 pieces+0.027
Neg logit contributions
iding-0.089
 som-0.083
gh-0.082
inn-0.081
oving-0.080
Token the
Token ID262
Feature activation+3.76e+00

Pos logit contributions
 sky+0.154
 nowhere+0.148
 woman+0.140
 pieces+0.131
s+0.125
Neg logit contributions
iding-0.316
 som-0.291
inn-0.288
oving-0.286
gh-0.283
Token pastry
Token ID41738
Feature activation+1.36e+00

Pos logit contributions
 sky+0.072
 nowhere+0.068
 woman+0.065
Someone+0.061
 pieces+0.058
Neg logit contributions
iding-0.131
 som-0.120
inn-0.119
gh-0.118
oving-0.116
Token.
Token ID13
Feature activation-1.56e-01

Pos logit contributions
 sky+0.026
 nowhere+0.023
 pieces+0.023
 woman+0.022
s+0.021
Neg logit contributions
iding-0.051
oving-0.047
inn-0.047
 som-0.046
heit-0.045
Token She
Token ID1375
Feature activation-4.30e-01

Pos logit contributions
iding+0.006
oving+0.005
gh+0.005
 som+0.005
heit+0.005
Neg logit contributions
 sky-0.003
 woman-0.002
 nowhere-0.002
Someone-0.002
 old-0.002
Token quickly
Token ID2952
Feature activation-1.90e+00

Pos logit contributions
iding+0.014
 som+0.013
inn+0.013
gh+0.013
oving+0.013
Neg logit contributions
 sky-0.009
 nowhere-0.008
 woman-0.008
Someone-0.007
 pieces-0.007
Token<|endoftext|>
Token ID50256
Feature activation+3.53e+00

Pos logit contributions
iding+0.033
 som+0.031
gh+0.030
oving+0.030
inn+0.030
Neg logit contributions
 sky-0.016
 nowhere-0.014
 woman-0.014
Someone-0.013
 pieces-0.012
TokenTom
Token ID13787
Feature activation-1.07e+00

Pos logit contributions
 woman+0.054
 nowhere+0.052
Someone+0.047
 sky+0.047
keeper+0.045
Neg logit contributions
iding-0.125
inn-0.121
gh-0.117
 som-0.114
irl-0.108
Token and
Token ID290
Feature activation+2.40e+00

Pos logit contributions
iding+0.043
 som+0.040
oving+0.039
gh+0.039
inn+0.039
Neg logit contributions
 sky-0.016
 nowhere-0.014
 woman-0.013
 pieces-0.012
Someone-0.011
Token Lily
Token ID20037
Feature activation+2.16e-01

Pos logit contributions
 sky+0.063
 nowhere+0.060
 woman+0.057
Someone+0.055
 pieces+0.055
Neg logit contributions
iding-0.066
 som-0.059
inn-0.059
gh-0.058
oving-0.057
Token are
Token ID389
Feature activation+2.50e+00

Pos logit contributions
 sky+0.004
 woman+0.003
 nowhere+0.003
 lost+0.003
s+0.003
Neg logit contributions
iding-0.008
inn-0.008
gh-0.008
oving-0.008
 som-0.007
Token brother
Token ID3956
Feature activation+8.70e+00

Pos logit contributions
 sky+0.062
 woman+0.058
 nowhere+0.058
Someone+0.056
 pieces+0.054
Neg logit contributions
iding-0.073
inn-0.065
gh-0.063
 som-0.063
oving-0.062
Token and
Token ID290
Feature activation+2.87e+00

Pos logit contributions
 sky+0.126
 nowhere+0.115
 woman+0.113
 pieces+0.097
s+0.096
Neg logit contributions
iding-0.352
 som-0.326
gh-0.323
inn-0.322
oving-0.320
Token sister
Token ID6621
Feature activation+7.46e+00

Pos logit contributions
 woman+0.058
 sky+0.057
 nowhere+0.053
Someone+0.050
 she+0.049
Neg logit contributions
iding-0.102
inn-0.091
oving-0.089
 som-0.088
gh-0.087
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
 sky+0.163
 nowhere+0.154
 woman+0.151
Someone+0.137
 pieces+0.137
Neg logit contributions
iding-0.244
 som-0.221
inn-0.219
gh-0.217
oving-0.215
Token They
Token ID1119
Feature activation-1.40e+00

Pos logit contributions
 sky+0.004
 woman+0.003
 grandma+0.003
+0.003
s+0.003
Neg logit contributions
iding-0.008
heit-0.007
 som-0.007
gh-0.007
oving-0.007
Token like
Token ID588
Feature activation+2.32e+00

Pos logit contributions
iding+0.047
gh+0.043
oving+0.042
inn+0.042
 som+0.042
Neg logit contributions
 sky-0.031
 woman-0.027
 lost-0.026
 flowers-0.025
 nowhere-0.025
Token<|endoftext|>
Token ID50256
Feature activation+3.36e+00

Pos logit contributions
iding+0.006
 som+0.006
gh+0.006
oving+0.006
inn+0.006
Neg logit contributions
 sky-0.002
 nowhere-0.002
 woman-0.002
Someone-0.002
s-0.001
TokenTom
Token ID13787
Feature activation-1.19e+00

Pos logit contributions
 sky+0.045
 woman+0.044
 nowhere+0.043
Someone+0.040
 pieces+0.036
Neg logit contributions
iding-0.128
inn-0.121
gh-0.119
 som-0.118
oving-0.113
Token and
Token ID290
Feature activation+2.85e+00

Pos logit contributions
iding+0.049
 som+0.045
inn+0.044
gh+0.044
oving+0.044
Neg logit contributions
 sky-0.016
 nowhere-0.015
 woman-0.014
Someone-0.012
 pieces-0.012
Token Jen
Token ID13364
Feature activation-1.25e+00

Pos logit contributions
 sky+0.070
 nowhere+0.067
 woman+0.066
Someone+0.062
 pieces+0.059
Neg logit contributions
iding-0.087
 som-0.077
inn-0.076
gh-0.075
oving-0.075
Token are
Token ID389
Feature activation+2.66e+00

Pos logit contributions
iding+0.048
 som+0.044
inn+0.043
gh+0.043
oving+0.043
Neg logit contributions
 sky-0.021
 nowhere-0.019
 woman-0.018
Someone-0.016
 pieces-0.016
Token brother
Token ID3956
Feature activation+8.68e+00

Pos logit contributions
 sky+0.062
 nowhere+0.059
 woman+0.058
Someone+0.055
 pieces+0.053
Neg logit contributions
iding-0.082
inn-0.073
 som-0.073
gh-0.072
oving-0.071
Token and
Token ID290
Feature activation+3.29e+00

Pos logit contributions
 sky+0.124
 woman+0.114
 nowhere+0.114
s+0.093
 pieces+0.093
Neg logit contributions
iding-0.356
 som-0.327
inn-0.326
gh-0.325
oving-0.322
Token sister
Token ID6621
Feature activation+7.25e+00

Pos logit contributions
 woman+0.065
 sky+0.065
 nowhere+0.060
Someone+0.055
 bird+0.054
Neg logit contributions
iding-0.118
inn-0.107
oving-0.103
 som-0.102
gh-0.101
Token.
Token ID13
Feature activation+4.09e-01

Pos logit contributions
 sky+0.144
 woman+0.136
 nowhere+0.134
s+0.122
 pieces+0.117
Neg logit contributions
iding-0.255
inn-0.232
 som-0.232
gh-0.228
oving-0.225
Token They
Token ID1119
Feature activation-1.21e+00

Pos logit contributions
 sky+0.009
s+0.007
 woman+0.007
 Some+0.006
 trees+0.006
Neg logit contributions
iding-0.015
gh-0.014
 som-0.014
heit-0.013
 afloat-0.013
Token like
Token ID588
Feature activation+2.47e+00

Pos logit contributions
iding+0.046
inn+0.041
gh+0.041
 som+0.040
oving+0.040
Neg logit contributions
 sky-0.023
 woman-0.020
 lost-0.019
 nowhere-0.018
 flowers-0.018
Token their
Token ID511
Feature activation-2.53e-01

Pos logit contributions
iding+0.129
 som+0.117
inn+0.116
gh+0.115
oving+0.114
Neg logit contributions
 sky-0.073
 nowhere-0.069
 woman-0.066
Someone-0.063
 pieces-0.059
Token room
Token ID2119
Feature activation+1.91e+00

Pos logit contributions
iding+0.009
 som+0.009
gh+0.009
 appetite+0.009
oving+0.008
Neg logit contributions
 sky-0.004
 nowhere-0.004
 woman-0.003
Someone-0.003
 pieces-0.003
Token and
Token ID290
Feature activation+1.93e+00

Pos logit contributions
 sky+0.028
 nowhere+0.026
 woman+0.024
 pieces+0.023
s+0.020
Neg logit contributions
iding-0.077
inn-0.071
 som-0.071
oving-0.069
gh-0.069
Token showed
Token ID3751
Feature activation+9.59e-01

Pos logit contributions
 sky+0.042
 nowhere+0.040
 woman+0.039
 pieces+0.036
Someone+0.036
Neg logit contributions
iding-0.064
inn-0.057
 som-0.057
gh-0.056
oving-0.056
Token their
Token ID511
Feature activation+1.62e+00

Pos logit contributions
 sky+0.027
 nowhere+0.026
Someone+0.024
 woman+0.024
 pieces+0.022
Neg logit contributions
iding-0.024
 som-0.022
inn-0.022
gh-0.021
oving-0.021
Token mom
Token ID1995
Feature activation+8.67e+00

Pos logit contributions
 sky+0.027
 nowhere+0.026
Someone+0.026
 woman+0.024
s+0.021
Neg logit contributions
iding-0.055
 som-0.052
gh-0.052
 appetite-0.051
oving-0.050
Token.
Token ID13
Feature activation-8.23e-01

Pos logit contributions
 sky+0.188
 nowhere+0.177
Someone+0.175
 woman+0.166
 nearest+0.148
Neg logit contributions
iding-0.276
 som-0.249
inn-0.248
gh-0.242
oving-0.234
Token She
Token ID1375
Feature activation-7.80e-01

Pos logit contributions
iding+0.023
inn+0.021
 som+0.021
gh+0.020
oving+0.020
Neg logit contributions
 nowhere-0.020
 sky-0.020
 woman-0.019
Someone-0.018
 pieces-0.018
Token was
Token ID373
Feature activation+1.46e+00

Pos logit contributions
 som+0.022
iding+0.022
inn+0.021
oving+0.020
gh+0.020
Neg logit contributions
 sky-0.018
 nowhere-0.016
Someone-0.015
 woman-0.015
 pieces-0.014
Token very
Token ID845
Feature activation+8.43e-01

Pos logit contributions
 sky+0.030
 nowhere+0.027
 woman+0.027
Someone+0.025
 pieces+0.024
Neg logit contributions
iding-0.049
 som-0.045
inn-0.044
gh-0.044
oving-0.044
Token happy
Token ID3772
Feature activation+4.57e+00

Pos logit contributions
 sky+0.015
 woman+0.014
 nowhere+0.014
 old+0.013
Someone+0.013
Neg logit contributions
iding-0.031
 som-0.028
inn-0.028
gh-0.028
oving-0.027
Token went
Token ID1816
Feature activation-2.06e+00

Pos logit contributions
 sky+0.036
 woman+0.033
Someone+0.033
 nowhere+0.032
 curtains+0.031
Neg logit contributions
 som-0.043
iding-0.042
oy-0.041
oving-0.041
gh-0.040
Token home
Token ID1363
Feature activation+3.80e+00

Pos logit contributions
iding+0.068
inn+0.067
 som+0.063
 dive+0.062
gh+0.061
Neg logit contributions
Someone-0.039
 sky-0.039
 nowhere-0.037
 woman-0.034
 pieces-0.032
Token and
Token ID290
Feature activation+3.24e+00

Pos logit contributions
 sky+0.094
Someone+0.089
pill+0.081
 nowhere+0.080
 woman+0.077
Neg logit contributions
iding-0.111
inn-0.101
oving-0.097
 som-0.095
 appetite-0.094
Token showed
Token ID3751
Feature activation+1.53e+00

Pos logit contributions
 sky+0.077
 woman+0.069
 nowhere+0.069
Someone+0.068
 pieces+0.064
Neg logit contributions
iding-0.094
 som-0.090
inn-0.087
gh-0.086
oving-0.085
Token his
Token ID465
Feature activation+2.33e+00

Pos logit contributions
 sky+0.057
Someone+0.055
 nowhere+0.053
 woman+0.053
pill+0.050
Neg logit contributions
inn-0.022
iding-0.022
 som-0.022
gh-0.020
 Finn-0.018
Token mom
Token ID1995
Feature activation+8.66e+00

Pos logit contributions
 sky+0.052
Someone+0.051
 nowhere+0.048
 woman+0.047
pill+0.047
Neg logit contributions
iding-0.064
gh-0.063
 som-0.062
 dive-0.061
 appetite-0.060
Token the
Token ID262
Feature activation+3.74e+00

Pos logit contributions
 sky+0.210
Someone+0.209
 nowhere+0.192
 woman+0.191
 nearest+0.177
Neg logit contributions
iding-0.249
inn-0.231
 som-0.219
gh-0.208
oving-0.205
Token rock
Token ID3881
Feature activation+1.03e-01

Pos logit contributions
Someone+0.103
 nowhere+0.101
 sky+0.101
 woman+0.100
s+0.097
Neg logit contributions
 som-0.081
iding-0.081
gh-0.078
 dive-0.072
inn-0.071
Token.
Token ID13
Feature activation+1.36e-01

Pos logit contributions
 sky+0.002
 nowhere+0.002
 woman+0.002
Someone+0.002
 pieces+0.002
Neg logit contributions
iding-0.003
 som-0.003
inn-0.003
gh-0.003
oving-0.003
Token His
Token ID2399
Feature activation+2.56e-02

Pos logit contributions
 sky+0.002
 nowhere+0.002
 woman+0.002
Someone+0.002
 pieces+0.002
Neg logit contributions
iding-0.005
 som-0.005
inn-0.005
gh-0.005
oving-0.005
Token mom
Token ID1995
Feature activation+5.04e+00

Pos logit contributions
 sky+0.000
 nowhere+0.000
Someone+0.000
 woman+0.000
 pieces+0.000
Neg logit contributions
iding-0.001
gh-0.001
 som-0.001
 appetite-0.001
inn-0.001
TokenL
Token ID43
Feature activation-3.13e+00

Pos logit contributions
 woman+0.044
 nowhere+0.043
 sky+0.042
Someone+0.038
keeper+0.034
Neg logit contributions
iding-0.129
inn-0.123
gh-0.120
 som-0.119
oving-0.114
Tokenily
Token ID813
Feature activation+7.04e-01

Pos logit contributions
iding+0.069
inn+0.067
gh+0.061
oy+0.056
 som+0.056
Neg logit contributions
 sky-0.097
 nowhere-0.096
 woman-0.095
Someone-0.093
keeper-0.087
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
 sky+0.011
 nowhere+0.009
 woman+0.009
 pieces+0.008
s+0.008
Neg logit contributions
iding-0.029
oving-0.026
inn-0.026
gh-0.026
 som-0.026
Token Ben
Token ID3932
Feature activation-1.45e+00

Pos logit contributions
 sky+0.040
 nowhere+0.037
 woman+0.035
 pieces+0.034
Someone+0.034
Neg logit contributions
iding-0.051
 som-0.047
gh-0.046
inn-0.046
oving-0.045
Token are
Token ID389
Feature activation+2.61e+00

Pos logit contributions
iding+0.058
oving+0.053
inn+0.052
gh+0.052
 som+0.051
Neg logit contributions
 sky-0.025
 woman-0.021
 lost-0.021
 nowhere-0.021
 flowers-0.020
Token brother
Token ID3956
Feature activation+8.64e+00

Pos logit contributions
 sky+0.058
 nowhere+0.055
 woman+0.054
Someone+0.051
 pieces+0.049
Neg logit contributions
iding-0.083
inn-0.075
 som-0.075
gh-0.074
oving-0.073
Token and
Token ID290
Feature activation+2.77e+00

Pos logit contributions
 sky+0.119
 woman+0.108
 nowhere+0.106
s+0.096
 pieces+0.094
Neg logit contributions
iding-0.364
gh-0.340
 som-0.338
oving-0.333
inn-0.332
Token sister
Token ID6621
Feature activation+7.46e+00

Pos logit contributions
 woman+0.057
 sky+0.057
 nowhere+0.052
 she+0.049
 bird+0.049
Neg logit contributions
iding-0.098
inn-0.086
oving-0.085
 som-0.083
gh-0.082
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
 sky+0.149
 woman+0.139
 nowhere+0.139
s+0.127
 pieces+0.123
Neg logit contributions
iding-0.263
 som-0.240
inn-0.238
gh-0.237
oving-0.235
Token They
Token ID1119
Feature activation-1.46e+00

Pos logit contributions
 sky+0.002
s+0.002
+0.002
 nowhere+0.002
 she+0.002
Neg logit contributions
iding-0.005
heit-0.004
oving-0.004
gh-0.004
 som-0.004
Token like
Token ID588
Feature activation+2.26e+00

Pos logit contributions
iding+0.050
gh+0.045
oving+0.045
inn+0.045
 avail+0.044
Neg logit contributions
 sky-0.032
 woman-0.028
 lost-0.028
 flowers-0.027
 living-0.026
Token home
Token ID1363
Feature activation+3.56e+00

Pos logit contributions
iding+0.095
 som+0.087
gh+0.086
inn+0.086
oving+0.086
Neg logit contributions
 sky-0.033
 nowhere-0.031
 woman-0.029
Someone-0.025
 pieces-0.025
Token and
Token ID290
Feature activation+2.76e+00

Pos logit contributions
 sky+0.080
Someone+0.076
 nowhere+0.068
actus+0.067
pill+0.067
Neg logit contributions
iding-0.113
oving-0.098
inn-0.097
 som-0.095
gh-0.093
Token Lisa
Token ID15378
Feature activation+6.73e-01

Pos logit contributions
 sky+0.060
 nowhere+0.057
 woman+0.055
Someone+0.052
 pieces+0.050
Neg logit contributions
iding-0.090
 som-0.082
inn-0.081
gh-0.080
oving-0.079
Token showed
Token ID3751
Feature activation+1.32e+00

Pos logit contributions
 sky+0.013
 nowhere+0.012
 woman+0.012
Someone+0.012
 pieces+0.011
Neg logit contributions
iding-0.023
 som-0.021
gh-0.021
inn-0.020
oving-0.020
Token her
Token ID607
Feature activation+3.04e+00

Pos logit contributions
Someone+0.036
 sky+0.036
 nowhere+0.034
actus+0.034
ich+0.033
Neg logit contributions
iding-0.030
 som-0.029
gh-0.029
inn-0.027
et-0.026
Token mom
Token ID1995
Feature activation+8.64e+00

Pos logit contributions
 sky+0.065
Someone+0.064
 nowhere+0.058
 woman+0.054
actus+0.051
Neg logit contributions
iding-0.091
 som-0.089
gh-0.082
inn-0.081
 dive-0.080
Token all
Token ID477
Feature activation+1.42e+00

Pos logit contributions
 sky+0.182
Someone+0.173
 nowhere+0.163
 woman+0.161
 nearest+0.145
Neg logit contributions
iding-0.280
 som-0.256
inn-0.253
gh-0.247
oving-0.237
Token the
Token ID262
Feature activation+3.13e+00

Pos logit contributions
 sky+0.030
Someone+0.030
 nowhere+0.029
 woman+0.028
keeper+0.026
Neg logit contributions
iding-0.046
inn-0.042
 som-0.041
oving-0.039
gh-0.037
Token things
Token ID1243
Feature activation+3.30e+00

Pos logit contributions
 sky+0.054
 nowhere+0.052
Someone+0.047
 woman+0.046
s+0.041
Neg logit contributions
iding-0.111
 som-0.105
gh-0.103
inn-0.103
oving-0.101
Token she
Token ID673
Feature activation-1.67e+00

Pos logit contributions
 sky+0.040
 nowhere+0.037
 woman+0.034
 pieces+0.029
Someone+0.029
Neg logit contributions
iding-0.140
inn-0.129
 som-0.129
oving-0.127
gh-0.127
Token could
Token ID714
Feature activation-4.26e-01

Pos logit contributions
iding+0.053
 som+0.050
gh+0.049
inn+0.049
oving+0.048
Neg logit contributions
 sky-0.034
 woman-0.030
 nowhere-0.029
Someone-0.028
 pieces-0.028
Token her
Token ID607
Feature activation+7.49e-01

Pos logit contributions
 sky+0.034
 nowhere+0.031
 woman+0.030
Someone+0.029
 pieces+0.026
Neg logit contributions
iding-0.075
 som-0.069
inn-0.069
gh-0.067
oving-0.066
Token house
Token ID2156
Feature activation+3.06e+00

Pos logit contributions
 sky+0.012
 nowhere+0.012
Someone+0.011
 woman+0.011
 pieces+0.009
Neg logit contributions
iding-0.027
 som-0.025
 appetite-0.025
gh-0.024
inn-0.024
Token and
Token ID290
Feature activation+2.35e+00

Pos logit contributions
 sky+0.050
 nowhere+0.046
 woman+0.044
 pieces+0.039
Someone+0.038
Neg logit contributions
iding-0.117
 som-0.108
inn-0.107
gh-0.106
oving-0.105
Token showed
Token ID3751
Feature activation+1.49e+00

Pos logit contributions
 sky+0.053
Someone+0.047
 nowhere+0.046
 woman+0.045
 pieces+0.044
Neg logit contributions
iding-0.068
 som-0.066
gh-0.063
inn-0.062
oving-0.062
Token her
Token ID607
Feature activation+3.13e+00

Pos logit contributions
 sky+0.032
 nowhere+0.031
Someone+0.029
 woman+0.029
 pieces+0.026
Neg logit contributions
iding-0.046
 som-0.044
inn-0.044
gh-0.043
oving-0.041
Token mom
Token ID1995
Feature activation+8.62e+00

Pos logit contributions
 sky+0.060
Someone+0.055
 nowhere+0.055
 woman+0.053
s+0.045
Neg logit contributions
iding-0.104
 som-0.098
gh-0.096
inn-0.094
oving-0.093
Token the
Token ID262
Feature activation+3.26e+00

Pos logit contributions
 sky+0.181
 nowhere+0.168
Someone+0.167
 woman+0.162
 pieces+0.141
Neg logit contributions
iding-0.281
inn-0.254
 som-0.254
gh-0.248
oving-0.240
Token bad
Token ID2089
Feature activation-7.34e-01

Pos logit contributions
 sky+0.065
 nowhere+0.062
 woman+0.059
Someone+0.057
 pieces+0.052
Neg logit contributions
iding-0.109
 som-0.101
gh-0.100
inn-0.099
oving-0.097
Token boo
Token ID22513
Feature activation-1.55e+00

Pos logit contributions
iding+0.026
oving+0.023
inn+0.023
 som+0.022
gh+0.022
Neg logit contributions
 sky-0.015
 woman-0.014
 nowhere-0.014
 pieces-0.013
 old-0.012
Token-
Token ID12
Feature activation-2.02e+00

Pos logit contributions
iding+0.058
 som+0.053
inn+0.053
oving+0.052
gh+0.052
Neg logit contributions
 sky-0.026
 nowhere-0.023
 woman-0.023
 pieces-0.021
Someone-0.021
Tokenbo
Token ID2127
Feature activation-5.13e+00

Pos logit contributions
iding+0.048
gh+0.045
inn+0.045
 som+0.043
oving+0.043
Neg logit contributions
 sky-0.060
 nowhere-0.058
 woman-0.055
Someone-0.053
 curtains-0.052
Token another
Token ID1194
Feature activation+6.07e-01

Pos logit contributions
iding+0.091
oving+0.083
 appetite+0.081
icious+0.080
 accompl+0.078
Neg logit contributions
 sky-0.033
 pieces-0.032
 nowhere-0.029
 flowers-0.028
 pictures-0.027
Token wand
Token ID11569
Feature activation-9.45e-01

Pos logit contributions
 sky+0.014
 nowhere+0.013
 woman+0.012
 pieces+0.012
Someone+0.011
Neg logit contributions
iding-0.020
oving-0.018
 som-0.018
inn-0.017
gh-0.017
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
iding+0.035
heit+0.034
 som+0.034
oving+0.034
icious+0.033
Neg logit contributions
 sky-0.016
 nowhere-0.014
 woman-0.014
 pieces-0.014
s-0.013
Token "
Token ID366
Feature activation+1.08e+00

Pos logit contributions
iding+0.043
 som+0.040
gh+0.039
oving+0.039
inn+0.039
Neg logit contributions
 sky-0.015
 nowhere-0.014
 woman-0.013
Someone-0.012
 pieces-0.011
TokenA
Token ID32
Feature activation-1.71e+00

Pos logit contributions
 sky+0.022
 nowhere+0.021
 woman+0.020
Someone+0.019
 pieces+0.018
Neg logit contributions
iding-0.037
 som-0.033
inn-0.033
gh-0.033
oving-0.033
Tokenbr
Token ID1671
Feature activation-1.46e+01

Pos logit contributions
iding+0.056
oving+0.053
 accompl+0.049
inn+0.049
 appetite+0.047
Neg logit contributions
 sky-0.041
 woman-0.037
 bird-0.034
 pieces-0.033
 nowhere-0.033
Tokenac
Token ID330
Feature activation-4.39e+00

Pos logit contributions
iding+0.329
 som+0.288
gh+0.278
oving+0.277
inn+0.275
Neg logit contributions
 sky-0.456
 nowhere-0.440
 woman-0.428
Someone-0.411
 pieces-0.407
Tokenad
Token ID324
Feature activation-5.56e+00

Pos logit contributions
iding+0.108
 som+0.094
inn+0.093
gh+0.092
oving+0.091
Neg logit contributions
 sky-0.131
 nowhere-0.127
 woman-0.123
Someone-0.118
 pieces-0.116
Tokenab
Token ID397
Feature activation-1.04e+01

Pos logit contributions
iding+0.119
oving+0.109
 som+0.106
inn+0.102
 avail+0.100
Neg logit contributions
 sky-0.178
 nowhere-0.169
 woman-0.168
s-0.158
 bird-0.157
Tokenra
Token ID430
Feature activation-5.79e+00

Pos logit contributions
iding+0.258
oving+0.257
 accompl+0.246
inn+0.246
 som+0.241
Neg logit contributions
 sky-0.276
 woman-0.261
 nowhere-0.255
s-0.253
 bird-0.248
Token!"
Token ID2474
Feature activation+7.68e-01

Pos logit contributions
iding+0.161
oving+0.156
 accompl+0.155
inn+0.154
 margin+0.150
Neg logit contributions
 sky-0.127
 nowhere-0.125
ons-0.122
s-0.122
 woman-0.120
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
iding+0.149
 som+0.136
oving+0.134
 accompl+0.133
inn+0.132
Neg logit contributions
 sky-0.089
 pieces-0.078
s-0.078
 nowhere-0.078
 woman-0.077
Token How
Token ID1374
Feature activation-3.10e+00

Pos logit contributions
iding+0.064
 som+0.060
gh+0.058
oving+0.057
heit+0.056
Neg logit contributions
 sky-0.036
Someone-0.034
 woman-0.031
 nowhere-0.031
s-0.029
Token about
Token ID546
Feature activation-8.74e-02

Pos logit contributions
iding+0.099
inn+0.089
 som+0.089
oving+0.087
gh+0.087
Neg logit contributions
 sky-0.069
 nowhere-0.065
 woman-0.063
Someone-0.059
 pieces-0.058
Token oil
Token ID3056
Feature activation-3.52e+00

Pos logit contributions
iding+0.004
inn+0.003
 som+0.003
gh+0.003
oving+0.003
Neg logit contributions
 sky-0.001
 nowhere-0.001
 woman-0.001
 pieces-0.001
Someone-0.001
Token or
Token ID393
Feature activation+1.43e+00

Pos logit contributions
iding+0.126
 som+0.113
oving+0.113
inn+0.111
 accompl+0.110
Neg logit contributions
 sky-0.070
 nowhere-0.060
 pieces-0.059
s-0.058
 old-0.056
Token marg
Token ID6145
Feature activation-1.42e+01

Pos logit contributions
 sky+0.030
 nowhere+0.028
 woman+0.027
 pieces+0.026
Someone+0.025
Neg logit contributions
iding-0.049
inn-0.044
gh-0.043
oving-0.043
 som-0.042
Tokenarine
Token ID34569
Feature activation-9.09e-01

Pos logit contributions
iding+0.321
oving+0.277
 som+0.269
heit+0.266
 accompl+0.257
Neg logit contributions
 sky-0.445
 nowhere-0.422
 pieces-0.410
Someone-0.383
 stamps-0.381
Token?"
Token ID1701
Feature activation+1.34e+00

Pos logit contributions
iding+0.032
 som+0.030
oving+0.029
inn+0.029
 accompl+0.028
Neg logit contributions
 sky-0.018
 nowhere-0.016
s-0.015
 pieces-0.014
 old-0.014
Token
Token ID198
Feature activation-4.66e-01

Pos logit contributions
 sky+0.025
 nowhere+0.024
 woman+0.023
Someone+0.022
 pieces+0.021
Neg logit contributions
iding-0.047
 som-0.043
inn-0.043
gh-0.042
oving-0.041
Token
Token ID198
Feature activation-6.89e-01

Pos logit contributions
iding+0.015
inn+0.015
 som+0.014
gh+0.014
 Finn+0.013
Neg logit contributions
 sky-0.008
 nowhere-0.008
 woman-0.008
rings-0.007
 pieces-0.007
TokenAnna
Token ID31160
Feature activation-1.96e+00

Pos logit contributions
iding+0.020
 som+0.018
inn+0.018
gh+0.017
oving+0.017
Neg logit contributions
 sky-0.017
 nowhere-0.017
 woman-0.016
Someone-0.015
 pieces-0.015
Token the
Token ID262
Feature activation+1.20e+00

Pos logit contributions
iding+0.159
oving+0.147
 appetite+0.141
icious+0.139
gh+0.138
Neg logit contributions
 sky-0.062
 nowhere-0.062
 pieces-0.057
 woman-0.051
 old-0.045
Token air
Token ID1633
Feature activation-1.50e+00

Pos logit contributions
 nowhere+0.020
 sky+0.018
 woman+0.018
Someone+0.018
s+0.016
Neg logit contributions
iding-0.041
 som-0.039
inn-0.038
gh-0.038
heit-0.036
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
iding+0.064
heit+0.063
icious+0.062
oving+0.061
 AW+0.060
Neg logit contributions
 sky-0.022
 pieces-0.018
 old-0.015
s-0.015
 nowhere-0.015
Token "
Token ID366
Feature activation+1.74e+00

Pos logit contributions
iding+0.013
gh+0.013
oving+0.012
heit+0.012
 avail+0.012
Neg logit contributions
 sky-0.006
s-0.005
 nowhere-0.005
Someone-0.004
 old-0.004
TokenA
Token ID32
Feature activation-1.24e+00

Pos logit contributions
 sky+0.030
Someone+0.027
 nowhere+0.026
 woman+0.026
 pieces+0.023
Neg logit contributions
iding-0.066
gh-0.060
 appetite-0.060
oving-0.060
 som-0.059
Tokenbr
Token ID1671
Feature activation-1.42e+01

Pos logit contributions
iding+0.043
oving+0.040
inn+0.038
 appetite+0.037
omp+0.037
Neg logit contributions
 sky-0.028
 woman-0.025
 bird-0.024
 nowhere-0.023
 pieces-0.023
Tokenac
Token ID330
Feature activation-4.02e+00

Pos logit contributions
iding+0.314
 som+0.271
inn+0.265
gh+0.263
oving+0.259
Neg logit contributions
 sky-0.454
 nowhere-0.439
 woman-0.427
Someone-0.411
 pieces-0.405
Tokenad
Token ID324
Feature activation-5.11e+00

Pos logit contributions
iding+0.090
 som+0.079
gh+0.078
inn+0.078
oving+0.075
Neg logit contributions
 sky-0.128
 nowhere-0.124
 woman-0.123
Someone-0.118
 pieces-0.113
Tokenab
Token ID397
Feature activation-9.83e+00

Pos logit contributions
iding+0.116
oving+0.102
 som+0.102
inn+0.100
gh+0.095
Neg logit contributions
 sky-0.162
 nowhere-0.152
 woman-0.152
 pieces-0.143
s-0.141
Tokenra
Token ID430
Feature activation-5.36e+00

Pos logit contributions
iding+0.235
oving+0.226
inn+0.222
 som+0.218
 accompl+0.215
Neg logit contributions
 sky-0.275
 woman-0.257
 nowhere-0.256
s-0.246
 pieces-0.244
Token!"
Token ID2474
Feature activation+1.59e+00

Pos logit contributions
iding+0.147
oving+0.143
inn+0.142
 accompl+0.142
 margin+0.139
Neg logit contributions
 sky-0.122
ons-0.116
s-0.116
 pieces-0.115
's-0.114
Token did
Token ID750
Feature activation-1.75e+00

Pos logit contributions
iding+0.060
 som+0.055
inn+0.054
gh+0.054
oving+0.053
Neg logit contributions
 sky-0.035
 nowhere-0.034
 woman-0.032
Someone-0.030
 pieces-0.029
Token not
Token ID407
Feature activation-2.08e-01

Pos logit contributions
iding+0.064
inn+0.059
 som+0.058
oving+0.057
gh+0.056
Neg logit contributions
 nowhere-0.030
 sky-0.030
 woman-0.027
Someone-0.025
 pieces-0.024
Token like
Token ID588
Feature activation+1.15e+00

Pos logit contributions
iding+0.007
oving+0.007
heit+0.006
gh+0.006
 som+0.006
Neg logit contributions
 woman-0.005
 sky-0.004
 old-0.004
 children-0.004
 people-0.004
Token oil
Token ID3056
Feature activation-3.38e+00

Pos logit contributions
 sky+0.021
 nowhere+0.020
 woman+0.019
Someone+0.018
 pieces+0.017
Neg logit contributions
iding-0.041
 som-0.038
inn-0.037
gh-0.037
oving-0.036
Token or
Token ID393
Feature activation+1.52e+00

Pos logit contributions
iding+0.134
heit+0.121
inn+0.119
 som+0.119
oving+0.119
Neg logit contributions
 sky-0.057
 pieces-0.051
s-0.049
 old-0.047
 nowhere-0.046
Token marg
Token ID6145
Feature activation-1.40e+01

Pos logit contributions
 sky+0.032
 nowhere+0.030
 pieces+0.030
 woman+0.029
 old+0.028
Neg logit contributions
iding-0.054
inn-0.048
oving-0.046
gh-0.046
 som-0.043
Tokenarine
Token ID34569
Feature activation-6.78e-01

Pos logit contributions
iding+0.313
oving+0.278
heit+0.277
 accompl+0.272
 som+0.267
Neg logit contributions
 sky-0.429
 pieces-0.405
 nowhere-0.394
 stamps-0.361
Someone-0.358
Token.
Token ID13
Feature activation-1.63e+00

Pos logit contributions
iding+0.026
heit+0.024
 som+0.024
inn+0.024
 avail+0.023
Neg logit contributions
 sky-0.011
s-0.010
 pieces-0.010
 nowhere-0.010
 old-0.009
Token But
Token ID887
Feature activation-2.26e+00

Pos logit contributions
iding+0.063
 som+0.058
inn+0.057
gh+0.057
oving+0.056
Neg logit contributions
 sky-0.025
 nowhere-0.023
 woman-0.022
Someone-0.020
 pieces-0.020
Token she
Token ID673
Feature activation-3.50e+00

Pos logit contributions
iding+0.089
 som+0.082
inn+0.081
gh+0.081
oving+0.079
Neg logit contributions
 sky-0.033
 nowhere-0.030
 woman-0.029
Someone-0.027
 pieces-0.025
Token did
Token ID750
Feature activation-1.81e+00

Pos logit contributions
iding+0.125
 som+0.112
inn+0.110
gh+0.110
oving+0.109
Neg logit contributions
 sky-0.067
 nowhere-0.065
 woman-0.062
Someone-0.056
 pieces-0.055
TokenLook
Token ID8567
Feature activation-2.64e+00

Pos logit contributions
 sky+0.065
 woman+0.061
 nowhere+0.060
Someone+0.059
 pieces+0.055
Neg logit contributions
iding-0.097
 som-0.086
oving-0.084
inn-0.084
gh-0.084
Token,
Token ID11
Feature activation-1.67e+00

Pos logit contributions
iding+0.091
oving+0.086
 som+0.085
inn+0.085
 accompl+0.083
Neg logit contributions
 sky-0.045
 nowhere-0.045
s-0.044
 woman-0.042
 bird-0.040
Token Lily
Token ID20037
Feature activation-5.75e-01

Pos logit contributions
iding+0.052
 som+0.047
inn+0.046
gh+0.046
oving+0.045
Neg logit contributions
 sky-0.039
 nowhere-0.037
 woman-0.036
Someone-0.034
 pieces-0.033
Token,
Token ID11
Feature activation-2.56e+00

Pos logit contributions
iding+0.021
inn+0.020
 som+0.019
oving+0.019
 accompl+0.018
Neg logit contributions
 sky-0.012
 woman-0.010
 nowhere-0.010
 pieces-0.010
s-0.009
Token a
Token ID257
Feature activation-8.03e-01

Pos logit contributions
iding+0.090
 som+0.082
inn+0.082
gh+0.081
oving+0.080
Neg logit contributions
 sky-0.048
 nowhere-0.045
 woman-0.043
Someone-0.040
 pieces-0.039
Token che
Token ID1125
Feature activation-1.39e+01

Pos logit contributions
iding+0.034
oving+0.030
inn+0.030
ided+0.029
gh+0.028
Neg logit contributions
 sky-0.014
 woman-0.013
 bird-0.011
 nowhere-0.011
 old-0.010
Tokenet
Token ID316
Feature activation-6.16e+00

Pos logit contributions
iding+0.255
oving+0.205
 som+0.201
 accompl+0.195
inn+0.190
Neg logit contributions
 sky-0.491
 nowhere-0.468
 pieces-0.463
 woman-0.455
 blood-0.430
Tokenah
Token ID993
Feature activation-4.89e+00

Pos logit contributions
iding+0.156
inn+0.136
 accompl+0.131
oving+0.130
 som+0.126
Neg logit contributions
 sky-0.187
 woman-0.173
 bird-0.167
s-0.166
 pieces-0.165
Token!"
Token ID2474
Feature activation+1.42e+00

Pos logit contributions
iding+0.116
inn+0.104
oving+0.098
 som+0.098
 accompl+0.093
Neg logit contributions
 sky-0.150
 nowhere-0.140
 woman-0.139
 pieces-0.134
Someone-0.132
Token Sam
Token ID3409
Feature activation-1.76e+00

Pos logit contributions
 sky+0.041
 nowhere+0.040
 woman+0.039
Someone+0.037
 pieces+0.036
Neg logit contributions
iding-0.036
 som-0.031
inn-0.031
gh-0.031
oving-0.030
Token said
Token ID531
Feature activation-1.03e+00

Pos logit contributions
iding+0.075
gh+0.068
inn+0.068
 som+0.067
oving+0.066
Neg logit contributions
 sky-0.024
 woman-0.022
 nowhere-0.021
s-0.020
 pieces-0.019
Token She
Token ID1375
Feature activation-1.43e+00

Pos logit contributions
iding+0.057
inn+0.052
 som+0.052
gh+0.051
oving+0.051
Neg logit contributions
 sky-0.021
 nowhere-0.021
 woman-0.020
 pieces-0.017
Someone-0.017
Token said
Token ID531
Feature activation+1.47e-01

Pos logit contributions
iding+0.039
 som+0.037
inn+0.037
gh+0.035
oving+0.035
Neg logit contributions
 sky-0.036
 nowhere-0.032
 woman-0.032
Someone-0.031
 pieces-0.029
Token,
Token ID11
Feature activation-8.76e-01

Pos logit contributions
 sky+0.003
 nowhere+0.003
 woman+0.002
Someone+0.002
 pieces+0.002
Neg logit contributions
iding-0.005
inn-0.005
oving-0.005
 som-0.005
gh-0.005
Token "
Token ID366
Feature activation+1.63e+00

Pos logit contributions
iding+0.033
oving+0.030
inn+0.030
 som+0.030
gh+0.030
Neg logit contributions
 sky-0.015
 nowhere-0.014
 woman-0.014
Someone-0.012
 pieces-0.012
TokenA
Token ID32
Feature activation-1.61e+00

Pos logit contributions
 sky+0.037
 nowhere+0.036
 woman+0.034
Someone+0.032
 pieces+0.032
Neg logit contributions
iding-0.051
 som-0.046
inn-0.046
gh-0.045
oving-0.045
Tokenbr
Token ID1671
Feature activation-1.39e+01

Pos logit contributions
iding+0.058
oving+0.052
inn+0.051
 accompl+0.048
ided+0.048
Neg logit contributions
 sky-0.033
 woman-0.030
 bird-0.029
 pieces-0.028
 old-0.028
Tokenac
Token ID330
Feature activation-4.04e+00

Pos logit contributions
iding+0.312
 som+0.279
oving+0.268
gh+0.268
inn+0.257
Neg logit contributions
 sky-0.429
 nowhere-0.417
 woman-0.402
Someone-0.388
 pieces-0.388
Tokenad
Token ID324
Feature activation-5.26e+00

Pos logit contributions
iding+0.107
 som+0.094
inn+0.092
oving+0.090
gh+0.089
Neg logit contributions
 sky-0.114
 nowhere-0.109
 woman-0.105
 pieces-0.101
Someone-0.100
Tokenab
Token ID397
Feature activation-9.93e+00

Pos logit contributions
iding+0.132
oving+0.125
 avail+0.121
 som+0.121
inn+0.117
Neg logit contributions
 sky-0.147
 nowhere-0.139
 woman-0.139
s-0.134
 bird-0.131
Tokenra
Token ID430
Feature activation-5.43e+00

Pos logit contributions
iding+0.254
oving+0.248
 accompl+0.240
inn+0.239
 som+0.239
Neg logit contributions
 sky-0.251
 nowhere-0.240
 woman-0.237
s-0.234
 bird-0.230
Token!"
Token ID2474
Feature activation+8.63e-01

Pos logit contributions
iding+0.173
oving+0.172
 accompl+0.170
 som+0.168
inn+0.168
Neg logit contributions
 sky-0.094
's-0.093
 nowhere-0.093
s-0.092
ons-0.092
Token felt
Token ID2936
Feature activation+2.43e+00

Pos logit contributions
iding+0.029
inn+0.026
gh+0.026
oving+0.025
 som+0.025
Neg logit contributions
 sky-0.010
 nowhere-0.009
 woman-0.009
s-0.008
 pieces-0.008
Token as
Token ID355
Feature activation+2.87e+00

Pos logit contributions
 sky+0.047
 nowhere+0.045
 woman+0.042
Someone+0.039
 pieces+0.038
Neg logit contributions
iding-0.085
 som-0.077
inn-0.077
gh-0.076
oving-0.076
Token fast
Token ID3049
Feature activation-2.73e+00

Pos logit contributions
 sky+0.063
 nowhere+0.061
 woman+0.057
Someone+0.055
 pieces+0.054
Neg logit contributions
iding-0.091
 som-0.082
inn-0.080
gh-0.080
oving-0.079
Token as
Token ID355
Feature activation+2.02e+00

Pos logit contributions
iding+0.093
gh+0.084
oving+0.084
inn+0.082
icious+0.081
Neg logit contributions
 sky-0.058
 nowhere-0.054
 woman-0.051
 pieces-0.048
 she-0.047
Token a
Token ID257
Feature activation-4.24e-01

Pos logit contributions
 sky+0.020
 nowhere+0.017
 woman+0.016
Someone+0.013
 pieces+0.012
Neg logit contributions
iding-0.090
 som-0.084
inn-0.084
gh-0.083
oving-0.083
Token che
Token ID1125
Feature activation-1.39e+01

Pos logit contributions
iding+0.014
oving+0.014
inn+0.013
heit+0.013
bit+0.012
Neg logit contributions
 sky-0.010
 woman-0.009
 bird-0.009
 nowhere-0.008
 old-0.008
Tokenet
Token ID316
Feature activation-6.61e+00

Pos logit contributions
iding+0.237
oving+0.197
 som+0.194
 accompl+0.191
 compete+0.181
Neg logit contributions
 sky-0.480
 nowhere-0.478
 pieces-0.452
 woman-0.435
 blood-0.425
Tokenah
Token ID993
Feature activation-5.21e+00

Pos logit contributions
iding+0.216
oving+0.202
inn+0.198
heit+0.196
 accompl+0.195
Neg logit contributions
 sky-0.144
 nowhere-0.127
 woman-0.126
s-0.119
 pieces-0.114
Token!
Token ID0
Feature activation-2.31e-01

Pos logit contributions
iding+0.147
inn+0.133
oving+0.131
 som+0.130
gh+0.126
Neg logit contributions
 sky-0.135
 nowhere-0.127
 woman-0.123
Someone-0.116
 pieces-0.115
Token Her
Token ID2332
Feature activation-1.01e+00

Pos logit contributions
iding+0.008
 som+0.007
inn+0.007
gh+0.007
oving+0.007
Neg logit contributions
 sky-0.004
 nowhere-0.004
 woman-0.004
Someone-0.004
 pieces-0.004
Token life
Token ID1204
Feature activation-1.68e+00

Pos logit contributions
iding+0.033
 som+0.030
inn+0.029
gh+0.029
oving+0.029
Neg logit contributions
 sky-0.022
 nowhere-0.021
 woman-0.020
Someone-0.019
 pieces-0.018
Token and
Token ID290
Feature activation+9.95e-01

Pos logit contributions
 sky+0.027
 nowhere+0.024
 woman+0.023
 pieces+0.021
s+0.019
Neg logit contributions
iding-0.080
inn-0.074
 som-0.074
gh-0.074
oving-0.074
Token said
Token ID531
Feature activation-9.28e-02

Pos logit contributions
 sky+0.022
 nowhere+0.021
 woman+0.020
Someone+0.019
 pieces+0.018
Neg logit contributions
iding-0.031
 som-0.029
inn-0.027
oving-0.027
gh-0.027
Token,
Token ID11
Feature activation-8.14e-01

Pos logit contributions
iding+0.003
inn+0.003
oving+0.003
icious+0.003
 som+0.003
Neg logit contributions
 sky-0.001
 she-0.001
s-0.001
 woman-0.001
 that-0.001
Token "
Token ID366
Feature activation+1.74e+00

Pos logit contributions
iding+0.031
inn+0.029
oving+0.029
gh+0.029
 som+0.029
Neg logit contributions
 sky-0.013
 nowhere-0.012
 woman-0.011
Someone-0.010
s-0.009
TokenA
Token ID32
Feature activation-1.27e+00

Pos logit contributions
 sky+0.037
 nowhere+0.035
 woman+0.034
Someone+0.032
 pieces+0.031
Neg logit contributions
iding-0.058
 som-0.052
inn-0.051
gh-0.051
oving-0.051
Tokenbr
Token ID1671
Feature activation-1.38e+01

Pos logit contributions
iding+0.043
oving+0.041
inn+0.038
 appetite+0.037
heit+0.037
Neg logit contributions
 sky-0.028
 bird-0.025
 woman-0.024
 old-0.023
 nowhere-0.022
Tokenac
Token ID330
Feature activation-4.01e+00

Pos logit contributions
iding+0.302
 som+0.266
gh+0.257
oving+0.256
inn+0.249
Neg logit contributions
 sky-0.440
 nowhere-0.427
 woman-0.412
Someone-0.398
 pieces-0.396
Tokenad
Token ID324
Feature activation-5.13e+00

Pos logit contributions
iding+0.085
gh+0.076
 som+0.075
inn+0.074
oving+0.071
Neg logit contributions
 sky-0.131
 woman-0.127
 nowhere-0.127
Someone-0.121
s-0.116
Tokenab
Token ID397
Feature activation-9.97e+00

Pos logit contributions
iding+0.114
oving+0.108
 avail+0.103
 som+0.103
inn+0.100
Neg logit contributions
 sky-0.156
 nowhere-0.149
 woman-0.146
 bird-0.142
s-0.141
Tokenra
Token ID430
Feature activation-5.42e+00

Pos logit contributions
iding+0.244
oving+0.238
inn+0.227
 som+0.224
 accompl+0.222
Neg logit contributions
 sky-0.271
 nowhere-0.260
 woman-0.251
s-0.244
 bird-0.244
Token!"
Token ID2474
Feature activation+9.53e-01

Pos logit contributions
iding+0.151
oving+0.149
inn+0.147
 accompl+0.144
 margin+0.141
Neg logit contributions
 nowhere-0.119
 sky-0.118
ons-0.114
's-0.112
 woman-0.111
Token
Token ID198
Feature activation+1.33e-01

Pos logit contributions
inn+0.017
iding+0.016
 som+0.015
oving+0.014
gh+0.014
Neg logit contributions
 nowhere-0.012
 woman-0.011
 sky-0.011
 pieces-0.011
Someone-0.010
Token
Token ID198
Feature activation-1.57e-01

Pos logit contributions
 sky+0.003
 woman+0.003
 nowhere+0.003
 pieces+0.003
 candles+0.002
Neg logit contributions
iding-0.004
inn-0.004
gh-0.004
 som-0.004
oving-0.004
TokenBut
Token ID1537
Feature activation-1.53e+00

Pos logit contributions
iding+0.005
 som+0.004
inn+0.004
gh+0.004
oving+0.004
Neg logit contributions
 sky-0.004
 nowhere-0.004
 woman-0.004
 pieces-0.003
Someone-0.003
Token when
Token ID618
Feature activation+1.77e+00

Pos logit contributions
iding+0.051
 som+0.046
inn+0.046
gh+0.045
oving+0.045
Neg logit contributions
 sky-0.032
 nowhere-0.030
 woman-0.029
Someone-0.028
 pieces-0.027
Token she
Token ID673
Feature activation-3.84e+00

Pos logit contributions
 sky+0.020
 nowhere+0.018
 woman+0.017
Someone+0.015
 pieces+0.014
Neg logit contributions
iding-0.076
 som-0.071
inn-0.070
gh-0.070
oving-0.069
Token che
Token ID1125
Feature activation-1.38e+01

Pos logit contributions
iding+0.139
 som+0.125
oving+0.123
inn+0.123
gh+0.122
Neg logit contributions
 sky-0.072
 nowhere-0.069
 woman-0.063
Someone-0.059
 pieces-0.058
Tokenwed
Token ID19103
Feature activation-2.13e+00

Pos logit contributions
iding+0.265
 som+0.226
oving+0.206
gh+0.205
 accompl+0.201
Neg logit contributions
 nowhere-0.471
 sky-0.463
 pieces-0.438
 woman-0.432
Someone-0.422
Token her
Token ID607
Feature activation-1.29e-01

Pos logit contributions
iding+0.079
 som+0.072
oving+0.071
 appetite+0.070
gh+0.068
Neg logit contributions
 sky-0.039
 pieces-0.034
 nowhere-0.034
s-0.032
 woman-0.032
Token nails
Token ID23361
Feature activation+1.85e-01

Pos logit contributions
iding+0.004
gh+0.004
 som+0.004
inn+0.003
oving+0.003
Neg logit contributions
 nowhere-0.003
 sky-0.003
 woman-0.003
Someone-0.003
keeper-0.002
Token,
Token ID11
Feature activation-7.97e-01

Pos logit contributions
 sky+0.004
 nowhere+0.004
 woman+0.003
 pieces+0.003
s+0.003
Neg logit contributions
iding-0.006
 som-0.005
inn-0.005
oving-0.005
gh-0.005
Token she
Token ID673
Feature activation-1.90e+00

Pos logit contributions
iding+0.030
 som+0.029
gh+0.028
inn+0.028
oving+0.027
Neg logit contributions
 sky-0.011
 nowhere-0.010
 woman-0.010
Someone-0.009
s-0.008
Token it
Token ID340
Feature activation+2.35e+00

Pos logit contributions
 sky+0.004
 woman+0.003
 nowhere+0.003
s+0.003
 flowers+0.003
Neg logit contributions
iding-0.013
oving-0.013
icious-0.013
 appetite-0.012
inn-0.012
Token around
Token ID1088
Feature activation+9.45e-01

Pos logit contributions
 sky+0.041
 nowhere+0.037
s+0.035
 pieces+0.034
 woman+0.031
Neg logit contributions
iding-0.087
 som-0.082
 appetite-0.081
oving-0.081
icious-0.081
Token.
Token ID13
Feature activation-5.91e-02

Pos logit contributions
 sky+0.011
 nowhere+0.011
 woman+0.009
 pieces+0.008
 flowers+0.007
Neg logit contributions
iding-0.044
oving-0.041
heit-0.040
icious-0.040
 AW-0.039
Token "
Token ID366
Feature activation+1.86e+00

Pos logit contributions
iding+0.002
 som+0.002
gh+0.002
inn+0.002
oving+0.002
Neg logit contributions
 sky-0.001
 nowhere-0.001
 woman-0.001
Someone-0.001
 pieces-0.001
TokenA
Token ID32
Feature activation-1.12e+00

Pos logit contributions
 sky+0.039
 nowhere+0.036
 woman+0.035
Someone+0.034
 pieces+0.032
Neg logit contributions
iding-0.063
 som-0.057
gh-0.056
inn-0.056
oving-0.056
Tokenbr
Token ID1671
Feature activation-1.38e+01

Pos logit contributions
iding+0.034
oving+0.031
inn+0.030
 accompl+0.029
 som+0.028
Neg logit contributions
 sky-0.029
 woman-0.027
 nowhere-0.025
 pieces-0.024
 bird-0.024
Tokenac
Token ID330
Feature activation-3.63e+00

Pos logit contributions
iding+0.325
 som+0.280
inn+0.280
gh+0.272
oving+0.268
Neg logit contributions
 sky-0.424
 nowhere-0.410
 woman-0.399
Someone-0.383
 pieces-0.375
Tokenad
Token ID324
Feature activation-4.88e+00

Pos logit contributions
iding+0.086
 som+0.074
gh+0.074
inn+0.073
oving+0.071
Neg logit contributions
 sky-0.112
 nowhere-0.109
 woman-0.106
Someone-0.103
 pieces-0.099
Tokenab
Token ID397
Feature activation-9.64e+00

Pos logit contributions
iding+0.102
 som+0.090
oving+0.090
inn+0.088
 accompl+0.082
Neg logit contributions
 sky-0.161
 nowhere-0.153
 woman-0.152
s-0.142
 pieces-0.141
Tokenra
Token ID430
Feature activation-5.18e+00

Pos logit contributions
iding+0.234
oving+0.231
inn+0.225
 accompl+0.221
 som+0.221
Neg logit contributions
 sky-0.261
 woman-0.245
 nowhere-0.240
s-0.237
 bird-0.229
Token!"
Token ID2474
Feature activation+1.38e+00

Pos logit contributions
iding+0.140
inn+0.137
 accompl+0.135
oving+0.135
 margin+0.131
Neg logit contributions
 sky-0.119
s-0.113
 nowhere-0.113
 woman-0.111
ons-0.110
Token and
Token ID290
Feature activation+2.66e+00

Pos logit contributions
 sky+0.042
s+0.037
 woman+0.036
 pieces+0.035
 nowhere+0.035
Neg logit contributions
iding-0.103
heit-0.102
oving-0.100
 som-0.100
 AW-0.096
Token saying
Token ID2282
Feature activation+6.26e-01

Pos logit contributions
 nowhere+0.055
 sky+0.053
 woman+0.051
 pieces+0.046
 lost+0.044
Neg logit contributions
iding-0.097
inn-0.089
oving-0.086
gh-0.086
icious-0.082
Token,
Token ID11
Feature activation-2.56e-01

Pos logit contributions
 she+0.008
 that+0.008
 to+0.007
 sky+0.006
 a+0.006
Neg logit contributions
oving-0.026
iding-0.026
icious-0.026
rated-0.026
inn-0.025
Token "
Token ID366
Feature activation+1.79e+00

Pos logit contributions
iding+0.010
inn+0.009
heit+0.009
gh+0.009
 som+0.009
Neg logit contributions
 sky-0.004
 woman-0.004
 nowhere-0.004
s-0.003
 she-0.003
TokenA
Token ID32
Feature activation-1.19e+00

Pos logit contributions
 sky+0.042
 nowhere+0.041
 woman+0.039
 pieces+0.036
Someone+0.035
Neg logit contributions
iding-0.054
 som-0.048
inn-0.048
gh-0.047
oving-0.047
Tokenbr
Token ID1671
Feature activation-1.38e+01

Pos logit contributions
iding+0.043
oving+0.039
inn+0.037
 accompl+0.036
 som+0.035
Neg logit contributions
 sky-0.025
 woman-0.023
 nowhere-0.021
 old-0.021
 bird-0.021
Tokenac
Token ID330
Feature activation-3.91e+00

Pos logit contributions
iding+0.300
 som+0.260
gh+0.251
inn+0.250
oving+0.249
Neg logit contributions
 sky-0.443
 nowhere-0.429
 woman-0.418
Someone-0.402
 pieces-0.397
Tokenad
Token ID324
Feature activation-4.89e+00

Pos logit contributions
iding+0.097
 som+0.085
inn+0.084
gh+0.082
oving+0.082
Neg logit contributions
 sky-0.116
 nowhere-0.112
 woman-0.109
Someone-0.104
 pieces-0.102
Tokenab
Token ID397
Feature activation-9.69e+00

Pos logit contributions
iding+0.109
oving+0.101
 som+0.097
inn+0.094
 avail+0.093
Neg logit contributions
 sky-0.154
 woman-0.145
 nowhere-0.145
s-0.137
 bird-0.136
Tokenra
Token ID430
Feature activation-5.27e+00

Pos logit contributions
iding+0.244
oving+0.237
inn+0.227
 som+0.226
 accompl+0.225
Neg logit contributions
 sky-0.256
 woman-0.241
 nowhere-0.240
s-0.234
 bird-0.228
Token!"
Token ID2474
Feature activation+1.14e+00

Pos logit contributions
oving+0.167
 accompl+0.165
iding+0.164
inn+0.162
 margin+0.161
Neg logit contributions
 sky-0.096
's-0.093
s-0.092
ons-0.092
 woman-0.088
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
iding+0.006
oving+0.006
heit+0.006
 som+0.006
gh+0.006
Neg logit contributions
 sky-0.002
 woman-0.002
 nowhere-0.001
 pieces-0.001
s-0.001
Token said
Token ID531
Feature activation+5.01e-01

Pos logit contributions
 sky+0.040
 nowhere+0.038
 woman+0.037
Someone+0.036
 pieces+0.034
Neg logit contributions
iding-0.055
 som-0.051
inn-0.049
gh-0.049
oving-0.048
Token,
Token ID11
Feature activation-2.93e-01

Pos logit contributions
 she+0.007
s+0.007
 sky+0.006
 that+0.006
 to+0.006
Neg logit contributions
iding-0.019
oving-0.019
inn-0.019
icious-0.019
rated-0.019
Token "
Token ID366
Feature activation+2.13e+00

Pos logit contributions
iding+0.012
oving+0.011
inn+0.011
gh+0.011
 som+0.011
Neg logit contributions
 sky-0.005
 woman-0.004
 nowhere-0.004
s-0.003
Someone-0.003
TokenA
Token ID32
Feature activation-1.10e+00

Pos logit contributions
 sky+0.049
 nowhere+0.045
 woman+0.045
Someone+0.043
 pieces+0.040
Neg logit contributions
iding-0.069
inn-0.061
 som-0.061
gh-0.060
oving-0.060
Tokenbr
Token ID1671
Feature activation-1.37e+01

Pos logit contributions
iding+0.039
oving+0.036
inn+0.035
 accompl+0.034
heit+0.034
Neg logit contributions
 sky-0.023
 woman-0.021
 bird-0.019
 old-0.018
 nowhere-0.018
Tokenac
Token ID330
Feature activation-3.78e+00

Pos logit contributions
iding+0.283
inn+0.242
 som+0.230
gh+0.226
oving+0.217
Neg logit contributions
 sky-0.468
 nowhere-0.452
 woman-0.444
Someone-0.429
 pieces-0.417
Tokenad
Token ID324
Feature activation-4.77e+00

Pos logit contributions
iding+0.086
gh+0.076
 som+0.075
inn+0.074
oving+0.071
Neg logit contributions
 sky-0.118
 nowhere-0.114
 woman-0.113
Someone-0.110
 pieces-0.103
Tokenab
Token ID397
Feature activation-9.85e+00

Pos logit contributions
iding+0.107
oving+0.099
 som+0.096
inn+0.093
heit+0.090
Neg logit contributions
 sky-0.151
 woman-0.142
 nowhere-0.141
s-0.133
 pieces-0.131
Tokenra
Token ID430
Feature activation-5.18e+00

Pos logit contributions
iding+0.236
oving+0.220
 som+0.216
inn+0.216
 accompl+0.205
Neg logit contributions
 sky-0.284
 woman-0.270
 nowhere-0.269
s-0.251
Someone-0.250
Token,
Token ID11
Feature activation-2.94e+00

Pos logit contributions
iding+0.166
oving+0.163
inn+0.161
 accompl+0.160
 som+0.160
Neg logit contributions
 sky-0.098
s-0.092
 nowhere-0.091
 woman-0.091
's-0.088
Token said
Token ID531
Feature activation-1.29e-02

Pos logit contributions
iding+0.112
 som+0.102
inn+0.102
gh+0.101
oving+0.101
Neg logit contributions
 sky-0.042
 nowhere-0.040
 woman-0.037
Someone-0.033
 pieces-0.032
Token together
Token ID1978
Feature activation-2.96e+00

Pos logit contributions
iding+0.000
inn+0.000
oving+0.000
icious+0.000
 som+0.000
Neg logit contributions
 sky-0.000
 woman-0.000
 nowhere-0.000
s-0.000
 old-0.000
Token,
Token ID11
Feature activation-8.00e-01

Pos logit contributions
iding+0.113
oving+0.105
inn+0.105
heit+0.104
 som+0.102
Neg logit contributions
 sky-0.050
 nowhere-0.046
 woman-0.045
s-0.043
 pieces-0.042
Token "
Token ID366
Feature activation+1.72e+00

Pos logit contributions
iding+0.032
gh+0.031
inn+0.031
oving+0.030
 som+0.030
Neg logit contributions
 sky-0.012
 woman-0.010
 nowhere-0.010
Someone-0.008
s-0.008
TokenA
Token ID32
Feature activation-1.59e+00

Pos logit contributions
 sky+0.034
 nowhere+0.033
 woman+0.031
 pieces+0.028
Someone+0.028
Neg logit contributions
iding-0.059
 som-0.053
inn-0.053
gh-0.052
oving-0.052
Tokenbr
Token ID1671
Feature activation-1.37e+01

Pos logit contributions
iding+0.051
inn+0.046
oving+0.045
 som+0.045
gh+0.044
Neg logit contributions
 sky-0.037
 woman-0.035
 nowhere-0.034
Someone-0.031
 pieces-0.031
Tokenac
Token ID330
Feature activation-3.69e+00

Pos logit contributions
iding+0.312
inn+0.269
 som+0.260
gh+0.254
oving+0.248
Neg logit contributions
 sky-0.439
 nowhere-0.425
 woman-0.415
Someone-0.399
 pieces-0.387
Tokenad
Token ID324
Feature activation-4.86e+00

Pos logit contributions
iding+0.081
gh+0.072
inn+0.069
 som+0.069
oving+0.067
Neg logit contributions
 sky-0.118
 nowhere-0.115
 woman-0.113
Someone-0.110
s-0.104
Tokenab
Token ID397
Feature activation-9.61e+00

Pos logit contributions
iding+0.109
oving+0.098
 som+0.098
inn+0.096
 avail+0.090
Neg logit contributions
 sky-0.152
 woman-0.144
 nowhere-0.144
s-0.134
 pieces-0.133
Tokenra
Token ID430
Feature activation-5.16e+00

Pos logit contributions
iding+0.242
inn+0.237
oving+0.232
 accompl+0.231
 som+0.228
Neg logit contributions
 sky-0.253
 woman-0.240
s-0.233
 nowhere-0.230
 bird-0.225
Token!"
Token ID2474
Feature activation+1.26e+00

Pos logit contributions
iding+0.151
 som+0.149
inn+0.148
oving+0.148
 accompl+0.146
Neg logit contributions
 sky-0.109
 nowhere-0.103
s-0.101
's-0.099
 woman-0.099
Token soon
Token ID2582
Feature activation+1.18e+00

Pos logit contributions
 sky+0.027
 nowhere+0.025
 woman+0.024
Someone+0.022
 pieces+0.022
Neg logit contributions
iding-0.048
 som-0.044
inn-0.043
gh-0.043
oving-0.043
Token nothing
Token ID2147
Feature activation+1.91e+00

Pos logit contributions
 sky+0.025
 nowhere+0.023
 woman+0.022
 pieces+0.020
Someone+0.020
Neg logit contributions
iding-0.040
inn-0.036
 som-0.036
gh-0.036
oving-0.036
Token but
Token ID475
Feature activation-5.06e-01

Pos logit contributions
 sky+0.033
 nowhere+0.032
 woman+0.030
Someone+0.028
 pieces+0.027
Neg logit contributions
iding-0.070
 som-0.064
inn-0.063
gh-0.063
oving-0.062
Token a
Token ID257
Feature activation-1.11e+00

Pos logit contributions
iding+0.017
 som+0.016
gh+0.015
inn+0.015
 accompl+0.015
Neg logit contributions
 sky-0.009
 woman-0.009
 nowhere-0.009
Someone-0.009
 pieces-0.008
Token small
Token ID1402
Feature activation-2.11e+00

Pos logit contributions
iding+0.043
inn+0.039
oving+0.039
 som+0.039
gh+0.038
Neg logit contributions
 sky-0.018
 nowhere-0.017
 woman-0.017
Someone-0.014
 pieces-0.014
Token spe
Token ID693
Feature activation-1.37e+01

Pos logit contributions
iding+0.093
oving+0.086
inn+0.086
gh+0.085
heit+0.082
Neg logit contributions
 sky-0.031
 woman-0.027
 nowhere-0.025
 bird-0.022
 old-0.020
Tokenck
Token ID694
Feature activation-3.92e+00

Pos logit contributions
iding+0.216
 som+0.174
inn+0.170
gh+0.166
oving+0.162
Neg logit contributions
 sky-0.524
 nowhere-0.510
 woman-0.499
Someone-0.483
 pieces-0.477
Token in
Token ID287
Feature activation-4.72e+00

Pos logit contributions
iding+0.143
oving+0.132
inn+0.131
 som+0.131
 accompl+0.130
Neg logit contributions
 sky-0.076
 nowhere-0.067
 woman-0.066
 pieces-0.061
 bird-0.059
Token the
Token ID262
Feature activation+1.22e+00

Pos logit contributions
iding+0.196
oving+0.179
gh+0.170
inn+0.169
 som+0.164
Neg logit contributions
 sky-0.085
 nowhere-0.082
 woman-0.073
 pieces-0.065
 old-0.062
Token sky
Token ID6766
Feature activation+1.18e+00

Pos logit contributions
 nowhere+0.015
Someone+0.014
s+0.013
ons+0.013
 woman+0.012
Neg logit contributions
 som-0.044
iding-0.043
 appetite-0.041
inn-0.041
gh-0.041
Token.
Token ID13
Feature activation-6.66e-01

Pos logit contributions
 sky+0.024
 nowhere+0.021
 woman+0.020
s+0.018
 pieces+0.017
Neg logit contributions
iding-0.044
inn-0.041
oving-0.040
heit-0.040
gh-0.039
Token fun
Token ID1257
Feature activation-3.13e+00

Pos logit contributions
iding+0.003
oving+0.003
heit+0.003
inn+0.003
gh+0.003
Neg logit contributions
 sky-0.003
 nowhere-0.003
 woman-0.003
 pieces-0.003
s-0.002
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
iding+0.117
heit+0.111
inn+0.108
 seventeen+0.107
bit+0.105
Neg logit contributions
 sky-0.052
 pieces-0.048
s-0.047
 nowhere-0.047
 flowers-0.044
Token Lily
Token ID20037
Feature activation+2.11e-01

Pos logit contributions
iding+0.005
gh+0.004
 som+0.004
oving+0.004
inn+0.004
Neg logit contributions
 sky-0.004
 nowhere-0.004
 woman-0.003
Someone-0.003
 pieces-0.003
Token realized
Token ID6939
Feature activation+3.72e+00

Pos logit contributions
 sky+0.003
 nowhere+0.003
 woman+0.003
Someone+0.003
 pieces+0.002
Neg logit contributions
iding-0.008
 som-0.008
gh-0.007
inn-0.007
oving-0.007
Token that
Token ID326
Feature activation+1.21e+00

Pos logit contributions
 sky+0.046
 nowhere+0.037
Someone+0.036
 woman+0.036
 pieces+0.033
Neg logit contributions
iding-0.152
 som-0.146
gh-0.141
inn-0.140
oving-0.139
Token pic
Token ID8301
Feature activation-1.36e+01

Pos logit contributions
 sky+0.026
 woman+0.025
 nowhere+0.025
Someone+0.024
keeper+0.022
Neg logit contributions
iding-0.036
 som-0.035
gh-0.033
inn-0.032
 accompl-0.032
Tokenn
Token ID77
Feature activation-6.01e+00

Pos logit contributions
iding+0.295
 som+0.250
inn+0.247
oving+0.239
gh+0.238
Neg logit contributions
 sky-0.438
 nowhere-0.428
 woman-0.410
Someone-0.394
 pieces-0.390
Tokenics
Token ID873
Feature activation+5.45e-01

Pos logit contributions
iding+0.181
inn+0.161
oving+0.152
gh+0.152
omp+0.149
Neg logit contributions
 woman-0.145
 nowhere-0.130
 sky-0.126
 curtains-0.122
Someone-0.121
Token were
Token ID547
Feature activation+1.22e+00

Pos logit contributions
 sky+0.007
 nowhere+0.006
 woman+0.005
 pieces+0.005
Someone+0.005
Neg logit contributions
iding-0.023
inn-0.021
 som-0.021
oving-0.021
gh-0.021
Token not
Token ID407
Feature activation+1.93e+00

Pos logit contributions
 sky+0.025
 nowhere+0.025
 woman+0.023
 pieces+0.021
Someone+0.021
Neg logit contributions
iding-0.042
inn-0.038
 som-0.037
gh-0.037
oving-0.037
Token so
Token ID523
Feature activation+3.53e-01

Pos logit contributions
 nowhere+0.039
 sky+0.038
 old+0.035
 woman+0.034
 pieces+0.034
Neg logit contributions
iding-0.069
gh-0.062
inn-0.061
oving-0.060
 som-0.060
Token and
Token ID290
Feature activation+1.28e+00

Pos logit contributions
 sky+0.018
 nowhere+0.016
s+0.016
 woman+0.014
 pieces+0.014
Neg logit contributions
iding-0.060
inn-0.058
heit-0.057
gh-0.056
oving-0.056
Token said
Token ID531
Feature activation+2.53e-01

Pos logit contributions
 woman+0.020
 nowhere+0.020
 sky+0.019
 pieces+0.017
 lost+0.016
Neg logit contributions
iding-0.055
inn-0.048
gh-0.047
icious-0.047
oving-0.046
Token,
Token ID11
Feature activation-6.28e-01

Pos logit contributions
 she+0.003
 that+0.003
s+0.003
 to+0.003
 old+0.003
Neg logit contributions
iding-0.010
icious-0.010
inn-0.010
rated-0.010
 avail-0.010
Token "
Token ID366
Feature activation+1.85e+00

Pos logit contributions
iding+0.027
 avail+0.025
inn+0.025
oving+0.025
gh+0.024
Neg logit contributions
 sky-0.008
 woman-0.006
 nowhere-0.006
s-0.005
 old-0.005
TokenA
Token ID32
Feature activation-1.08e+00

Pos logit contributions
 sky+0.036
 nowhere+0.033
Someone+0.033
 woman+0.032
 pieces+0.028
Neg logit contributions
iding-0.067
 som-0.060
gh-0.059
 appetite-0.059
inn-0.059
Tokenbr
Token ID1671
Feature activation-1.36e+01

Pos logit contributions
iding+0.038
oving+0.034
ided+0.032
irm+0.032
 afloat+0.032
Neg logit contributions
 sky-0.023
 woman-0.022
 bird-0.022
 old-0.021
 lawyer-0.020
Tokenac
Token ID330
Feature activation-3.86e+00

Pos logit contributions
iding+0.308
 som+0.271
gh+0.262
oving+0.259
inn+0.258
Neg logit contributions
 sky-0.423
 nowhere-0.410
 woman-0.398
Someone-0.382
 pieces-0.379
Tokenad
Token ID324
Feature activation-4.91e+00

Pos logit contributions
iding+0.104
 som+0.090
inn+0.090
oving+0.086
gh+0.086
Neg logit contributions
 sky-0.108
 nowhere-0.104
 woman-0.099
 pieces-0.096
Someone-0.094
Tokenab
Token ID397
Feature activation-9.74e+00

Pos logit contributions
iding+0.118
oving+0.108
 avail+0.108
 som+0.107
inn+0.105
Neg logit contributions
 sky-0.143
 woman-0.135
 nowhere-0.135
s-0.131
 bird-0.128
Tokenra
Token ID430
Feature activation-5.22e+00

Pos logit contributions
iding+0.241
oving+0.235
inn+0.231
 som+0.229
 accompl+0.226
Neg logit contributions
 sky-0.258
 woman-0.245
 nowhere-0.238
s-0.236
 bird-0.232
Token,
Token ID11
Feature activation-3.14e+00

Pos logit contributions
iding+0.162
 accompl+0.160
inn+0.159
oving+0.156
 som+0.154
Neg logit contributions
s-0.097
's-0.096
 sky-0.095
ons-0.093
 nowhere-0.093
Token and
Token ID290
Feature activation+2.33e+00

Pos logit contributions
 sky+0.011
 nowhere+0.010
 woman+0.009
 pieces+0.008
 flowers+0.007
Neg logit contributions
iding-0.033
oving-0.030
inn-0.030
gh-0.030
 som-0.029
Token said
Token ID531
Feature activation+6.65e-01

Pos logit contributions
 sky+0.043
 nowhere+0.040
 woman+0.039
 pieces+0.035
Someone+0.034
Neg logit contributions
iding-0.087
inn-0.079
gh-0.078
oving-0.077
 som-0.075
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
 sky+0.011
 she+0.010
 woman+0.010
s+0.010
 that+0.009
Neg logit contributions
iding-0.025
inn-0.024
oving-0.023
icious-0.023
 appetite-0.022
Token "
Token ID366
Feature activation+2.38e+00

Pos logit contributions
iding+0.006
oving+0.005
inn+0.005
gh+0.005
 avail+0.005
Neg logit contributions
 sky-0.002
 woman-0.001
 nowhere-0.001
s-0.001
Someone-0.001
TokenA
Token ID32
Feature activation-8.75e-01

Pos logit contributions
 sky+0.050
 nowhere+0.046
 woman+0.044
Someone+0.043
 pieces+0.040
Neg logit contributions
iding-0.081
 som-0.073
inn-0.072
oving-0.072
gh-0.072
Tokenbr
Token ID1671
Feature activation-1.36e+01

Pos logit contributions
iding+0.030
oving+0.029
inn+0.026
 accompl+0.026
 appetite+0.026
Neg logit contributions
 sky-0.019
 woman-0.017
 nowhere-0.017
 old-0.016
 bird-0.015
Tokenac
Token ID330
Feature activation-3.80e+00

Pos logit contributions
iding+0.293
inn+0.250
 som+0.246
gh+0.239
oving+0.232
Neg logit contributions
 sky-0.448
 nowhere-0.433
 woman-0.424
Someone-0.408
 pieces-0.399
Tokenad
Token ID324
Feature activation-4.80e+00

Pos logit contributions
iding+0.081
gh+0.072
 som+0.071
inn+0.068
oving+0.066
Neg logit contributions
 sky-0.123
 nowhere-0.120
 woman-0.120
Someone-0.116
s-0.110
Tokenab
Token ID397
Feature activation-9.74e+00

Pos logit contributions
iding+0.099
oving+0.089
 som+0.087
inn+0.085
 accompl+0.080
Neg logit contributions
 sky-0.160
 nowhere-0.151
 woman-0.150
s-0.140
 bird-0.139
Tokenra
Token ID430
Feature activation-5.24e+00

Pos logit contributions
iding+0.235
oving+0.228
inn+0.219
 som+0.214
 accompl+0.211
Neg logit contributions
 sky-0.275
 nowhere-0.258
 woman-0.257
s-0.242
Someone-0.239
Token!
Token ID0
Feature activation-1.96e+00

Pos logit contributions
iding+0.135
inn+0.133
oving+0.130
 accompl+0.128
 som+0.123
Neg logit contributions
 sky-0.133
 nowhere-0.126
 woman-0.124
s-0.121
's-0.117
Token and
Token ID290
Feature activation+1.79e+00

Pos logit contributions
 sky+0.008
 nowhere+0.007
 woman+0.007
Someone+0.007
 pieces+0.006
Neg logit contributions
iding-0.019
inn-0.017
 som-0.017
gh-0.017
oving-0.017
Token said
Token ID531
Feature activation+4.51e-01

Pos logit contributions
 sky+0.041
 nowhere+0.039
 woman+0.037
Someone+0.036
 pieces+0.034
Neg logit contributions
iding-0.054
 som-0.051
oving-0.048
inn-0.048
gh-0.048
Token,
Token ID11
Feature activation-2.58e-01

Pos logit contributions
 sky+0.009
 nowhere+0.009
 woman+0.009
s+0.008
 pieces+0.008
Neg logit contributions
iding-0.015
inn-0.014
oving-0.013
 som-0.013
gh-0.013
Token "
Token ID366
Feature activation+2.34e+00

Pos logit contributions
iding+0.010
inn+0.009
oving+0.009
gh+0.009
 som+0.009
Neg logit contributions
 sky-0.004
 nowhere-0.004
 woman-0.004
Someone-0.003
s-0.003
TokenA
Token ID32
Feature activation-8.14e-01

Pos logit contributions
 sky+0.056
 nowhere+0.055
 woman+0.055
 old+0.054
s+0.053
Neg logit contributions
iding-0.058
inn-0.058
 som-0.057
gh-0.055
bit-0.053
Tokenbr
Token ID1671
Feature activation-1.35e+01

Pos logit contributions
iding+0.027
oving+0.025
inn+0.024
 appetite+0.023
 som+0.023
Neg logit contributions
 sky-0.018
 nowhere-0.016
 woman-0.016
 pieces-0.015
 bird-0.014
Tokenac
Token ID330
Feature activation-3.58e+00

Pos logit contributions
iding+0.251
inn+0.222
 som+0.191
gh+0.187
oving+0.177
Neg logit contributions
 sky-0.500
 woman-0.479
 nowhere-0.478
Someone-0.459
 pieces-0.442
Tokenad
Token ID324
Feature activation-4.71e+00

Pos logit contributions
iding+0.065
gh+0.063
 som+0.059
inn+0.057
bit+0.057
Neg logit contributions
 sky-0.124
 woman-0.123
 nowhere-0.119
Someone-0.119
s-0.116
Tokenab
Token ID397
Feature activation-9.55e+00

Pos logit contributions
iding+0.103
oving+0.092
 som+0.090
inn+0.088
 avail+0.085
Neg logit contributions
 sky-0.149
 nowhere-0.142
 woman-0.141
s-0.132
 bird-0.132
Tokenra
Token ID430
Feature activation-4.95e+00

Pos logit contributions
iding+0.216
inn+0.192
 som+0.192
oving+0.191
gh+0.180
Neg logit contributions
 sky-0.292
 nowhere-0.281
 woman-0.275
Someone-0.262
 pieces-0.259
Token!"
Token ID2474
Feature activation+1.48e+00

Pos logit contributions
iding+0.138
inn+0.134
oving+0.130
 accompl+0.129
 som+0.126
Neg logit contributions
 sky-0.112
 nowhere-0.111
 woman-0.108
ons-0.105
s-0.104
Token that
Token ID326
Feature activation+4.08e-01

Pos logit contributions
 sky+0.008
 nowhere+0.008
 woman+0.007
 pieces+0.006
Someone+0.005
Neg logit contributions
iding-0.034
inn-0.031
oving-0.031
 som-0.030
gh-0.030
Token he
Token ID339
Feature activation-3.48e+00

Pos logit contributions
 sky+0.006
 nowhere+0.006
 woman+0.005
 pieces+0.005
 old+0.004
Neg logit contributions
iding-0.017
inn-0.016
oving-0.015
 som-0.015
gh-0.015
Token had
Token ID550
Feature activation-4.21e-01

Pos logit contributions
iding+0.127
 som+0.118
gh+0.116
inn+0.116
oving+0.114
Neg logit contributions
 sky-0.059
 nowhere-0.054
 woman-0.052
Someone-0.048
 pieces-0.046
Token used
Token ID973
Feature activation-1.95e+00

Pos logit contributions
iding+0.016
inn+0.014
oving+0.014
 som+0.014
heit+0.013
Neg logit contributions
 nowhere-0.008
 sky-0.008
 woman-0.007
 pieces-0.007
Someone-0.006
Token the
Token ID262
Feature activation+5.87e-01

Pos logit contributions
iding+0.074
oving+0.066
inn+0.066
 som+0.066
gh+0.064
Neg logit contributions
 sky-0.034
 nowhere-0.033
 pieces-0.029
 woman-0.029
 old-0.026
Token squee
Token ID13170
Feature activation-1.35e+01

Pos logit contributions
 sky+0.012
 nowhere+0.012
 woman+0.011
 pieces+0.010
Someone+0.010
Neg logit contributions
iding-0.020
inn-0.018
oving-0.018
 som-0.018
gh-0.018
Tokengee
Token ID29622
Feature activation-9.45e-01

Pos logit contributions
iding+0.362
inn+0.313
icious+0.291
 Deal+0.288
 accompl+0.283
Neg logit contributions
 pieces-0.363
ons-0.325
 nowhere-0.323
 sky-0.318
 needles-0.302
Token to
Token ID284
Feature activation-3.42e+00

Pos logit contributions
iding+0.036
inn+0.033
 som+0.033
oving+0.032
heit+0.032
Neg logit contributions
 sky-0.016
 woman-0.014
 nowhere-0.014
 pieces-0.013
Someone-0.012
Token good
Token ID922
Feature activation-3.38e+00

Pos logit contributions
iding+0.113
inn+0.108
heit+0.099
oving+0.098
 AW+0.098
Neg logit contributions
 sky-0.073
 that-0.068
 woman-0.068
 old-0.067
 she-0.067
Token use
Token ID779
Feature activation-1.19e+00

Pos logit contributions
iding+0.126
inn+0.114
oving+0.110
 AW+0.110
icious+0.109
Neg logit contributions
 sky-0.071
 pieces-0.067
 old-0.060
 woman-0.059
 flowers-0.058
Token!
Token ID0
Feature activation-6.73e-01

Pos logit contributions
iding+0.047
inn+0.042
oving+0.042
icious+0.041
 som+0.040
Neg logit contributions
 sky-0.020
 nowhere-0.019
 pieces-0.018
 old-0.016
 woman-0.015
Token them
Token ID606
Feature activation+1.90e+00

Pos logit contributions
iding+0.001
inn+0.001
 appetite+0.001
gh+0.001
 AW+0.001
Neg logit contributions
 sky-0.000
 pieces-0.000
 woman-0.000
 nowhere-0.000
 old-0.000
Token feel
Token ID1254
Feature activation+4.35e+00

Pos logit contributions
 sky+0.039
 pieces+0.035
 nowhere+0.034
 woman+0.033
 old+0.032
Neg logit contributions
iding-0.063
inn-0.062
gh-0.058
heit-0.057
oving-0.057
Token secure
Token ID5713
Feature activation-2.37e+00

Pos logit contributions
 sky+0.089
 nowhere+0.079
 old+0.077
 pieces+0.075
 woman+0.072
Neg logit contributions
iding-0.159
inn-0.143
gh-0.139
oving-0.137
heit-0.135
Token.
Token ID13
Feature activation-9.01e-01

Pos logit contributions
iding+0.095
inn+0.091
 som+0.089
heit+0.088
gh+0.086
Neg logit contributions
 sky-0.036
 nowhere-0.033
 pieces-0.032
 woman-0.030
 old-0.029
Token The
Token ID383
Feature activation+3.10e-01

Pos logit contributions
iding+0.037
gh+0.034
 som+0.034
oving+0.033
heit+0.032
Neg logit contributions
 sky-0.014
 nowhere-0.012
 woman-0.011
Someone-0.011
s-0.010
Token pers
Token ID2774
Feature activation-1.35e+01

Pos logit contributions
 sky+0.005
 nowhere+0.004
 woman+0.004
 pieces+0.004
Someone+0.004
Neg logit contributions
iding-0.012
inn-0.011
 som-0.011
oving-0.011
gh-0.011
Tokenistant
Token ID10167
Feature activation-2.00e+00

Pos logit contributions
iding+0.248
 som+0.235
 appetite+0.219
inn+0.217
gh+0.213
Neg logit contributions
 sky-0.443
 nowhere-0.412
 pieces-0.402
Someone-0.402
 woman-0.395
Token love
Token ID1842
Feature activation+1.41e+00

Pos logit contributions
iding+0.077
inn+0.069
 accompl+0.068
oving+0.067
 Deal+0.066
Neg logit contributions
 sky-0.041
 pieces-0.037
 woman-0.031
 nowhere-0.031
 old-0.030
Token of
Token ID286
Feature activation-1.96e+00

Pos logit contributions
 sky+0.018
 nowhere+0.015
 pieces+0.014
 woman+0.014
 that+0.013
Neg logit contributions
iding-0.062
oving-0.057
heit-0.056
inn-0.056
 AW-0.055
Token their
Token ID511
Feature activation-1.21e+00

Pos logit contributions
iding+0.079
inn+0.073
 AW+0.072
rated+0.071
oving+0.069
Neg logit contributions
 nowhere-0.031
 sky-0.028
 old-0.028
 that-0.026
 living-0.026
Token parents
Token ID3397
Feature activation+4.51e+00

Pos logit contributions
iding+0.040
inn+0.037
oving+0.035
 som+0.034
gh+0.034
Neg logit contributions
 sky-0.028
 pieces-0.025
 woman-0.025
 nowhere-0.025
 old-0.024
Token explore
Token ID7301
Feature activation+1.09e+00

Pos logit contributions
iding+0.133
gh+0.124
 som+0.123
oving+0.122
inn+0.119
Neg logit contributions
 sky-0.066
 nowhere-0.058
 woman-0.057
s-0.056
 pieces-0.053
Token!"
Token ID2474
Feature activation+2.02e+00

Pos logit contributions
 sky+0.020
 nowhere+0.020
 woman+0.018
 pieces+0.017
Someone+0.017
Neg logit contributions
iding-0.039
inn-0.035
 som-0.035
gh-0.035
oving-0.035
Token said
Token ID531
Feature activation-8.77e-01

Pos logit contributions
 sky+0.045
 nowhere+0.043
 woman+0.041
Someone+0.039
 pieces+0.038
Neg logit contributions
iding-0.063
 som-0.058
inn-0.057
gh-0.056
oving-0.056
Token Jake
Token ID14757
Feature activation-2.02e+00

Pos logit contributions
iding+0.024
 som+0.021
oving+0.021
heit+0.020
inn+0.020
Neg logit contributions
 nowhere-0.023
 sky-0.023
 woman-0.023
 pieces-0.021
s-0.021
Token's
Token ID338
Feature activation-4.51e-01

Pos logit contributions
iding+0.070
 som+0.068
heit+0.066
icious+0.065
inn+0.065
Neg logit contributions
 nowhere-0.033
 woman-0.033
 sky-0.033
s-0.032
 pieces-0.030
Token mom
Token ID1995
Feature activation+4.69e+00

Pos logit contributions
iding+0.019
inn+0.018
 som+0.018
oving+0.018
gh+0.017
Neg logit contributions
 sky-0.005
 woman-0.005
 nowhere-0.005
 pieces-0.004
Someone-0.004
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
 sky+0.086
 woman+0.085
 nowhere+0.084
s+0.078
keeper+0.076
Neg logit contributions
iding-0.161
 som-0.153
heit-0.149
inn-0.146
gh-0.145
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
iding+0.037
 som+0.034
inn+0.034
gh+0.033
oving+0.033
Neg logit contributions
 sky-0.018
 nowhere-0.017
 woman-0.016
Someone-0.015
 pieces-0.015
Token
Token ID198
Feature activation-3.99e-01

Pos logit contributions
iding+0.008
inn+0.007
gh+0.007
 som+0.007
oving+0.007
Neg logit contributions
 sky-0.003
 nowhere-0.003
 woman-0.003
Someone-0.003
 pieces-0.003
Token"
Token ID1
Feature activation+3.23e+00

Pos logit contributions
iding+0.011
 som+0.010
inn+0.010
gh+0.010
oving+0.010
Neg logit contributions
 sky-0.010
 nowhere-0.010
 woman-0.009
Someone-0.009
 pieces-0.009
TokenI
Token ID40
Feature activation-4.00e+00

Pos logit contributions
 sky+0.077
Someone+0.074
 woman+0.072
 nowhere+0.072
 pieces+0.064
Neg logit contributions
iding-0.100
 appetite-0.091
gh-0.089
 som-0.088
oving-0.087
Token outside
Token ID2354
Feature activation-5.86e-01

Pos logit contributions
iding+0.031
inn+0.028
 som+0.028
oving+0.027
heit+0.027
Neg logit contributions
 sky-0.013
 nowhere-0.012
 woman-0.011
 pieces-0.010
Someone-0.010
Token in
Token ID287
Feature activation-2.00e+00

Pos logit contributions
iding+0.020
 som+0.018
inn+0.018
gh+0.018
oving+0.018
Neg logit contributions
 sky-0.012
 nowhere-0.011
 woman-0.011
Someone-0.010
 pieces-0.010
Token the
Token ID262
Feature activation+2.51e+00

Pos logit contributions
iding+0.056
 som+0.054
 dive+0.052
inn+0.052
irl+0.051
Neg logit contributions
keeper-0.043
 sky-0.041
Someone-0.041
 woman-0.040
 nowhere-0.039
Token sun
Token ID4252
Feature activation-3.30e-01

Pos logit contributions
 nowhere+0.053
 sky+0.051
 woman+0.050
Someone+0.048
 pieces+0.046
Neg logit contributions
iding-0.079
 som-0.072
inn-0.071
gh-0.070
oving-0.068
Token and
Token ID290
Feature activation+2.66e+00

Pos logit contributions
iding+0.010
 som+0.009
inn+0.009
gh+0.009
oving+0.009
Neg logit contributions
 nowhere-0.008
 sky-0.007
 woman-0.007
Someone-0.007
 pieces-0.006
Token feel
Token ID1254
Feature activation+4.68e+00

Pos logit contributions
 sky+0.079
 nowhere+0.078
 woman+0.075
Someone+0.073
 pieces+0.072
Neg logit contributions
iding-0.062
 som-0.056
inn-0.053
gh-0.052
oving-0.051
Token the
Token ID262
Feature activation+2.48e+00

Pos logit contributions
 sky+0.096
 nowhere+0.096
 woman+0.089
Someone+0.088
 pieces+0.083
Neg logit contributions
iding-0.150
 som-0.142
inn-0.136
oving-0.132
gh-0.130
Token earth
Token ID4534
Feature activation+1.19e+00

Pos logit contributions
 nowhere+0.057
 sky+0.054
 woman+0.053
Someone+0.051
 pieces+0.049
Neg logit contributions
iding-0.074
 som-0.068
inn-0.065
gh-0.065
oving-0.063
Token under
Token ID739
Feature activation-2.19e+00

Pos logit contributions
 nowhere+0.028
 woman+0.027
 sky+0.027
Someone+0.026
 pieces+0.023
Neg logit contributions
iding-0.034
 som-0.031
gh-0.030
inn-0.029
oving-0.029
Token her
Token ID607
Feature activation+4.40e-02

Pos logit contributions
iding+0.065
 som+0.064
gh+0.061
inn+0.057
 appetite+0.057
Neg logit contributions
keeper-0.044
Someone-0.044
 nowhere-0.043
 woman-0.043
 sky-0.042
Token feet
Token ID3625
Feature activation+6.05e-01

Pos logit contributions
 nowhere+0.001
Someone+0.001
 sky+0.001
 woman+0.001
keeper+0.001
Neg logit contributions
iding-0.001
gh-0.001
 som-0.001
 appetite-0.001
 dive-0.001
Token looked
Token ID3114
Feature activation-1.24e+00

Pos logit contributions
 sky+0.023
 nowhere+0.021
 woman+0.021
 pieces+0.018
Someone+0.017
Neg logit contributions
iding-0.069
inn-0.063
 som-0.062
gh-0.062
oving-0.062
Token in
Token ID287
Feature activation-1.41e+00

Pos logit contributions
iding+0.043
gh+0.040
 som+0.039
oving+0.038
inn+0.038
Neg logit contributions
 sky-0.025
 nowhere-0.024
 woman-0.023
 old-0.021
s-0.021
Token the
Token ID262
Feature activation+2.75e+00

Pos logit contributions
iding+0.061
oving+0.058
gh+0.055
icious+0.053
inn+0.053
Neg logit contributions
 sky-0.023
 nowhere-0.022
 woman-0.019
 old-0.019
 pieces-0.019
Token mirror
Token ID10162
Feature activation-7.86e-01

Pos logit contributions
 sky+0.049
 nowhere+0.046
 woman+0.044
Someone+0.041
 pieces+0.039
Neg logit contributions
iding-0.101
 som-0.092
inn-0.091
gh-0.091
oving-0.090
Token and
Token ID290
Feature activation+2.41e+00

Pos logit contributions
iding+0.033
inn+0.031
 som+0.030
oving+0.030
heit+0.030
Neg logit contributions
 sky-0.011
 nowhere-0.009
 woman-0.009
 pieces-0.008
s-0.007
Token felt
Token ID2936
Feature activation+3.16e+00

Pos logit contributions
 sky+0.041
 nowhere+0.039
 woman+0.037
Someone+0.033
 pieces+0.032
Neg logit contributions
iding-0.092
inn-0.083
gh-0.083
 som-0.082
oving-0.082
Token so
Token ID523
Feature activation+1.87e+00

Pos logit contributions
 sky+0.057
 nowhere+0.054
 woman+0.051
Someone+0.047
 pieces+0.046
Neg logit contributions
iding-0.116
inn-0.105
 som-0.104
gh-0.103
oving-0.103
Token proud
Token ID6613
Feature activation+3.85e+00

Pos logit contributions
 sky+0.030
 old+0.027
 nowhere+0.025
 woman+0.024
 lost+0.024
Neg logit contributions
iding-0.073
inn-0.069
gh-0.065
 som-0.065
oving-0.064
Token.
Token ID13
Feature activation-4.86e-01

Pos logit contributions
 sky+0.050
 nowhere+0.043
 woman+0.040
 pieces+0.037
s+0.034
Neg logit contributions
iding-0.164
gh-0.152
heit-0.151
oving-0.151
 som-0.150
Token He
Token ID679
Feature activation-1.20e+00

Pos logit contributions
iding+0.015
gh+0.014
 som+0.013
oving+0.013
inn+0.013
Neg logit contributions
 sky-0.012
 nowhere-0.011
 woman-0.011
Someone-0.010
 pieces-0.010
Token had
Token ID550
Feature activation+1.69e+00

Pos logit contributions
iding+0.048
inn+0.042
gh+0.042
oving+0.042
 som+0.040
Neg logit contributions
 sky-0.020
 nowhere-0.019
 woman-0.019
Someone-0.016
 pieces-0.016
Token,
Token ID11
Feature activation-9.35e-01

Pos logit contributions
iding+0.217
oving+0.203
inn+0.200
icious+0.197
 appetite+0.195
Neg logit contributions
 sky-0.096
 nowhere-0.081
 pieces-0.074
 flowers-0.070
s-0.070
Token it
Token ID340
Feature activation+3.32e-01

Pos logit contributions
iding+0.033
 som+0.031
inn+0.030
gh+0.030
oving+0.030
Neg logit contributions
 sky-0.016
 nowhere-0.015
 woman-0.015
Someone-0.014
 pieces-0.013
Token seemed
Token ID3947
Feature activation+1.52e+00

Pos logit contributions
 sky+0.007
 nowhere+0.006
 woman+0.006
Someone+0.006
 pieces+0.006
Neg logit contributions
iding-0.011
 som-0.010
inn-0.010
gh-0.010
oving-0.010
Token to
Token ID284
Feature activation-1.42e+00

Pos logit contributions
 sky+0.022
 nowhere+0.020
 woman+0.018
Someone+0.016
 pieces+0.016
Neg logit contributions
iding-0.061
inn-0.056
 som-0.056
gh-0.056
oving-0.055
Token make
Token ID787
Feature activation+3.49e-01

Pos logit contributions
iding+0.049
oving+0.047
inn+0.046
heit+0.044
icious+0.044
Neg logit contributions
 sky-0.030
 old-0.027
 lost-0.026
 she-0.025
 a-0.024
Token people
Token ID661
Feature activation+4.70e+00

Pos logit contributions
 sky+0.006
 nowhere+0.005
 woman+0.005
 pieces+0.005
 old+0.004
Neg logit contributions
iding-0.014
inn-0.013
gh-0.012
oving-0.012
 som-0.012
Token smile
Token ID8212
Feature activation+2.53e+00

Pos logit contributions
 sky+0.126
 nowhere+0.122
 woman+0.117
Someone+0.113
 pieces+0.110
Neg logit contributions
iding-0.128
 som-0.114
inn-0.110
gh-0.109
oving-0.109
Token.
Token ID13
Feature activation-4.77e-01

Pos logit contributions
 sky+0.042
 woman+0.036
 nowhere+0.036
s+0.034
 pieces+0.032
Neg logit contributions
iding-0.097
inn-0.093
oving-0.090
gh-0.089
 som-0.089
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
iding+0.018
 som+0.017
gh+0.017
oving+0.016
inn+0.016
Neg logit contributions
 sky-0.008
 nowhere-0.007
 woman-0.007
Someone-0.006
 pieces-0.006
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
 sky+0.001
 nowhere+0.001
 woman+0.001
Someone+0.001
 pieces+0.001
Neg logit contributions
iding-0.005
inn-0.004
 som-0.004
gh-0.004
oving-0.004
TokenOne
Token ID3198
Feature activation-3.61e+00

Pos logit contributions
iding+0.004
 som+0.004
gh+0.003
inn+0.003
 appetite+0.003
Neg logit contributions
 sky-0.003
 nowhere-0.002
 woman-0.002
Someone-0.002
 pieces-0.002
Token the
Token ID262
Feature activation+2.73e+00

Pos logit contributions
iding+0.058
oving+0.052
gh+0.052
inn+0.052
 som+0.052
Neg logit contributions
 sky-0.021
 nowhere-0.020
 woman-0.018
 pieces-0.016
Someone-0.015
Token direction
Token ID4571
Feature activation+2.86e+00

Pos logit contributions
 nowhere+0.047
Someone+0.042
 pieces+0.038
 Hood+0.037
s+0.037
Neg logit contributions
 som-0.085
iding-0.084
inn-0.084
 appetite-0.078
cluded-0.077
Token and
Token ID290
Feature activation+2.27e+00

Pos logit contributions
 sky+0.049
 nowhere+0.045
 woman+0.042
 pieces+0.038
Someone+0.038
Neg logit contributions
iding-0.108
 som-0.099
inn-0.099
gh-0.098
oving-0.098
Token saw
Token ID2497
Feature activation+3.73e+00

Pos logit contributions
 sky+0.036
 nowhere+0.032
 woman+0.031
 pieces+0.030
Someone+0.029
Neg logit contributions
iding-0.082
 som-0.078
inn-0.075
gh-0.074
oving-0.073
Token a
Token ID257
Feature activation+1.19e+00

Pos logit contributions
 sky+0.058
 nowhere+0.055
 woman+0.051
Someone+0.050
s+0.045
Neg logit contributions
iding-0.131
 som-0.130
gh-0.123
oving-0.121
inn-0.120
Token little
Token ID1310
Feature activation+3.11e+00

Pos logit contributions
 sky+0.018
 nowhere+0.017
 woman+0.016
Someone+0.014
 pieces+0.014
Neg logit contributions
iding-0.047
inn-0.043
 som-0.043
gh-0.042
oving-0.042
Token girl
Token ID2576
Feature activation+4.22e+00

Pos logit contributions
 sky+0.036
 nowhere+0.032
 woman+0.030
Someone+0.026
 pieces+0.025
Neg logit contributions
iding-0.133
 som-0.123
inn-0.123
gh-0.122
oving-0.121
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
 sky+0.076
 nowhere+0.074
 woman+0.072
Someone+0.062
s+0.061
Neg logit contributions
iding-0.154
inn-0.143
 som-0.140
oving-0.138
gh-0.138
Token She
Token ID1375
Feature activation-1.06e+00

Pos logit contributions
iding+0.010
 som+0.009
inn+0.009
gh+0.009
oving+0.009
Neg logit contributions
 sky-0.005
 nowhere-0.005
 woman-0.004
Someone-0.004
 pieces-0.004
Token was
Token ID373
Feature activation+1.18e+00

Pos logit contributions
iding+0.041
 som+0.038
inn+0.038
gh+0.037
oving+0.037
Neg logit contributions
 sky-0.016
 nowhere-0.015
 woman-0.014
Someone-0.013
 pieces-0.012
Token looking
Token ID2045
Feature activation-1.04e+00

Pos logit contributions
 sky+0.021
 nowhere+0.020
 woman+0.019
Someone+0.018
 pieces+0.017
Neg logit contributions
iding-0.042
 som-0.039
inn-0.038
gh-0.038
oving-0.038
Token doll
Token ID3654
Feature activation+2.71e+00

Pos logit contributions
iding+0.054
inn+0.049
oving+0.049
 som+0.049
gh+0.048
Neg logit contributions
 sky-0.025
 nowhere-0.023
 woman-0.023
 pieces-0.020
Someone-0.020
Token inside
Token ID2641
Feature activation+2.36e-01

Pos logit contributions
 sky+0.055
 nowhere+0.052
 woman+0.050
 pieces+0.046
Someone+0.046
Neg logit contributions
iding-0.093
inn-0.084
 som-0.084
gh-0.082
oving-0.082
Token.
Token ID13
Feature activation-7.52e-01

Pos logit contributions
 sky+0.005
 nowhere+0.005
 woman+0.005
 pieces+0.004
Someone+0.004
Neg logit contributions
iding-0.008
 som-0.007
inn-0.007
oving-0.007
gh-0.007
Token She
Token ID1375
Feature activation-1.52e+00

Pos logit contributions
iding+0.028
gh+0.026
 som+0.025
oving+0.025
inn+0.025
Neg logit contributions
 sky-0.014
 nowhere-0.012
 woman-0.012
Someone-0.011
s-0.010
Token was
Token ID373
Feature activation+1.18e+00

Pos logit contributions
 som+0.045
iding+0.045
oving+0.041
inn+0.041
gh+0.040
Neg logit contributions
 sky-0.034
 nowhere-0.031
Someone-0.030
 woman-0.030
 pieces-0.027
Token so
Token ID523
Feature activation+1.88e+00

Pos logit contributions
 sky+0.022
 nowhere+0.020
 woman+0.020
Someone+0.019
 pieces+0.018
Neg logit contributions
iding-0.041
 som-0.038
inn-0.037
gh-0.037
oving-0.037
Token happy
Token ID3772
Feature activation+4.08e+00

Pos logit contributions
 sky+0.043
 nowhere+0.041
 woman+0.039
Someone+0.037
 pieces+0.037
Neg logit contributions
iding-0.060
 som-0.053
inn-0.053
gh-0.052
oving-0.052
Token and
Token ID290
Feature activation+2.32e+00

Pos logit contributions
 sky+0.059
 nowhere+0.054
 woman+0.051
Someone+0.050
 pieces+0.045
Neg logit contributions
iding-0.160
 som-0.149
inn-0.145
gh-0.144
oving-0.143
Token hugged
Token ID41130
Feature activation+1.06e+00

Pos logit contributions
 sky+0.049
 nowhere+0.047
 woman+0.044
Someone+0.042
 pieces+0.041
Neg logit contributions
iding-0.076
 som-0.070
inn-0.068
gh-0.068
oving-0.068
Token her
Token ID607
Feature activation+2.02e+00

Pos logit contributions
 sky+0.017
 nowhere+0.016
 woman+0.015
 pieces+0.013
Someone+0.013
Neg logit contributions
iding-0.042
oving-0.038
gh-0.038
 som-0.038
inn-0.038
Token grandma
Token ID49890
Feature activation+6.16e+00

Pos logit contributions
 sky+0.035
 nowhere+0.033
Someone+0.033
 woman+0.030
s+0.026
Neg logit contributions
iding-0.071
 som-0.065
inn-0.064
 appetite-0.062
gh-0.062
Token not
Token ID407
Feature activation+3.18e-01

Pos logit contributions
iding+0.051
inn+0.048
oving+0.046
 appetite+0.046
oy+0.046
Neg logit contributions
 nowhere-0.018
 sky-0.018
 pieces-0.017
 old-0.016
 blood-0.015
Token dry
Token ID5894
Feature activation-5.40e+00

Pos logit contributions
 pieces+0.006
 sky+0.006
 old+0.006
 lost+0.006
 nowhere+0.005
Neg logit contributions
iding-0.011
heit-0.010
 accompl-0.010
inn-0.010
oving-0.010
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
iding+0.210
heit+0.192
 som+0.190
oving+0.189
icious+0.188
Neg logit contributions
 sky-0.095
 pieces-0.089
 nowhere-0.086
 old-0.081
 flowers-0.076
Token The
Token ID383
Feature activation+1.73e-01

Pos logit contributions
iding+0.051
inn+0.048
 som+0.047
gh+0.045
oving+0.044
Neg logit contributions
 sky-0.031
 nowhere-0.031
 woman-0.030
 pieces-0.027
Someone-0.027
Token ball
Token ID2613
Feature activation-6.88e-01

Pos logit contributions
 sky+0.004
 nowhere+0.003
 woman+0.003
Someone+0.003
 pieces+0.003
Neg logit contributions
iding-0.006
 som-0.005
inn-0.005
gh-0.005
oving-0.005
Token was
Token ID373
Feature activation+6.14e-01

Pos logit contributions
iding+0.023
 som+0.022
gh+0.021
inn+0.021
oving+0.020
Neg logit contributions
 sky-0.013
 nowhere-0.013
 woman-0.012
Someone-0.012
 pieces-0.011
Token still
Token ID991
Feature activation+1.47e-01

Pos logit contributions
 nowhere+0.011
 sky+0.010
 old+0.009
 pieces+0.009
 woman+0.009
Neg logit contributions
iding-0.023
oving-0.021
 som-0.021
gh-0.021
heit-0.021
Token flat
Token ID6228
Feature activation-5.05e+00

Pos logit contributions
 nowhere+0.002
 sky+0.002
 pieces+0.002
 old+0.002
 lost+0.002
Neg logit contributions
iding-0.006
heit-0.006
 som-0.006
oving-0.006
inn-0.006
Token and
Token ID290
Feature activation+1.95e+00

Pos logit contributions
iding+0.209
 som+0.193
inn+0.190
gh+0.189
oving+0.189
Neg logit contributions
 sky-0.068
 nowhere-0.062
 woman-0.055
 pieces-0.054
Someone-0.048
Token useless
Token ID13894
Feature activation-8.79e-01

Pos logit contributions
 nowhere+0.038
 sky+0.037
 pieces+0.033
 woman+0.032
 old+0.032
Neg logit contributions
iding-0.072
oving-0.063
inn-0.063
gh-0.062
 som-0.061
Token.
Token ID13
Feature activation-1.47e+00

Pos logit contributions
iding+0.035
heit+0.032
oving+0.032
inn+0.032
icious+0.031
Neg logit contributions
 sky-0.014
 pieces-0.013
 nowhere-0.013
s-0.012
 woman-0.011
Token urge
Token ID14960
Feature activation+1.11e+00

Pos logit contributions
iding+0.038
inn+0.035
oving+0.033
 som+0.033
gh+0.032
Neg logit contributions
 sky-0.049
 nowhere-0.047
 woman-0.045
Someone-0.044
s-0.043
Token to
Token ID284
Feature activation-7.62e-02

Pos logit contributions
 sky+0.014
 nowhere+0.013
 woman+0.012
Someone+0.011
 pieces+0.010
Neg logit contributions
iding-0.046
 som-0.043
inn-0.042
gh-0.042
oving-0.041
Token touch
Token ID3638
Feature activation+6.45e-02

Pos logit contributions
iding+0.002
inn+0.002
 som+0.002
gh+0.002
oving+0.002
Neg logit contributions
 sky-0.002
 nowhere-0.002
 woman-0.002
 pieces-0.002
 old-0.002
Token the
Token ID262
Feature activation+2.64e+00

Pos logit contributions
 sky+0.001
 nowhere+0.001
 woman+0.001
Someone+0.001
 pieces+0.001
Neg logit contributions
iding-0.002
 som-0.002
inn-0.002
gh-0.002
oving-0.002
Token knife
Token ID9845
Feature activation+5.05e-01

Pos logit contributions
 nowhere+0.060
Someone+0.056
 sky+0.054
 woman+0.054
armac+0.051
Neg logit contributions
iding-0.071
 som-0.070
 appetite-0.070
gh-0.069
inn-0.064
Token and
Token ID290
Feature activation+2.53e+00

Pos logit contributions
 sky+0.008
 nowhere+0.007
 pieces+0.007
s+0.007
 woman+0.007
Neg logit contributions
iding-0.019
heit-0.018
 som-0.018
inn-0.018
oving-0.018
Token play
Token ID711
Feature activation-1.52e+00

Pos logit contributions
 sky+0.061
 nowhere+0.059
 woman+0.056
Someone+0.054
 pieces+0.052
Neg logit contributions
iding-0.074
 som-0.068
inn-0.066
gh-0.066
oving-0.065
Token with
Token ID351
Feature activation+5.69e-01

Pos logit contributions
iding+0.061
heit+0.057
oving+0.054
inn+0.054
 AW+0.054
Neg logit contributions
 nowhere-0.023
 sky-0.022
 pieces-0.021
 woman-0.019
 bird-0.018
Token it
Token ID340
Feature activation+2.16e+00

Pos logit contributions
 sky+0.012
Someone+0.012
 woman+0.011
 nowhere+0.011
actus+0.010
Neg logit contributions
iding-0.016
 som-0.016
inn-0.016
gh-0.016
oving-0.015
Token.
Token ID13
Feature activation+4.22e-02

Pos logit contributions
 sky+0.038
 nowhere+0.038
 pieces+0.034
s+0.032
 she+0.031
Neg logit contributions
iding-0.080
heit-0.074
inn-0.072
oving-0.072
 som-0.072
Token She
Token ID1375
Feature activation-8.90e-01

Pos logit contributions
 nowhere+0.001
 pieces+0.001
 woman+0.001
 sky+0.001
Someone+0.001
Neg logit contributions
iding-0.001
inn-0.001
 som-0.001
gh-0.001
oving-0.001
Token dad
Token ID9955
Feature activation+4.78e+00

Pos logit contributions
 sky+0.027
 nowhere+0.025
 woman+0.023
Someone+0.023
 pieces+0.022
Neg logit contributions
iding-0.054
 som-0.051
gh-0.049
inn-0.049
oving-0.048
Token,
Token ID11
Feature activation-6.61e-01

Pos logit contributions
 sky+0.080
 woman+0.076
 nowhere+0.074
s+0.070
 pieces+0.066
Neg logit contributions
iding-0.178
inn-0.171
 som-0.161
oving-0.160
gh-0.160
Token because
Token ID780
Feature activation+1.41e+00

Pos logit contributions
iding+0.025
inn+0.024
gh+0.024
oving+0.023
 som+0.023
Neg logit contributions
 sky-0.011
 woman-0.011
 nowhere-0.011
 pieces-0.009
Someone-0.009
Token they
Token ID484
Feature activation-2.66e+00

Pos logit contributions
 sky+0.024
 nowhere+0.023
 woman+0.022
Someone+0.019
 pieces+0.019
Neg logit contributions
iding-0.053
inn-0.048
 som-0.048
gh-0.047
oving-0.047
Token knew
Token ID2993
Feature activation+3.29e+00

Pos logit contributions
iding+0.096
 som+0.087
inn+0.087
gh+0.086
oving+0.085
Neg logit contributions
 sky-0.048
 nowhere-0.046
 woman-0.044
Someone-0.040
 pieces-0.039
Token they
Token ID484
Feature activation-1.81e+00

Pos logit contributions
 sky+0.050
 nowhere+0.049
 woman+0.047
 pieces+0.040
 old+0.040
Neg logit contributions
iding-0.131
inn-0.121
oving-0.117
 som-0.116
gh-0.115
Token would
Token ID561
Feature activation-8.56e-01

Pos logit contributions
iding+0.069
 som+0.063
inn+0.062
gh+0.061
oving+0.061
Neg logit contributions
 sky-0.030
 nowhere-0.028
 woman-0.027
Someone-0.024
 pieces-0.024
Token say
Token ID910
Feature activation-1.10e-01

Pos logit contributions
iding+0.031
inn+0.030
heit+0.028
oving+0.028
 AW+0.027
Neg logit contributions
 sky-0.017
 lost-0.016
 woman-0.015
 that-0.015
 nowhere-0.014
Token no
Token ID645
Feature activation+4.10e-02

Pos logit contributions
inn+0.004
iding+0.004
oving+0.004
rated+0.003
heit+0.003
Neg logit contributions
 sky-0.002
 woman-0.002
 that-0.002
 she-0.002
 old-0.002
Token.
Token ID13
Feature activation-1.19e+00

Pos logit contributions
 sky+0.001
 woman+0.001
 old+0.001
 flowers+0.001
 pieces+0.001
Neg logit contributions
iding-0.002
inn-0.002
heit-0.001
 AW-0.001
oving-0.001
Token
Token ID198
Feature activation-3.28e-01

Pos logit contributions
iding+0.042
 som+0.038
gh+0.038
inn+0.037
oving+0.037
Neg logit contributions
 sky-0.025
 nowhere-0.023
 woman-0.022
Someone-0.021
s-0.019
Token perfect
Token ID2818
Feature activation-2.97e+00

Pos logit contributions
 sky+0.025
 nowhere+0.022
 woman+0.022
 pieces+0.021
 old+0.020
Neg logit contributions
iding-0.039
oving-0.035
inn-0.035
 som-0.034
heit-0.033
Token hidden
Token ID7104
Feature activation-4.61e+00

Pos logit contributions
iding+0.121
oving+0.117
omp+0.116
icious+0.115
inn+0.113
Neg logit contributions
 sky-0.050
 woman-0.047
 pieces-0.044
 old-0.043
 door-0.042
Token place
Token ID1295
Feature activation+1.13e+00

Pos logit contributions
iding+0.175
oving+0.163
inn+0.160
icious+0.158
 som+0.156
Neg logit contributions
 sky-0.085
 woman-0.080
 old-0.078
 pieces-0.076
 nowhere-0.073
Token for
Token ID329
Feature activation+4.84e-01

Pos logit contributions
 sky+0.018
 nowhere+0.017
 woman+0.015
 pieces+0.014
s+0.014
Neg logit contributions
iding-0.044
 som-0.041
inn-0.040
oving-0.040
gh-0.040
Token my
Token ID616
Feature activation-1.62e+00

Pos logit contributions
 nowhere+0.009
 sky+0.009
 pieces+0.008
 woman+0.007
Someone+0.007
Neg logit contributions
iding-0.018
inn-0.016
 som-0.016
oving-0.016
gh-0.016
Token surprise
Token ID5975
Feature activation-1.38e+00

Pos logit contributions
iding+0.064
inn+0.060
 som+0.058
oving+0.058
gh+0.056
Neg logit contributions
 sky-0.026
 woman-0.024
 nowhere-0.024
 pieces-0.020
 old-0.020
Token!"
Token ID2474
Feature activation+1.95e+00

Pos logit contributions
iding+0.044
 som+0.041
inn+0.041
oving+0.040
 accompl+0.040
Neg logit contributions
 sky-0.032
 pieces-0.029
 woman-0.029
 nowhere-0.029
s-0.027
Token Tim
Token ID5045
Feature activation-1.07e+00

Pos logit contributions
 sky+0.056
 nowhere+0.053
 woman+0.052
Someone+0.050
 pieces+0.049
Neg logit contributions
iding-0.052
 som-0.045
inn-0.044
gh-0.044
oving-0.043
Token put
Token ID1234
Feature activation-8.14e-01

Pos logit contributions
iding+0.039
 som+0.035
inn+0.035
gh+0.035
oving+0.035
Neg logit contributions
 sky-0.019
 nowhere-0.018
 woman-0.017
Someone-0.016
 pieces-0.015
Token his
Token ID465
Feature activation-2.01e-01

Pos logit contributions
iding+0.028
inn+0.025
 som+0.025
gh+0.025
oving+0.024
Neg logit contributions
 sky-0.016
 nowhere-0.015
 woman-0.015
Someone-0.014
 pieces-0.013
Token uniform
Token ID8187
Feature activation+1.37e+00

Pos logit contributions
iding+0.005
gh+0.005
 som+0.004
inn+0.004
 appetite+0.004
Neg logit contributions
 sky-0.005
 nowhere-0.005
Someone-0.005
 woman-0.005
keeper-0.005
Token climbed
Token ID19952
Feature activation-2.84e+00

Pos logit contributions
iding+0.060
gh+0.056
oving+0.054
icious+0.053
 som+0.052
Neg logit contributions
 sky-0.031
 woman-0.028
 nowhere-0.028
s-0.024
 pieces-0.024
Token into
Token ID656
Feature activation-2.75e+00

Pos logit contributions
iding+0.098
 som+0.089
inn+0.088
gh+0.087
oving+0.086
Neg logit contributions
 sky-0.056
 nowhere-0.053
 woman-0.051
Someone-0.048
 pieces-0.046
Token the
Token ID262
Feature activation+1.63e+00

Pos logit contributions
iding+0.102
 som+0.096
inn+0.093
gh+0.092
oving+0.091
Neg logit contributions
 sky-0.043
 nowhere-0.040
 woman-0.039
Someone-0.037
s-0.033
Token car
Token ID1097
Feature activation+2.38e-01

Pos logit contributions
 sky+0.026
 nowhere+0.026
 woman+0.024
Someone+0.023
 pieces+0.021
Neg logit contributions
iding-0.060
 som-0.056
inn-0.055
gh-0.054
oving-0.053
Token and
Token ID290
Feature activation+1.56e+00

Pos logit contributions
 sky+0.004
 nowhere+0.004
 woman+0.004
 pieces+0.003
s+0.003
Neg logit contributions
iding-0.009
inn-0.008
gh-0.008
 som-0.008
oving-0.008
Token drove
Token ID10357
Feature activation-3.08e+00

Pos logit contributions
 sky+0.035
 woman+0.032
 nowhere+0.032
 pieces+0.029
Someone+0.028
Neg logit contributions
iding-0.053
inn-0.047
gh-0.047
oving-0.047
 appetite-0.045
Token back
Token ID736
Feature activation+6.08e-01

Pos logit contributions
iding+0.123
 appetite+0.121
icious+0.121
oving+0.118
inn+0.115
Neg logit contributions
 sky-0.048
 woman-0.043
 pieces-0.040
s-0.040
 nowhere-0.039
Token home
Token ID1363
Feature activation+2.82e+00

Pos logit contributions
 sky+0.010
 nowhere+0.009
 woman+0.009
 pieces+0.008
s+0.008
Neg logit contributions
iding-0.023
 som-0.021
gh-0.021
inn-0.021
oving-0.021
Token.
Token ID13
Feature activation-7.67e-01

Pos logit contributions
 sky+0.052
 nowhere+0.048
 woman+0.048
 pieces+0.045
s+0.045
Neg logit contributions
iding-0.099
inn-0.095
heit-0.092
 som-0.091
gh-0.090
Token
Token ID198
Feature activation-3.87e-02

Pos logit contributions
iding+0.030
inn+0.027
 som+0.027
gh+0.027
oving+0.027
Neg logit contributions
 sky-0.012
 nowhere-0.011
 woman-0.010
Someone-0.009
 pieces-0.009
Token
Token ID198
Feature activation-3.30e-01

Pos logit contributions
iding+0.001
inn+0.001
 som+0.001
gh+0.001
oving+0.001
Neg logit contributions
 sky-0.001
 woman-0.001
 nowhere-0.001
 pieces-0.001
Someone-0.001
Token her
Token ID607
Feature activation+1.13e+00

Pos logit contributions
 sky+0.010
 nowhere+0.010
Someone+0.009
 woman+0.009
actus+0.008
Neg logit contributions
iding-0.019
 som-0.018
inn-0.017
gh-0.017
oving-0.017
Token toys
Token ID14958
Feature activation+3.58e+00

Pos logit contributions
 nowhere+0.026
Someone+0.024
 sky+0.024
 woman+0.024
actus+0.023
Neg logit contributions
iding-0.032
 som-0.029
 appetite-0.029
oving-0.028
gh-0.028
Token sort
Token ID3297
Feature activation-1.30e+00

Pos logit contributions
 sky+0.077
 nowhere+0.071
 woman+0.067
 pieces+0.067
s+0.062
Neg logit contributions
iding-0.118
inn-0.111
oving-0.107
gh-0.105
heit-0.105
Token just
Token ID655
Feature activation-1.32e+00

Pos logit contributions
iding+0.045
 som+0.041
inn+0.040
gh+0.040
oving+0.040
Neg logit contributions
 sky-0.026
 nowhere-0.025
 woman-0.023
 pieces-0.022
Someone-0.022
Token as
Token ID355
Feature activation+2.21e+00

Pos logit contributions
iding+0.047
inn+0.045
oving+0.043
gh+0.043
 som+0.042
Neg logit contributions
 sky-0.026
 nowhere-0.023
 old-0.022
 pieces-0.022
 woman-0.021
Token she
Token ID673
Feature activation-3.28e+00

Pos logit contributions
 sky+0.041
 nowhere+0.039
 woman+0.037
Someone+0.035
 pieces+0.034
Neg logit contributions
iding-0.078
 som-0.071
inn-0.071
gh-0.070
oving-0.069
Token wants
Token ID3382
Feature activation+2.06e+00

Pos logit contributions
iding+0.123
inn+0.111
oving+0.109
 som+0.109
gh+0.109
Neg logit contributions
 sky-0.061
 nowhere-0.054
 woman-0.051
 pieces-0.051
s-0.048
Token.
Token ID13
Feature activation-3.71e-01

Pos logit contributions
 sky+0.036
 nowhere+0.033
 woman+0.031
 pieces+0.030
 old+0.027
Neg logit contributions
iding-0.079
inn-0.072
oving-0.071
 som-0.070
heit-0.069
Token It
Token ID632
Feature activation+1.54e+00

Pos logit contributions
iding+0.014
 som+0.013
inn+0.013
gh+0.013
oving+0.012
Neg logit contributions
 sky-0.006
 nowhere-0.006
 woman-0.005
Someone-0.005
 pieces-0.005
Token's
Token ID338
Feature activation-2.86e-01

Pos logit contributions
 sky+0.028
 nowhere+0.027
 woman+0.026
Someone+0.024
 pieces+0.022
Neg logit contributions
iding-0.054
 som-0.051
inn-0.049
gh-0.049
oving-0.048
Token her
Token ID607
Feature activation-1.26e+00

Pos logit contributions
iding+0.009
inn+0.008
 som+0.008
gh+0.008
oving+0.008
Neg logit contributions
 sky-0.006
 nowhere-0.006
 woman-0.006
 pieces-0.005
 old-0.005
Token sun
Token ID4252
Feature activation-2.31e+00

Pos logit contributions
 nowhere+0.011
 sky+0.010
 woman+0.010
Someone+0.010
s+0.009
Neg logit contributions
iding-0.016
 som-0.015
gh-0.014
inn-0.014
oving-0.014
Token was
Token ID373
Feature activation+7.43e-01

Pos logit contributions
iding+0.083
inn+0.075
 som+0.074
oving+0.074
gh+0.074
Neg logit contributions
 sky-0.048
 woman-0.042
 nowhere-0.041
 pieces-0.038
s-0.038
Token setting
Token ID4634
Feature activation-2.99e+00

Pos logit contributions
 sky+0.016
 nowhere+0.015
 old+0.012
 window+0.012
 lost+0.011
Neg logit contributions
iding-0.027
 som-0.026
lex-0.025
heit-0.025
 AW-0.025
Token and
Token ID290
Feature activation+3.23e+00

Pos logit contributions
iding+0.134
inn+0.127
 som+0.125
oving+0.125
heit+0.124
Neg logit contributions
 sky-0.039
s-0.028
 nowhere-0.027
 woman-0.026
 old-0.025
Token the
Token ID262
Feature activation+2.05e+00

Pos logit contributions
 sky+0.056
 nowhere+0.053
 woman+0.048
 pieces+0.042
Someone+0.042
Neg logit contributions
iding-0.128
inn-0.117
gh-0.116
oving-0.114
 som-0.111
Token adventurous
Token ID39770
Feature activation-2.94e+00

Pos logit contributions
 nowhere+0.045
Someone+0.042
 sky+0.042
 woman+0.042
rings+0.041
Neg logit contributions
iding-0.057
 som-0.054
gh-0.052
 dive-0.050
inn-0.050
Token whale
Token ID22206
Feature activation+1.98e+00

Pos logit contributions
iding+0.102
 som+0.092
inn+0.091
gh+0.091
oving+0.090
Neg logit contributions
 sky-0.060
 nowhere-0.056
 woman-0.054
Someone-0.049
 pieces-0.049
Token went
Token ID1816
Feature activation-2.10e+00

Pos logit contributions
 sky+0.034
 nowhere+0.030
 woman+0.029
s+0.026
 pieces+0.026
Neg logit contributions
iding-0.078
inn-0.072
gh-0.070
 som-0.069
oving-0.069
Token home
Token ID1363
Feature activation+3.91e+00

Pos logit contributions
iding+0.095
heit+0.093
icious+0.093
oving+0.092
rated+0.091
Neg logit contributions
 sky-0.031
 to-0.021
 trees-0.020
 flowers-0.020
s-0.020
Token.
Token ID13
Feature activation-4.72e-01

Pos logit contributions
 sky+0.070
 nowhere+0.066
 woman+0.064
 pieces+0.060
s+0.059
Neg logit contributions
iding-0.141
inn-0.134
heit-0.132
 som-0.128
gh-0.128
Token He
Token ID679
Feature activation-1.06e+00

Pos logit contributions
iding+0.019
inn+0.017
 som+0.017
gh+0.017
oving+0.017
Neg logit contributions
 sky-0.007
 nowhere-0.006
 woman-0.006
Someone-0.005
 pieces-0.005
Token had
Token ID550
Feature activation+1.03e+00

Pos logit contributions
iding+0.093
 som+0.087
gh+0.087
oving+0.085
inn+0.085
Neg logit contributions
 sky-0.051
 woman-0.046
 nowhere-0.045
Someone-0.043
 pieces-0.041
Token been
Token ID587
Feature activation-1.35e+00

Pos logit contributions
 sky+0.018
 nowhere+0.017
 woman+0.016
Someone+0.015
 pieces+0.014
Neg logit contributions
iding-0.038
 som-0.035
inn-0.034
gh-0.034
oving-0.034
Token so
Token ID523
Feature activation+1.00e+00

Pos logit contributions
iding+0.050
inn+0.046
 som+0.044
heit+0.044
 appetite+0.043
Neg logit contributions
 nowhere-0.026
 sky-0.023
 woman-0.021
 lost-0.021
 old-0.020
Token ignorant
Token ID20109
Feature activation+1.74e+00

Pos logit contributions
 sky+0.021
 nowhere+0.020
 woman+0.019
Someone+0.018
 pieces+0.017
Neg logit contributions
iding-0.034
 som-0.030
inn-0.030
gh-0.030
oving-0.030
Token that
Token ID326
Feature activation+1.62e+00

Pos logit contributions
 sky+0.028
 nowhere+0.026
 woman+0.024
 pieces+0.023
 old+0.021
Neg logit contributions
iding-0.067
inn-0.062
 som-0.062
oving-0.061
gh-0.061
Token he
Token ID339
Feature activation-3.04e+00

Pos logit contributions
 sky+0.028
 nowhere+0.026
 woman+0.024
 pieces+0.022
 old+0.021
Neg logit contributions
iding-0.065
inn-0.060
oving-0.058
heit-0.056
gh-0.056
Token had
Token ID550
Feature activation+7.85e-01

Pos logit contributions
iding+0.114
 som+0.103
inn+0.103
gh+0.102
oving+0.101
Neg logit contributions
 sky-0.052
 nowhere-0.050
 woman-0.047
Someone-0.043
 pieces-0.042
Token not
Token ID407
Feature activation+5.71e-02

Pos logit contributions
 sky+0.014
 nowhere+0.013
 woman+0.012
 pieces+0.011
Someone+0.011
Neg logit contributions
iding-0.029
inn-0.027
 som-0.026
oving-0.026
gh-0.026
Token noticed
Token ID6810
Feature activation+2.83e+00

Pos logit contributions
 sky+0.001
 nowhere+0.001
 woman+0.001
 pieces+0.001
Someone+0.001
Neg logit contributions
iding-0.002
inn-0.002
 som-0.002
gh-0.002
oving-0.002
Token his
Token ID465
Feature activation-1.52e+00

Pos logit contributions
 sky+0.053
 nowhere+0.051
 woman+0.047
 pieces+0.044
Someone+0.043
Neg logit contributions
iding-0.101
inn-0.092
 som-0.091
oving-0.090
gh-0.090
Token own
Token ID898
Feature activation-2.26e-01

Pos logit contributions
iding+0.051
inn+0.047
 som+0.045
oving+0.045
gh+0.045
Neg logit contributions
 sky-0.033
 nowhere-0.031
 woman-0.030
 pieces-0.027
Someone-0.027
Token look
Token ID804
Feature activation-2.85e-02

Pos logit contributions
iding+0.009
inn+0.009
ross+0.008
oving+0.008
gh+0.008
Neg logit contributions
 sky-0.005
 pieces-0.005
 lost-0.005
 bird-0.005
 woman-0.005
Token for
Token ID329
Feature activation+3.37e+00

Pos logit contributions
iding+0.001
gh+0.001
 som+0.001
oving+0.001
inn+0.001
Neg logit contributions
 sky-0.001
 nowhere-0.001
 woman-0.001
 pieces-0.001
 old-0.001
Token something
Token ID1223
Feature activation+3.67e+00

Pos logit contributions
 sky+0.056
 nowhere+0.050
 woman+0.049
Someone+0.047
s+0.042
Neg logit contributions
iding-0.122
 som-0.117
inn-0.113
gh-0.113
oving-0.109
Token sweet
Token ID6029
Feature activation-4.49e-01

Pos logit contributions
 nowhere+0.040
 sky+0.040
 woman+0.034
 pieces+0.033
 old+0.032
Neg logit contributions
iding-0.159
oving-0.146
inn-0.145
heit-0.145
 som-0.143
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
iding+0.017
oving+0.015
inn+0.015
 som+0.015
gh+0.014
Neg logit contributions
 sky-0.009
 nowhere-0.008
 woman-0.007
 pieces-0.007
s-0.007
Token y
Token ID331
Feature activation-6.77e+00

Pos logit contributions
 sky+0.026
 nowhere+0.026
 woman+0.024
 pieces+0.023
 old+0.023
Neg logit contributions
iding-0.048
inn-0.042
oving-0.042
gh-0.042
 som-0.041
Tokenummy
Token ID13513
Feature activation+1.87e+00

Pos logit contributions
iding+0.241
 som+0.225
oving+0.216
 accompl+0.214
gh+0.211
Neg logit contributions
 sky-0.123
 nowhere-0.109
 pieces-0.104
s-0.104
Someone-0.095
Token.
Token ID13
Feature activation-3.73e-01

Pos logit contributions
 sky+0.032
 nowhere+0.029
 pieces+0.029
 woman+0.027
 flowers+0.026
Neg logit contributions
iding-0.073
oving-0.067
inn-0.065
heit-0.064
 som-0.064
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
iding+0.011
inn+0.010
 som+0.010
oving+0.009
gh+0.009
Neg logit contributions
 sky-0.009
 nowhere-0.009
 woman-0.008
 pieces-0.008
Someone-0.008
Token
Token ID220
Feature activation-5.97e-01

Pos logit contributions
 sky+0.006
 nowhere+0.005
 woman+0.005
 pieces+0.005
Someone+0.004
Neg logit contributions
iding-0.013
inn-0.012
 som-0.011
gh-0.011
oving-0.011
Token
Token ID198
Feature activation+1.15e-01

Pos logit contributions
iding+0.024
inn+0.022
 som+0.022
oving+0.022
gh+0.022
Neg logit contributions
 sky-0.008
 nowhere-0.008
 woman-0.007
Someone-0.006
 pieces-0.006
Token!
Token ID0
Feature activation-9.00e-01

Pos logit contributions
iding+0.030
inn+0.027
oving+0.026
 accompl+0.026
 som+0.025
Neg logit contributions
 sky-0.028
s-0.026
 pieces-0.026
 nowhere-0.025
 woman-0.024
Token It
Token ID632
Feature activation+1.51e+00

Pos logit contributions
iding+0.032
 som+0.029
gh+0.028
oving+0.028
inn+0.027
Neg logit contributions
 sky-0.018
Someone-0.017
 nowhere-0.016
 woman-0.016
 pieces-0.014
Token is
Token ID318
Feature activation+1.55e+00

Pos logit contributions
 sky+0.020
 nowhere+0.019
 woman+0.018
Someone+0.016
 pieces+0.015
Neg logit contributions
iding-0.060
 som-0.056
inn-0.055
gh-0.055
oving-0.055
Token dirty
Token ID11841
Feature activation-1.45e+00

Pos logit contributions
 nowhere+0.030
 sky+0.028
 pieces+0.024
 old+0.024
 lost+0.023
Neg logit contributions
iding-0.061
oving-0.054
inn-0.052
ided-0.051
 som-0.051
Token and
Token ID290
Feature activation+2.03e+00

Pos logit contributions
iding+0.050
 som+0.047
heit+0.045
 accompl+0.045
inn+0.044
Neg logit contributions
 sky-0.031
 pieces-0.029
 nowhere-0.028
 old-0.026
s-0.025
Token st
Token ID336
Feature activation-9.77e+00

Pos logit contributions
 sky+0.038
 nowhere+0.037
 pieces+0.033
 woman+0.033
 old+0.031
Neg logit contributions
iding-0.077
inn-0.067
oving-0.067
gh-0.066
 som-0.065
Tokeninky
Token ID29246
Feature activation-1.10e+00

Pos logit contributions
iding+0.267
 som+0.238
inn+0.231
gh+0.231
oving+0.230
Neg logit contributions
 sky-0.262
 nowhere-0.248
 woman-0.236
Someone-0.230
 pieces-0.229
Token!
Token ID0
Feature activation-4.39e-01

Pos logit contributions
iding+0.032
inn+0.030
 accompl+0.029
oving+0.028
 som+0.028
Neg logit contributions
 pieces-0.028
 sky-0.028
 nowhere-0.027
s-0.026
 lost-0.025
Token I
Token ID314
Feature activation-2.37e+00

Pos logit contributions
iding+0.015
 som+0.014
gh+0.014
oving+0.014
inn+0.013
Neg logit contributions
 sky-0.009
Someone-0.008
 woman-0.008
 nowhere-0.008
s-0.007
Token don
Token ID836
Feature activation+7.09e-01

Pos logit contributions
iding+0.078
 accompl+0.066
 avail+0.066
 som+0.066
gh+0.066
Neg logit contributions
 lost-0.051
 nowhere-0.050
 sky-0.050
s-0.050
 pieces-0.045
Token't
Token ID470
Feature activation-1.31e+00

Pos logit contributions
 woman+0.014
 sky+0.014
 nowhere+0.013
Someone+0.011
keeper+0.011
Neg logit contributions
iding-0.024
gh-0.022
inn-0.022
oving-0.022
 som-0.022
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
iding+0.052
oving+0.048
heit+0.047
 som+0.047
gh+0.047
Neg logit contributions
 sky-0.026
 nowhere-0.024
s-0.022
 pieces-0.022
 woman-0.022
Token she
Token ID673
Feature activation-2.37e+00

Pos logit contributions
 sky+0.035
 woman+0.034
 nowhere+0.033
 pieces+0.032
Someone+0.030
Neg logit contributions
iding-0.047
inn-0.041
gh-0.040
oving-0.040
 som-0.039
Token stepped
Token ID10764
Feature activation-3.27e+00

Pos logit contributions
iding+0.069
 som+0.062
inn+0.062
gh+0.061
oving+0.060
Neg logit contributions
 sky-0.059
 nowhere-0.057
 woman-0.055
Someone-0.052
 pieces-0.051
Token into
Token ID656
Feature activation-1.31e+00

Pos logit contributions
iding+0.136
oving+0.130
 som+0.128
heit+0.125
gh+0.124
Neg logit contributions
 sky-0.046
 nowhere-0.042
 pieces-0.035
 flowers-0.034
 nearest-0.032
Token the
Token ID262
Feature activation+2.49e+00

Pos logit contributions
iding+0.047
 som+0.045
inn+0.044
gh+0.043
oving+0.042
Neg logit contributions
 sky-0.022
 woman-0.020
 nowhere-0.020
Someone-0.019
s-0.017
Token p
Token ID279
Feature activation-9.20e+00

Pos logit contributions
 sky+0.062
 nowhere+0.058
 woman+0.057
Someone+0.053
 pieces+0.053
Neg logit contributions
iding-0.075
 som-0.067
inn-0.066
gh-0.066
oving-0.065
Tokenuddle
Token ID24500
Feature activation-1.62e+00

Pos logit contributions
iding+0.233
inn+0.205
 som+0.202
oving+0.196
gh+0.190
Neg logit contributions
 nowhere-0.267
 sky-0.262
 woman-0.254
Someone-0.248
 pieces-0.236
Token.
Token ID13
Feature activation-2.18e-01

Pos logit contributions
iding+0.066
heit+0.066
oving+0.061
gh+0.060
 som+0.060
Neg logit contributions
 sky-0.026
 pieces-0.022
s-0.021
 she-0.020
 nowhere-0.020
Token
Token ID198
Feature activation+4.04e-01

Pos logit contributions
iding+0.006
inn+0.006
 som+0.006
gh+0.006
oving+0.005
Neg logit contributions
 nowhere-0.005
 woman-0.004
 sky-0.004
 pieces-0.004
actus-0.004
Token
Token ID198
Feature activation+9.86e-02

Pos logit contributions
 sky+0.008
 woman+0.008
 nowhere+0.008
 pieces+0.008
rings+0.007
Neg logit contributions
iding-0.013
inn-0.012
gh-0.012
oving-0.011
 som-0.011
TokenThe
Token ID464
Feature activation+1.09e+00

Pos logit contributions
 sky+0.003
 nowhere+0.003
 woman+0.003
 pieces+0.003
 blood+0.003
Neg logit contributions
iding-0.002
gh-0.002
oving-0.002
inn-0.002
 som-0.002
Token said
Token ID531
Feature activation-1.67e-02

Pos logit contributions
 sky+0.048
 nowhere+0.045
 woman+0.045
 pieces+0.039
Someone+0.038
Neg logit contributions
iding-0.108
 som-0.100
gh-0.098
inn-0.098
oving-0.097
Token,
Token ID11
Feature activation-5.01e-01

Pos logit contributions
iding+0.001
oving+0.001
icious+0.001
inn+0.001
 accompl+0.001
Neg logit contributions
 she-0.000
 that-0.000
s-0.000
 woman-0.000
 sky-0.000
Token
Token ID6184
Feature activation-7.24e+00

Pos logit contributions
iding+0.022
oving+0.022
 avail+0.022
 som+0.021
irl+0.021
Neg logit contributions
 woman-0.005
 sky-0.005
 she-0.004
s-0.004
 old-0.004
Token
Token ID95
Feature activation-7.04e+00

Pos logit contributions
iding+0.162
inn+0.139
rum+0.136
oving+0.136
gh+0.136
Neg logit contributions
 sky-0.209
 woman-0.198
 that-0.197
 nowhere-0.194
actus-0.188
Token
Token ID26391
Feature activation-4.40e+00

Pos logit contributions
iding+0.182
 som+0.158
inn+0.155
heit+0.153
oving+0.150
Neg logit contributions
 sky-0.204
 nowhere-0.191
 woman-0.181
Someone-0.177
 nearest-0.165
Token
Token ID129
Feature activation-8.80e+00

Pos logit contributions
iding+0.125
 som+0.111
gh+0.109
inn+0.107
oving+0.107
Neg logit contributions
 sky-0.113
 nowhere-0.109
 woman-0.105
Someone-0.100
 pieces-0.098
Token
Token ID241
Feature activation-3.76e-01

Pos logit contributions
iding+0.195
inn+0.168
 avail+0.164
 som+0.160
 appetite+0.160
Neg logit contributions
 sky-0.268
 nowhere-0.251
 old-0.250
 woman-0.246
 nearest-0.228
TokenOf
Token ID5189
Feature activation-3.13e+00

Pos logit contributions
iding+0.012
heit+0.011
oving+0.011
 appetite+0.011
gh+0.011
Neg logit contributions
 sky-0.008
 woman-0.008
 nowhere-0.008
Someone-0.008
s-0.007
Token course
Token ID1781
Feature activation-2.53e+00

Pos logit contributions
iding+0.103
oving+0.091
 som+0.090
inn+0.088
 accompl+0.086
Neg logit contributions
 sky-0.072
 nowhere-0.068
 woman-0.067
 pieces-0.060
Someone-0.060
Token!
Token ID0
Feature activation-1.53e+00

Pos logit contributions
iding+0.106
 accompl+0.103
inn+0.103
oving+0.102
ws+0.100
Neg logit contributions
 that-0.036
 she-0.034
s-0.034
 of-0.028
's-0.028
Token Let
Token ID3914
Feature activation-2.33e+00

Pos logit contributions
iding+0.050
gh+0.049
 som+0.049
oving+0.047
 appetite+0.045
Neg logit contributions
 sky-0.033
Someone-0.031
 woman-0.030
s-0.028
 nowhere-0.028
Tokenmy
Token ID1820
Feature activation+1.30e+00

Pos logit contributions
iding+0.121
 som+0.117
oving+0.113
gh+0.112
 accompl+0.112
Neg logit contributions
 sky-0.024
 nowhere-0.021
 woman-0.021
s-0.020
 pieces-0.016
Token's
Token ID338
Feature activation-6.49e-01

Pos logit contributions
 sky+0.022
s+0.022
 woman+0.021
 nowhere+0.021
keeper+0.020
Neg logit contributions
iding-0.047
 som-0.044
heit-0.042
oving-0.042
gh-0.042
Token mom
Token ID1995
Feature activation+4.18e+00

Pos logit contributions
iding+0.027
 som+0.025
oving+0.025
inn+0.025
gh+0.024
Neg logit contributions
 sky-0.009
 woman-0.008
 nowhere-0.008
 pieces-0.006
 old-0.006
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
 sky+0.061
 woman+0.057
 nowhere+0.056
s+0.054
keeper+0.049
Neg logit contributions
iding-0.164
 som-0.156
gh-0.150
inn-0.149
oving-0.149
Token She
Token ID1375
Feature activation-1.02e+00

Pos logit contributions
iding+0.046
 som+0.043
gh+0.043
inn+0.041
heit+0.041
Neg logit contributions
 sky-0.011
 nowhere-0.009
 woman-0.008
s-0.008
Someone-0.008
Token st
Token ID336
Feature activation-1.10e+01

Pos logit contributions
iding+0.033
 som+0.030
inn+0.030
gh+0.029
oving+0.029
Neg logit contributions
 sky-0.023
 nowhere-0.021
 woman-0.021
Someone-0.020
 pieces-0.019
Tokenitched
Token ID10981
Feature activation-2.61e+00

Pos logit contributions
iding+0.247
inn+0.219
gh+0.203
oving+0.200
 som+0.198
Neg logit contributions
 sky-0.363
 nowhere-0.347
 woman-0.347
Someone-0.322
 pieces-0.310
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
iding+0.100
oving+0.088
 som+0.088
gh+0.088
inn+0.087
Neg logit contributions
 sky-0.044
 nowhere-0.041
 pieces-0.039
 woman-0.038
 old-0.035
Token small
Token ID1402
Feature activation-1.62e+00

Pos logit contributions
 sky+0.022
 nowhere+0.021
 woman+0.020
Someone+0.019
 pieces+0.018
Neg logit contributions
iding-0.040
 som-0.036
inn-0.036
gh-0.035
oving-0.035
Token tear
Token ID11626
Feature activation-1.94e+00

Pos logit contributions
iding+0.061
 som+0.055
inn+0.055
oving+0.055
gh+0.055
Neg logit contributions
 sky-0.028
 nowhere-0.025
 woman-0.025
 pieces-0.023
Someone-0.022
Token in
Token ID287
Feature activation-3.08e+00

Pos logit contributions
iding+0.077
oving+0.071
heit+0.071
 som+0.070
inn+0.070
Neg logit contributions
 sky-0.030
 pieces-0.026
 nowhere-0.025
 woman-0.024
s-0.022
Token she
Token ID673
Feature activation-1.15e+00

Pos logit contributions
 sky+0.007
 nowhere+0.006
 woman+0.006
Someone+0.005
 pieces+0.005
Neg logit contributions
iding-0.018
inn-0.016
oving-0.016
 som-0.016
gh-0.016
Token would
Token ID561
Feature activation-7.73e-01

Pos logit contributions
iding+0.039
 som+0.037
gh+0.036
inn+0.036
oving+0.036
Neg logit contributions
 sky-0.022
 nowhere-0.020
 woman-0.019
Someone-0.018
 pieces-0.018
Token promise
Token ID6991
Feature activation+2.92e+00

Pos logit contributions
iding+0.026
inn+0.026
heit+0.025
 AW+0.024
oving+0.024
Neg logit contributions
 sky-0.016
 woman-0.014
 that-0.014
 she-0.014
 lost-0.014
Token him
Token ID683
Feature activation+4.98e-01

Pos logit contributions
 sky+0.029
 woman+0.027
 nowhere+0.026
 she+0.024
 that+0.023
Neg logit contributions
iding-0.132
inn-0.125
 som-0.120
heit-0.120
 AW-0.119
Token a
Token ID257
Feature activation-1.91e-02

Pos logit contributions
 sky+0.006
 nowhere+0.005
 woman+0.005
Someone+0.004
 pieces+0.004
Neg logit contributions
iding-0.021
inn-0.019
 som-0.019
oving-0.019
gh-0.019
Token sc
Token ID629
Feature activation-9.61e+00

Pos logit contributions
iding+0.001
oving+0.001
inn+0.001
 som+0.001
gh+0.001
Neg logit contributions
 sky-0.000
 woman-0.000
 nowhere-0.000
 old-0.000
Someone-0.000
Tokenooter
Token ID25141
Feature activation-1.98e+00

Pos logit contributions
iding+0.303
 som+0.277
inn+0.274
gh+0.272
oving+0.270
Neg logit contributions
 sky-0.210
 woman-0.198
 nowhere-0.197
Someone-0.182
 pieces-0.176
Token if
Token ID611
Feature activation+2.56e+00

Pos logit contributions
iding+0.074
inn+0.069
 som+0.067
oving+0.066
heit+0.066
Neg logit contributions
 sky-0.034
 woman-0.032
 nowhere-0.031
 pieces-0.028
s-0.027
Token he
Token ID339
Feature activation-4.18e+00

Pos logit contributions
 sky+0.025
 nowhere+0.025
 woman+0.024
 she+0.020
 pieces+0.018
Neg logit contributions
iding-0.115
inn-0.108
oving-0.105
 appetite-0.103
 som-0.102
Token was
Token ID373
Feature activation-9.63e-02

Pos logit contributions
iding+0.161
inn+0.145
 som+0.144
oving+0.142
gh+0.142
Neg logit contributions
 sky-0.067
 nowhere-0.064
 woman-0.061
Someone-0.055
 pieces-0.055
Token good
Token ID922
Feature activation-1.29e+00

Pos logit contributions
iding+0.004
heit+0.003
inn+0.003
 som+0.003
 AW+0.003
Neg logit contributions
 nowhere-0.002
 old-0.002
 lost-0.002
 sky-0.001
 woman-0.001