TOP ACTIVATIONS
MAX = 5.936

. " A pe b ble , Mom my
M ummy pe ered down at the ground
she skipped until the f auc et was a blur of
Hello , children ," a voice said . " I have
meet new friends ," a voice says . S
saw something strange ! A pe b ble next to him
, who a !" a voice says . " Don 't
are you playing ?" a voice says . They
safely away in a small pe b ble .
, then she grabbed a pe b ble . She looked
and see her ?" a voice says . "
Who goes there ?" a voice said from inside .
to turn on the f auc et . The water came
" I found a pe b ble at the beach
. He looked for another pe b ble that was smaller
other plants ." The f auc et said , " Yes
children agreed and let the pe b ble help measure the
always brought her two high pe aches every week . She
, stop it !" a voice shouts . It is Mom
just me ," a small voice replied . Tim

MIN ACTIVATIONS
MIN = -4.880

young girl had caught a severe case of hyp other mia
so grateful that he became Teddy 's friend and they played
cry . Lily was holding Ruby and laughing . She had
Lily made sure she held Max 's handle tightly so he
, the sea became cho ppy and it started to rain
on , the diamond became Lucy 's favorite toy to play
Bob , her ball was Charlie and her book was Dave
The boy and his little friend were always together and
ran to Lily and snatched Ruby from her hands . She
. Lily laughed and hugged Max . Then , they all
. They got their back packs from the trunk . They
shoulder . He felt their little hands tick ling his neck
loyal dog . He hugged Max and said , " I
happy too . She hugged Max and said , " You
very happy . She holds Daisy and talks to her .
am Sara . This is Max . He is my puppy
would wear their bath ro bes together and play games .
and found the candy wra ppers . L ily
the water was getting cho ppy . The wind was getting
, Anna . This is Elsa . She is your sister

INTERVAL 3.232 - 5.936
CONTAINS 0.126%

, c aw , c aw ". <|endoftext|> Anna and Ben
suddenly he heard a loud voice saying : " You cannot
. The man at the stand said , " You have
Suddenly , Brian heard a voice . The voice was mild
need coins to buy more pe aches and other things ."

INTERVAL 0.528 - 3.232
CONTAINS 29.096%

. She wants her mom to see her trophy . She
the best knees in the school . They were big and
fun toy . They do not want to read the books
the statue . He says , " Okay , mom .
nodded . She went to the living room and played with

INTERVAL -2.176 - 0.528
CONTAINS 68.938%

knew what to do . He spoke into his radio to
toes and stretched out her hands . Snap ! Anna cl
said she was making some y ummy breakfast and asked him
me ." So they went outside and they looked and looked
, he would take it down and test it . He

INTERVAL -4.880 - -2.176
CONTAINS 1.840%

on your plate . Bro ccoli is not that bad .
dragon flies that were sk imming the surface of the water
time , there was a little girl named Lily . She
some food to eat . Fl uffy was happy and started
. One day when they arrived at the mill
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
 thumb+0.021
 Sister+0.018
 mummy+0.018
 Teddy+0.018
 baby+0.018
Neg logit contributions
aw-0.017
aris-0.017
ues-0.016
oke-0.014
lic-0.014
Token
Token ID198
Feature activation+5.53e-01

Pos logit contributions
aw+0.034
aris+0.033
ues+0.032
lic+0.030
oke+0.029
Neg logit contributions
 thumb-0.031
 mummy-0.026
 Sister-0.026
 Teddy-0.026
 baby-0.026
Token
Token ID198
Feature activation-3.32e-01

Pos logit contributions
aw+0.016
aris+0.016
ues+0.015
lic+0.014
hatt+0.014
Neg logit contributions
 thumb-0.013
 mummy-0.011
 Teddy-0.011
 Sister-0.011
 baby-0.011
Token"
Token ID1
Feature activation+1.34e-01

Pos logit contributions
 thumb+0.008
 mummy+0.007
 Teddy+0.007
 Sister+0.007
 baby+0.007
Neg logit contributions
aris-0.009
aw-0.009
ues-0.009
oke-0.008
lic-0.008
TokenA
Token ID32
Feature activation+2.19e+00

Pos logit contributions
aris+0.005
aw+0.005
ues+0.005
oke+0.004
eway+0.004
Neg logit contributions
 thumb-0.002
 Teddy-0.002
 mummy-0.002
 Sister-0.002
 baby-0.002
Token pe
Token ID613
Feature activation+5.94e+00

Pos logit contributions
aris+0.066
aw+0.065
ues+0.064
hatt+0.057
ets+0.056
Neg logit contributions
 thumb-0.052
 baby-0.048
 mummy-0.047
 Teddy-0.042
 Baby-0.041
Tokenb
Token ID65
Feature activation+2.22e+00

Pos logit contributions
aris+0.170
aw+0.142
arium+0.138
hatt+0.137
ues+0.132
Neg logit contributions
 thumb-0.156
 mummy-0.128
 arm-0.122
el-0.119
 baby-0.119
Tokenble
Token ID903
Feature activation+1.66e+00

Pos logit contributions
aris+0.093
aw+0.092
ues+0.088
hatt+0.086
lic+0.085
Neg logit contributions
 thumb-0.026
 mummy-0.017
 baby-0.015
 Teddy-0.015
 Sister-0.013
Token,
Token ID11
Feature activation+2.12e+00

Pos logit contributions
aris+0.055
ues+0.049
hatt+0.048
aw+0.048
lic+0.047
Neg logit contributions
 thumb-0.037
 baby-0.030
 mummy-0.029
 Teddy-0.028
 arm-0.027
Token Mom
Token ID11254
Feature activation+6.41e-01

Pos logit contributions
aris+0.072
aw+0.070
ues+0.066
lic+0.064
hatt+0.063
Neg logit contributions
 thumb-0.043
 mummy-0.037
 Teddy-0.037
 baby-0.036
 Sister-0.034
Tokenmy
Token ID1820
Feature activation-3.09e-01

Pos logit contributions
aris+0.025
aw+0.025
ues+0.024
eway+0.023
hatt+0.023
Neg logit contributions
 thumb-0.009
 Teddy-0.007
 mummy-0.006
 baby-0.006
 Sister-0.006
Token
Token ID220
Feature activation-2.15e-01

Pos logit contributions
 thumb+0.011
 mummy+0.011
 Baby+0.010
 Sister+0.010
 Teddy+0.010
Neg logit contributions
aw-0.017
aris-0.016
ues-0.016
ms-0.015
br-0.015
Token
Token ID198
Feature activation+5.05e-01

Pos logit contributions
 thumb+0.005
 mummy+0.004
 Teddy+0.004
 Sister+0.004
 baby+0.004
Neg logit contributions
aw-0.007
aris-0.006
ues-0.006
hatt-0.006
lic-0.006
Token
Token ID198
Feature activation-6.63e-01

Pos logit contributions
aw+0.016
aris+0.015
ues+0.015
oke+0.014
hatt+0.014
Neg logit contributions
 thumb-0.010
 mummy-0.009
 Teddy-0.009
 Sister-0.009
 Baby-0.009
TokenM
Token ID44
Feature activation-1.18e+00

Pos logit contributions
 thumb+0.014
 mummy+0.013
 Baby+0.012
 Sister+0.012
 Teddy+0.012
Neg logit contributions
aris-0.019
aw-0.019
ues-0.019
oke-0.018
 facts-0.017
Tokenummy
Token ID13513
Feature activation+1.30e+00

Pos logit contributions
 thumb+0.014
 mummy+0.013
 Sister+0.011
 mum+0.009
 baby+0.009
Neg logit contributions
aris-0.047
aw-0.045
ues-0.045
eway-0.044
ks-0.043
Token pe
Token ID613
Feature activation+5.81e+00

Pos logit contributions
aris+0.035
aw+0.034
ues+0.033
eway+0.030
hatt+0.029
Neg logit contributions
 thumb-0.035
 mummy-0.031
 Teddy-0.031
 Sister-0.031
 baby-0.030
Tokenered
Token ID1068
Feature activation+9.96e-01

Pos logit contributions
aris+0.158
 skysc+0.136
aw+0.135
 inconvenience+0.135
 facts+0.133
Neg logit contributions
 thumb-0.146
 mummy-0.126
el-0.122
bing-0.119
 infected-0.114
Token down
Token ID866
Feature activation+8.99e-01

Pos logit contributions
aw+0.031
aris+0.030
ues+0.029
lic+0.027
hatt+0.027
Neg logit contributions
 thumb-0.022
 Sister-0.018
 mummy-0.018
 Teddy-0.018
 baby-0.017
Token at
Token ID379
Feature activation+6.80e-01

Pos logit contributions
aw+0.029
aris+0.029
ues+0.028
oke+0.027
hatt+0.027
Neg logit contributions
 thumb-0.017
 mummy-0.016
 Teddy-0.015
 baby-0.015
 Sister-0.015
Token the
Token ID262
Feature activation+1.67e+00

Pos logit contributions
aw+0.021
aris+0.020
ues+0.018
hatt+0.018
eway+0.018
Neg logit contributions
 thumb-0.015
 Sister-0.012
 infected-0.012
 Teddy-0.012
 Midnight-0.012
Token ground
Token ID2323
Feature activation+1.61e+00

Pos logit contributions
aw+0.045
aris+0.044
ues+0.041
lic+0.039
hatt+0.039
Neg logit contributions
 thumb-0.043
 Sister-0.037
 Teddy-0.036
 mummy-0.036
 baby-0.035
Token she
Token ID673
Feature activation+7.86e-01

Pos logit contributions
aris+0.101
aw+0.100
ues+0.095
lic+0.091
hatt+0.090
Neg logit contributions
 thumb-0.067
 Teddy-0.055
 mummy-0.055
 Sister-0.055
 baby-0.054
Token skipped
Token ID26684
Feature activation+6.54e-01

Pos logit contributions
aris+0.022
aw+0.022
ues+0.022
oke+0.020
eway+0.020
Neg logit contributions
 thumb-0.019
 Teddy-0.016
 mummy-0.016
 Sister-0.015
 baby-0.015
Token until
Token ID1566
Feature activation-3.15e+00

Pos logit contributions
aris+0.023
aw+0.022
ues+0.022
oke+0.022
cod+0.021
Neg logit contributions
 thumb-0.011
 Teddy-0.010
 mummy-0.009
 herself-0.009
 baby-0.009
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
 thumb+0.063
 mummy+0.053
 Teddy+0.053
 Sister+0.052
 baby+0.051
Neg logit contributions
aris-0.103
aw-0.103
ues-0.099
lic-0.094
oke-0.094
Token f
Token ID277
Feature activation+3.71e+00

Pos logit contributions
aris+0.041
aw+0.040
ues+0.038
oke+0.035
eway+0.035
Neg logit contributions
 thumb-0.028
 mummy-0.024
 baby-0.023
 Sister-0.023
 Teddy-0.022
Tokenauc
Token ID14272
Feature activation+5.65e+00

Pos logit contributions
 facts+0.072
arium+0.070
 mate+0.068
aris+0.068
cod+0.064
Neg logit contributions
 thumb-0.102
 Sister-0.092
 Baby-0.091
 mummy-0.091
el-0.091
Tokenet
Token ID316
Feature activation+3.00e+00

Pos logit contributions
aris+0.149
ues+0.139
oke+0.130
eway+0.129
ari+0.129
Neg logit contributions
 thumb-0.141
 Sister-0.122
 arm-0.120
 Teddy-0.115
 scrap-0.115
Token was
Token ID373
Feature activation-1.18e+00

Pos logit contributions
aris+0.101
 facts+0.099
ues+0.096
rets+0.092
cod+0.091
Neg logit contributions
 thumb-0.059
 mummy-0.048
 Teddy-0.048
 baby-0.047
 arm-0.046
Token a
Token ID257
Feature activation-3.13e-01

Pos logit contributions
 thumb+0.023
 mummy+0.019
 Teddy+0.019
 Sister+0.019
 baby+0.019
Neg logit contributions
aris-0.039
aw-0.039
ues-0.037
oke-0.036
hatt-0.035
Token blur
Token ID23671
Feature activation+1.45e+00

Pos logit contributions
 thumb+0.006
 mummy+0.005
 baby+0.005
 Sister+0.005
 Teddy+0.005
Neg logit contributions
aris-0.011
aw-0.011
ues-0.010
oke-0.009
hatt-0.009
Token of
Token ID286
Feature activation+1.05e+00

Pos logit contributions
aris+0.046
ues+0.042
aw+0.042
 facts+0.041
eway+0.041
Neg logit contributions
 thumb-0.032
 Teddy-0.028
 baby-0.027
 Sister-0.026
 mummy-0.025
TokenHello
Token ID15496
Feature activation+2.63e-01

Pos logit contributions
aris+0.010
aw+0.010
ues+0.009
oke+0.009
eway+0.009
Neg logit contributions
 thumb-0.007
 mummy-0.006
 baby-0.006
 Teddy-0.005
 Sister-0.005
Token,
Token ID11
Feature activation+1.51e+00

Pos logit contributions
aw+0.008
aris+0.008
ues+0.008
hatt+0.008
lic+0.007
Neg logit contributions
 thumb-0.006
 Teddy-0.005
 mummy-0.005
 baby-0.005
 Sister-0.004
Token children
Token ID1751
Feature activation+1.47e+00

Pos logit contributions
aw+0.047
aris+0.046
ues+0.045
hatt+0.041
lic+0.041
Neg logit contributions
 thumb-0.033
 Teddy-0.029
 mummy-0.028
 baby-0.027
 Sister-0.027
Token,"
Token ID553
Feature activation+9.62e-01

Pos logit contributions
aris+0.053
hatt+0.052
ues+0.052
lic+0.051
aw+0.051
Neg logit contributions
 thumb-0.024
 Teddy-0.019
 baby-0.018
 mummy-0.018
 Baby-0.017
Token a
Token ID257
Feature activation+1.86e+00

Pos logit contributions
aris+0.028
aw+0.028
ues+0.026
lic+0.025
hatt+0.024
Neg logit contributions
 thumb-0.023
 mummy-0.020
 Teddy-0.020
 Sister-0.020
 baby-0.020
Token voice
Token ID3809
Feature activation+5.63e+00

Pos logit contributions
aris+0.061
aw+0.060
ues+0.058
ets+0.055
ount+0.054
Neg logit contributions
 thumb-0.042
 baby-0.038
 mummy-0.037
 Sister-0.034
 Teddy-0.032
Token said
Token ID531
Feature activation+1.72e+00

Pos logit contributions
aris+0.182
ues+0.162
aw+0.160
hatt+0.148
 wins+0.148
Neg logit contributions
 thumb-0.121
 baby-0.108
 Teddy-0.106
 mummy-0.104
 herself-0.096
Token.
Token ID13
Feature activation+1.54e+00

Pos logit contributions
aris+0.055
aw+0.055
ues+0.051
hatt+0.050
lic+0.050
Neg logit contributions
 thumb-0.038
 Teddy-0.033
 mummy-0.032
 baby-0.031
 Sister-0.030
Token "
Token ID366
Feature activation+1.05e+00

Pos logit contributions
aw+0.043
aris+0.042
ues+0.039
hatt+0.037
eway+0.036
Neg logit contributions
 thumb-0.039
 Teddy-0.035
 mummy-0.034
 baby-0.034
 Sister-0.033
TokenI
Token ID40
Feature activation+1.06e+00

Pos logit contributions
aris+0.035
aw+0.035
ues+0.034
lic+0.032
oke+0.032
Neg logit contributions
 thumb-0.020
 Teddy-0.016
 baby-0.016
 Sister-0.016
 mummy-0.016
Token have
Token ID423
Feature activation+1.38e+00

Pos logit contributions
aw+0.037
aris+0.036
ues+0.034
eway+0.031
 facts+0.031
Neg logit contributions
 thumb-0.020
 Teddy-0.017
 baby-0.017
 mummy-0.017
 Baby-0.015
Token meet
Token ID1826
Feature activation-1.20e-01

Pos logit contributions
aw+0.055
aris+0.055
ues+0.053
lic+0.050
oke+0.050
Neg logit contributions
 thumb-0.031
 Teddy-0.027
 baby-0.025
 mummy-0.025
 Sister-0.023
Token new
Token ID649
Feature activation+1.63e+00

Pos logit contributions
 thumb+0.002
 Teddy+0.002
 baby+0.002
 mummy+0.002
 Baby+0.002
Neg logit contributions
ues-0.004
aris-0.004
lic-0.004
aw-0.004
hatt-0.004
Token friends
Token ID2460
Feature activation-3.22e-01

Pos logit contributions
aris+0.053
ues+0.053
lic+0.053
aw+0.052
oke+0.051
Neg logit contributions
 baby-0.027
 thumb-0.027
 mummy-0.025
 Teddy-0.025
 two-0.024
Token,"
Token ID553
Feature activation-1.06e-01

Pos logit contributions
 thumb+0.006
 Teddy+0.005
 mummy+0.005
 baby+0.005
 Baby+0.004
Neg logit contributions
aris-0.011
hatt-0.011
ues-0.011
aw-0.010
lic-0.010
Token a
Token ID257
Feature activation+1.64e+00

Pos logit contributions
 thumb+0.003
 Sister+0.002
 mummy+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aw-0.003
aris-0.003
ues-0.003
hatt-0.002
oke-0.002
Token voice
Token ID3809
Feature activation+5.59e+00

Pos logit contributions
aris+0.053
aw+0.052
ues+0.047
eway+0.046
ount+0.046
Neg logit contributions
 thumb-0.040
 baby-0.038
 mummy-0.036
 Sister-0.033
 bunny-0.032
Token says
Token ID1139
Feature activation+2.14e+00

Pos logit contributions
aris+0.163
ues+0.139
aw+0.138
ari+0.131
 habitats+0.129
Neg logit contributions
 thumb-0.125
 baby-0.122
 mummy-0.117
 herself-0.117
 Teddy-0.113
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
aris+0.072
aw+0.071
hatt+0.066
lic+0.066
cod+0.066
Neg logit contributions
 thumb-0.042
 Teddy-0.036
 mummy-0.036
 baby-0.034
 tightly-0.032
Token
Token ID198
Feature activation+2.89e-02

Pos logit contributions
aris+0.033
aw+0.032
ues+0.031
lic+0.029
eway+0.029
Neg logit contributions
 thumb-0.023
 Teddy-0.020
 Sister-0.020
 baby-0.020
 mummy-0.020
Token
Token ID198
Feature activation-8.91e-01

Pos logit contributions
aris+0.001
aw+0.001
ues+0.001
lic+0.001
hatt+0.001
Neg logit contributions
 thumb-0.001
 Teddy-0.001
 mummy-0.001
 Sister-0.001
 baby-0.001
TokenS
Token ID50
Feature activation+1.59e-01

Pos logit contributions
 thumb+0.023
 Sister+0.020
 Teddy+0.020
 mummy+0.019
 baby+0.019
Neg logit contributions
aris-0.024
aw-0.023
ues-0.022
lic-0.021
oke-0.021
Token saw
Token ID2497
Feature activation+1.65e+00

Pos logit contributions
 thumb+0.018
 mummy+0.016
 Teddy+0.015
 Sister+0.015
 baby+0.015
Neg logit contributions
aris-0.017
aw-0.017
ues-0.016
oke-0.015
lic-0.015
Token something
Token ID1223
Feature activation+1.61e+00

Pos logit contributions
aw+0.051
aris+0.047
ues+0.043
lic+0.043
hatt+0.042
Neg logit contributions
 thumb-0.038
 Sister-0.032
 mummy-0.031
 Baby-0.029
 Teddy-0.029
Token strange
Token ID6283
Feature activation+2.04e+00

Pos logit contributions
aw+0.052
aris+0.051
ues+0.049
lic+0.046
oke+0.046
Neg logit contributions
 thumb-0.033
 Sister-0.027
 mummy-0.027
 Teddy-0.027
 baby-0.026
Token!
Token ID0
Feature activation+1.26e-01

Pos logit contributions
aris+0.070
ues+0.066
aw+0.064
ari+0.063
oke+0.063
Neg logit contributions
 thumb-0.041
 baby-0.031
 Teddy-0.031
 mummy-0.031
 herself-0.028
Token A
Token ID317
Feature activation+6.98e-01

Pos logit contributions
aw+0.003
aris+0.003
lic+0.003
ues+0.003
oke+0.003
Neg logit contributions
 thumb-0.004
 mummy-0.003
 Sister-0.003
bing-0.003
 baby-0.003
Token pe
Token ID613
Feature activation+5.58e+00

Pos logit contributions
aw+0.024
aris+0.023
ues+0.022
lic+0.021
oke+0.021
Neg logit contributions
 thumb-0.013
 mummy-0.010
 Sister-0.010
 Teddy-0.010
 baby-0.010
Tokenb
Token ID65
Feature activation+1.67e+00

Pos logit contributions
aris+0.138
aw+0.122
ues+0.120
hatt+0.111
ount+0.109
Neg logit contributions
 thumb-0.163
 mummy-0.137
 baby-0.130
 scrap-0.128
 helpless-0.127
Tokenble
Token ID903
Feature activation+1.25e+00

Pos logit contributions
aw+0.066
aris+0.065
ues+0.063
lic+0.060
oke+0.060
Neg logit contributions
 thumb-0.022
 mummy-0.016
 Sister-0.016
 Teddy-0.015
 baby-0.015
Token next
Token ID1306
Feature activation+1.98e+00

Pos logit contributions
aris+0.041
ues+0.039
aw+0.038
 facts+0.035
ount+0.035
Neg logit contributions
 thumb-0.028
 mummy-0.022
 Teddy-0.022
 baby-0.022
 Sister-0.020
Token to
Token ID284
Feature activation-4.83e-01

Pos logit contributions
cod+0.074
ues+0.072
ount+0.069
aw+0.069
aris+0.068
Neg logit contributions
 thumb-0.034
 mummy-0.029
 baby-0.028
 arm-0.028
 two-0.025
Token him
Token ID683
Feature activation+2.45e-01

Pos logit contributions
 thumb+0.013
 ankle+0.012
 hardest+0.011
bing+0.011
 mummy+0.011
Neg logit contributions
aw-0.011
aris-0.009
 circus-0.009
 about-0.009
 museum-0.009
Token,
Token ID11
Feature activation+1.64e-01

Pos logit contributions
aris+0.043
ues+0.041
hatt+0.041
aw+0.040
eway+0.040
Neg logit contributions
 thumb-0.034
 Teddy-0.028
 baby-0.027
 Sister-0.026
 mummy-0.026
Token who
Token ID508
Feature activation+3.41e-01

Pos logit contributions
aris+0.005
aw+0.005
ues+0.005
lic+0.004
hatt+0.004
Neg logit contributions
 thumb-0.004
 Teddy-0.003
 baby-0.003
 mummy-0.003
 Baby-0.003
Tokena
Token ID64
Feature activation+1.38e+00

Pos logit contributions
ues+0.009
aris+0.009
aw+0.009
lic+0.008
eway+0.008
Neg logit contributions
 thumb-0.009
 Teddy-0.008
 baby-0.007
 Sister-0.007
 mummy-0.007
Token!"
Token ID2474
Feature activation+1.48e+00

Pos logit contributions
aris+0.038
ues+0.036
aw+0.036
hatt+0.036
lic+0.035
Neg logit contributions
 thumb-0.034
 Teddy-0.029
 baby-0.028
 Sister-0.028
 mummy-0.028
Token a
Token ID257
Feature activation+1.47e+00

Pos logit contributions
aw+0.037
aris+0.035
ues+0.034
oke+0.032
lic+0.032
Neg logit contributions
 thumb-0.040
bing-0.033
 Sister-0.032
 mummy-0.032
 Ginny-0.031
Token voice
Token ID3809
Feature activation+5.53e+00

Pos logit contributions
aris+0.047
aw+0.046
ues+0.044
ount+0.043
ets+0.042
Neg logit contributions
 thumb-0.034
 baby-0.030
 mummy-0.029
 Sister-0.028
 Baby-0.026
Token says
Token ID1139
Feature activation+2.13e+00

Pos logit contributions
aris+0.153
aw+0.137
ues+0.136
ari+0.123
hatt+0.120
Neg logit contributions
 thumb-0.141
 baby-0.130
 Teddy-0.129
 mummy-0.129
 Sister-0.117
Token.
Token ID13
Feature activation+6.59e-01

Pos logit contributions
aris+0.066
aw+0.065
ues+0.060
hatt+0.059
eway+0.058
Neg logit contributions
 thumb-0.049
 Teddy-0.042
 mummy-0.041
 baby-0.040
 Sister-0.039
Token "
Token ID366
Feature activation+7.50e-01

Pos logit contributions
aw+0.018
aris+0.018
ues+0.017
lic+0.016
hatt+0.016
Neg logit contributions
 thumb-0.017
 mummy-0.014
 Sister-0.014
 Teddy-0.014
 baby-0.014
TokenDon
Token ID3987
Feature activation-6.25e-01

Pos logit contributions
aw+0.023
aris+0.022
ues+0.021
hatt+0.020
lic+0.020
Neg logit contributions
 thumb-0.017
 mummy-0.015
 Sister-0.014
 Teddy-0.014
 baby-0.013
Token't
Token ID470
Feature activation+1.42e+00

Pos logit contributions
 thumb+0.013
 Sister+0.011
 mummy+0.010
 Baby+0.010
 Teddy+0.010
Neg logit contributions
aw-0.020
aris-0.019
lic-0.019
ues-0.018
oke-0.018
Token are
Token ID389
Feature activation-8.79e-01

Pos logit contributions
 thumb+0.013
 baby+0.011
 mummy+0.011
 Teddy+0.011
 two+0.010
Neg logit contributions
aw-0.018
ues-0.018
aris-0.018
hatt-0.017
lic-0.017
Token you
Token ID345
Feature activation+1.58e+00

Pos logit contributions
 mummy+0.012
 Teddy+0.012
 thumb+0.012
 baby+0.011
 Baby+0.010
Neg logit contributions
aris-0.031
aw-0.031
ues-0.031
lic-0.030
oke-0.030
Token playing
Token ID2712
Feature activation+9.56e-01

Pos logit contributions
aw+0.047
aris+0.046
ues+0.043
oke+0.042
lic+0.041
Neg logit contributions
 thumb-0.036
 Sister-0.030
 mummy-0.029
 Teddy-0.029
 baby-0.029
Token?"
Token ID1701
Feature activation+1.23e+00

Pos logit contributions
aris+0.029
aw+0.029
ues+0.028
hatt+0.027
oke+0.027
Neg logit contributions
 thumb-0.022
 mummy-0.018
 Teddy-0.018
 baby-0.017
 Sister-0.016
Token a
Token ID257
Feature activation+1.38e+00

Pos logit contributions
aris+0.030
aw+0.030
ues+0.028
lic+0.026
oke+0.025
Neg logit contributions
 thumb-0.036
 mummy-0.032
 Teddy-0.032
 Sister-0.032
 baby-0.031
Token voice
Token ID3809
Feature activation+5.52e+00

Pos logit contributions
aris+0.045
aw+0.044
ues+0.041
eway+0.040
ount+0.040
Neg logit contributions
 thumb-0.032
 baby-0.028
 mummy-0.028
 Sister-0.026
 Teddy-0.025
Token says
Token ID1139
Feature activation+2.25e+00

Pos logit contributions
aris+0.155
ues+0.137
aw+0.136
ari+0.127
lic+0.123
Neg logit contributions
 thumb-0.141
 mummy-0.128
 baby-0.126
 Teddy-0.125
 herself-0.116
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
aris+0.073
aw+0.072
hatt+0.067
lic+0.067
ues+0.067
Neg logit contributions
 thumb-0.047
 mummy-0.039
 Teddy-0.039
 baby-0.037
 Sister-0.035
Token
Token ID198
Feature activation+6.10e-01

Pos logit contributions
aris+0.047
aw+0.045
ues+0.044
ount+0.041
hatt+0.041
Neg logit contributions
 thumb-0.029
 Teddy-0.026
 mummy-0.025
 Sister-0.025
 baby-0.024
Token
Token ID198
Feature activation-2.75e-01

Pos logit contributions
aris+0.019
aw+0.019
ues+0.018
hatt+0.017
lic+0.017
Neg logit contributions
 thumb-0.013
 Teddy-0.011
 mummy-0.011
 Sister-0.011
 baby-0.010
TokenThey
Token ID2990
Feature activation+1.61e-01

Pos logit contributions
 thumb+0.006
 Teddy+0.005
 mummy+0.005
 Sister+0.005
Mom+0.005
Neg logit contributions
aris-0.008
ues-0.008
aw-0.008
ount-0.007
eway-0.007
Token safely
Token ID11512
Feature activation-2.41e+00

Pos logit contributions
 thumb+0.054
 Sister+0.047
 mummy+0.046
 baby+0.046
 Baby+0.044
Neg logit contributions
aw-0.056
aris-0.054
ues-0.050
lic-0.047
eway-0.046
Token away
Token ID1497
Feature activation-1.16e+00

Pos logit contributions
 thumb+0.052
 Sister+0.046
 mummy+0.044
 Teddy+0.043
 Baby+0.043
Neg logit contributions
aris-0.073
aw-0.072
ues-0.069
lic-0.065
eway-0.064
Token in
Token ID287
Feature activation-6.20e-01

Pos logit contributions
 thumb+0.028
 Sister+0.024
 mummy+0.024
 Teddy+0.024
 baby+0.023
Neg logit contributions
aw-0.033
aris-0.033
ues-0.031
lic-0.029
hatt-0.029
Token a
Token ID257
Feature activation+1.64e-01

Pos logit contributions
 thumb+0.013
 Sister+0.011
 mummy+0.010
 Teddy+0.010
 Ginny+0.010
Neg logit contributions
aw-0.019
aris-0.019
ues-0.018
eway-0.017
hatt-0.017
Token small
Token ID1402
Feature activation-1.16e+00

Pos logit contributions
aw+0.005
aris+0.005
ues+0.005
lic+0.005
oke+0.005
Neg logit contributions
 thumb-0.003
 mummy-0.003
 Sister-0.003
 Teddy-0.003
 baby-0.003
Token pe
Token ID613
Feature activation+5.52e+00

Pos logit contributions
 thumb+0.031
 Sister+0.027
 mummy+0.027
 Teddy+0.027
 Ginny+0.026
Neg logit contributions
aw-0.029
aris-0.029
ues-0.026
ari-0.024
lic-0.024
Tokenb
Token ID65
Feature activation+1.35e+00

Pos logit contributions
aris+0.151
ount+0.126
hatt+0.125
aw+0.124
oke+0.124
Neg logit contributions
 thumb-0.142
 arm-0.113
 mummy-0.113
 helpless-0.110
 ankle-0.109
Tokenble
Token ID903
Feature activation+7.23e-01

Pos logit contributions
aris+0.053
aw+0.052
hatt+0.050
ues+0.050
 facts+0.049
Neg logit contributions
 thumb-0.019
 mummy-0.013
 arm-0.011
 baby-0.011
 Teddy-0.011
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
aris+0.023
ues+0.022
aw+0.021
lic+0.021
oke+0.021
Neg logit contributions
 thumb-0.017
 mummy-0.013
 baby-0.013
 Teddy-0.013
 arm-0.012
Token
Token ID220
Feature activation-3.66e-01

Pos logit contributions
 thumb+0.007
 Teddy+0.006
 mummy+0.006
 Sister+0.006
 Baby+0.006
Neg logit contributions
aw-0.012
ues-0.012
aris-0.012
oke-0.011
lic-0.011
Token
Token ID198
Feature activation+3.00e-01

Pos logit contributions
 thumb+0.008
 mummy+0.007
 Teddy+0.007
 Sister+0.006
 baby+0.006
Neg logit contributions
aw-0.011
aris-0.011
ues-0.011
lic-0.010
hatt-0.010
Token,
Token ID11
Feature activation+9.72e-02

Pos logit contributions
aris+0.053
aw+0.053
ues+0.050
oke+0.050
lic+0.050
Neg logit contributions
 thumb-0.033
 mummy-0.028
 baby-0.027
 Teddy-0.026
 Sister-0.026
Token then
Token ID788
Feature activation-1.31e-01

Pos logit contributions
aw+0.003
aris+0.003
ues+0.003
lic+0.003
oke+0.003
Neg logit contributions
 thumb-0.002
 mummy-0.002
 Sister-0.002
 Teddy-0.002
 baby-0.002
Token she
Token ID673
Feature activation-1.61e-01

Pos logit contributions
 thumb+0.003
 mummy+0.003
 Teddy+0.002
 Sister+0.002
 baby+0.002
Neg logit contributions
aris-0.004
aw-0.004
ues-0.004
oke-0.004
lic-0.004
Token grabbed
Token ID13176
Feature activation+3.34e-01

Pos logit contributions
 thumb+0.004
 mummy+0.003
 Teddy+0.003
 Sister+0.003
 baby+0.003
Neg logit contributions
aris-0.005
aw-0.004
ues-0.004
eway-0.004
oke-0.004
Token a
Token ID257
Feature activation+6.04e-01

Pos logit contributions
aw+0.009
ues+0.008
aris+0.008
hatt+0.008
ks+0.008
Neg logit contributions
 thumb-0.008
 Sister-0.007
 Midnight-0.006
bing-0.006
 mummy-0.006
Token pe
Token ID613
Feature activation+5.49e+00

Pos logit contributions
aw+0.020
aris+0.020
ues+0.019
oke+0.018
lic+0.018
Neg logit contributions
 thumb-0.012
 mummy-0.010
 Sister-0.009
 Teddy-0.009
 baby-0.009
Tokenb
Token ID65
Feature activation+1.17e+00

Pos logit contributions
aris+0.149
aw+0.126
ari+0.120
oke+0.119
arium+0.119
Neg logit contributions
 thumb-0.156
 mummy-0.128
 baby-0.123
 arm-0.122
bing-0.120
Tokenble
Token ID903
Feature activation+1.94e-02

Pos logit contributions
aris+0.047
aw+0.047
ues+0.044
hatt+0.043
lic+0.043
Neg logit contributions
 thumb-0.015
 mummy-0.011
 Teddy-0.010
 Sister-0.010
 baby-0.010
Token.
Token ID13
Feature activation-7.99e-01

Pos logit contributions
aris+0.001
aw+0.001
ues+0.001
lic+0.001
oke+0.001
Neg logit contributions
 thumb-0.000
 mummy-0.000
 baby-0.000
 Teddy-0.000
 Sister-0.000
Token She
Token ID1375
Feature activation+4.23e-01

Pos logit contributions
 thumb+0.018
 mummy+0.015
 Sister+0.015
 Teddy+0.015
 baby+0.015
Neg logit contributions
aw-0.024
aris-0.024
ues-0.022
lic-0.021
oke-0.021
Token looked
Token ID3114
Feature activation+2.11e-01

Pos logit contributions
aris+0.012
aw+0.012
ues+0.012
oke+0.011
eway+0.011
Neg logit contributions
 thumb-0.010
 mummy-0.009
 Teddy-0.009
 Sister-0.008
 baby-0.008
Token and
Token ID290
Feature activation+8.79e-01

Pos logit contributions
aw+0.010
aris+0.010
ues+0.009
ari+0.009
lic+0.009
Neg logit contributions
 thumb-0.010
 Sister-0.009
 Baby-0.009
 Ginny-0.009
 mummy-0.008
Token see
Token ID766
Feature activation+1.42e+00

Pos logit contributions
aw+0.025
aris+0.025
ues+0.024
lic+0.022
hatt+0.022
Neg logit contributions
 thumb-0.021
 mummy-0.018
 Sister-0.018
 Teddy-0.017
 baby-0.017
Token her
Token ID607
Feature activation-8.56e-01

Pos logit contributions
aw+0.041
aris+0.039
ues+0.036
oke+0.034
lic+0.034
Neg logit contributions
 thumb-0.035
 Sister-0.029
 mummy-0.028
 baby-0.027
 Ginny-0.027
Token?"
Token ID1701
Feature activation+5.93e-01

Pos logit contributions
 thumb+0.021
 Sister+0.018
 mummy+0.018
 Teddy+0.017
 baby+0.017
Neg logit contributions
aw-0.024
aris-0.024
ues-0.022
lic-0.021
oke-0.021
Token a
Token ID257
Feature activation+1.29e+00

Pos logit contributions
aw+0.015
aris+0.014
oke+0.013
ues+0.013
hatt+0.012
Neg logit contributions
 thumb-0.016
bing-0.013
 Sister-0.013
 mummy-0.013
 Teddy-0.013
Token voice
Token ID3809
Feature activation+5.47e+00

Pos logit contributions
aris+0.041
aw+0.038
ues+0.037
eway+0.037
ount+0.035
Neg logit contributions
 thumb-0.031
 baby-0.028
 mummy-0.028
 Sister-0.027
 Teddy-0.025
Token says
Token ID1139
Feature activation+2.31e+00

Pos logit contributions
aris+0.156
ues+0.139
aw+0.133
ari+0.128
 habitats+0.121
Neg logit contributions
 thumb-0.131
 baby-0.128
 Teddy-0.122
 mummy-0.121
 helpless-0.114
Token.
Token ID13
Feature activation+3.76e-01

Pos logit contributions
aris+0.074
aw+0.074
ues+0.067
hatt+0.066
 facts+0.065
Neg logit contributions
 thumb-0.051
 Teddy-0.044
 mummy-0.042
 baby-0.041
 Sister-0.039
Token
Token ID198
Feature activation+1.94e-01

Pos logit contributions
aw+0.010
aris+0.010
ues+0.009
lic+0.009
oke+0.009
Neg logit contributions
 thumb-0.010
 mummy-0.008
 Sister-0.008
 Teddy-0.008
 baby-0.008
Token
Token ID198
Feature activation-8.50e-01

Pos logit contributions
aw+0.004
aris+0.004
ues+0.004
lic+0.004
oke+0.004
Neg logit contributions
 thumb-0.006
 Sister-0.005
 baby-0.005
 mummy-0.005
 Ginny-0.005
Token"
Token ID1
Feature activation-2.37e-01

Pos logit contributions
 thumb+0.028
 mummy+0.025
 baby+0.024
 Sister+0.024
 Teddy+0.023
Neg logit contributions
aw-0.018
aris-0.017
ues-0.016
lic-0.015
oke-0.015
TokenWho
Token ID8241
Feature activation+2.32e+00

Pos logit contributions
 thumb+0.019
 Sister+0.017
 Baby+0.017
 Teddy+0.016
 Ginny+0.016
Neg logit contributions
aris-0.020
aw-0.019
ues-0.017
ari-0.017
arium-0.016
Token goes
Token ID2925
Feature activation+1.27e+00

Pos logit contributions
aris+0.072
ues+0.070
aw+0.069
lic+0.068
hatt+0.066
Neg logit contributions
 thumb-0.050
 mummy-0.043
 baby-0.041
 Teddy-0.039
 two-0.038
Token there
Token ID612
Feature activation-1.59e-01

Pos logit contributions
aw+0.038
aris+0.038
ues+0.036
lic+0.034
hatt+0.034
Neg logit contributions
 thumb-0.029
 mummy-0.025
 Teddy-0.025
 Sister-0.024
 baby-0.024
Token?"
Token ID1701
Feature activation+9.82e-01

Pos logit contributions
 thumb+0.004
 mummy+0.003
 Teddy+0.003
 baby+0.003
 Sister+0.003
Neg logit contributions
aw-0.005
aris-0.005
ues-0.004
lic-0.004
hatt-0.004
Token a
Token ID257
Feature activation+1.47e+00

Pos logit contributions
aris+0.033
ues+0.032
aw+0.032
lic+0.030
ari+0.029
Neg logit contributions
 thumb-0.020
 mummy-0.018
 Teddy-0.017
 Sister-0.017
 Baby-0.017
Token voice
Token ID3809
Feature activation+5.47e+00

Pos logit contributions
aris+0.054
ues+0.051
aw+0.051
ount+0.048
ets+0.048
Neg logit contributions
 thumb-0.028
 baby-0.026
 mummy-0.025
 Sister-0.022
 Baby-0.022
Token said
Token ID531
Feature activation+1.76e+00

Pos logit contributions
aris+0.179
aw+0.160
ues+0.160
ari+0.148
cod+0.144
Neg logit contributions
 thumb-0.118
 mummy-0.110
 baby-0.108
 Teddy-0.098
 Baby-0.095
Token from
Token ID422
Feature activation+1.11e+00

Pos logit contributions
aris+0.062
aw+0.059
ues+0.056
 facts+0.054
hatt+0.054
Neg logit contributions
 thumb-0.036
 mummy-0.033
 Teddy-0.031
 baby-0.030
 Baby-0.028
Token inside
Token ID2641
Feature activation+1.30e+00

Pos logit contributions
aris+0.039
aw+0.039
ues+0.037
oke+0.035
lic+0.035
Neg logit contributions
 thumb-0.020
 mummy-0.017
 Teddy-0.016
 baby-0.016
 Sister-0.016
Token.
Token ID13
Feature activation+8.23e-01

Pos logit contributions
aris+0.047
aw+0.046
ues+0.044
hatt+0.042
lic+0.041
Neg logit contributions
 thumb-0.023
 mummy-0.020
 baby-0.020
 Teddy-0.019
 Baby-0.019
Token
Token ID198
Feature activation+8.68e-01

Pos logit contributions
aw+0.029
aris+0.029
ues+0.028
ets+0.028
cod+0.027
Neg logit contributions
 Teddy-0.014
 thumb-0.013
 mummy-0.013
 Sister-0.013
 Baby-0.013
Token to
Token ID284
Feature activation+2.74e-01

Pos logit contributions
aw+0.008
aris+0.007
ues+0.007
lic+0.007
hatt+0.007
Neg logit contributions
 thumb-0.005
 Teddy-0.005
 mummy-0.005
 baby-0.005
 Sister-0.004
Token turn
Token ID1210
Feature activation+2.04e-01

Pos logit contributions
aw+0.008
aris+0.008
ues+0.008
oke+0.007
lic+0.007
Neg logit contributions
 thumb-0.006
 mummy-0.005
 Sister-0.005
 Teddy-0.005
 baby-0.005
Token on
Token ID319
Feature activation-5.01e-01

Pos logit contributions
aw+0.006
aris+0.006
ues+0.006
hatt+0.005
ks+0.005
Neg logit contributions
 thumb-0.004
 Sister-0.004
 Ginny-0.003
 mummy-0.003
 Baby-0.003
Token the
Token ID262
Feature activation+1.66e+00

Pos logit contributions
 thumb+0.011
 Sister+0.008
 mummy+0.008
 baby+0.008
 Ginny+0.008
Neg logit contributions
aw-0.015
aris-0.015
ues-0.014
 facts-0.013
hatt-0.013
Token f
Token ID277
Feature activation+3.38e+00

Pos logit contributions
aw+0.035
lic+0.033
aris+0.033
ues+0.033
auc+0.032
Neg logit contributions
 thumb-0.047
 Sister-0.042
 Teddy-0.042
 Midnight-0.042
 Ginny-0.042
Tokenauc
Token ID14272
Feature activation+5.44e+00

Pos logit contributions
aris+0.060
aw+0.057
 facts+0.056
 mate+0.056
 circus+0.055
Neg logit contributions
 thumb-0.096
 Sister-0.087
 mummy-0.086
 iron-0.084
 Teddy-0.083
Tokenet
Token ID316
Feature activation+2.46e+00

Pos logit contributions
aris+0.137
ues+0.121
aw+0.121
oke+0.118
eway+0.118
Neg logit contributions
 thumb-0.150
 Sister-0.130
 arm-0.130
 Teddy-0.123
 iron-0.122
Token.
Token ID13
Feature activation-8.45e-01

Pos logit contributions
aris+0.078
aw+0.075
ues+0.071
hatt+0.071
lic+0.070
Neg logit contributions
 thumb-0.054
 Teddy-0.045
 mummy-0.045
 baby-0.044
 arm-0.041
Token The
Token ID383
Feature activation+2.90e-01

Pos logit contributions
 thumb+0.017
 Teddy+0.015
 mummy+0.015
 Sister+0.014
 baby+0.014
Neg logit contributions
aw-0.029
aris-0.027
ues-0.026
oke-0.025
eway-0.025
Token water
Token ID1660
Feature activation+8.81e-01

Pos logit contributions
aw+0.009
aris+0.009
ues+0.009
oke+0.008
lic+0.008
Neg logit contributions
 thumb-0.007
 mummy-0.006
 baby-0.006
 Sister-0.005
 Teddy-0.005
Token came
Token ID1625
Feature activation-1.74e+00

Pos logit contributions
aris+0.031
aw+0.029
ues+0.028
ari+0.026
rets+0.026
Neg logit contributions
 thumb-0.019
 mummy-0.016
 baby-0.015
 Teddy-0.014
 Sister-0.014
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 thumb+0.006
 mummy+0.005
 Teddy+0.005
 Sister+0.005
 baby+0.005
Neg logit contributions
aw-0.007
aris-0.007
ues-0.007
lic-0.006
hatt-0.006
Token"
Token ID1
Feature activation-9.81e-02

Pos logit contributions
 thumb+0.026
 mummy+0.022
 Sister+0.022
 Teddy+0.022
 baby+0.021
Neg logit contributions
aw-0.027
aris-0.027
ues-0.025
lic-0.024
oke-0.024
TokenI
Token ID40
Feature activation+9.34e-01

Pos logit contributions
 thumb+0.002
 mummy+0.002
 Sister+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aw-0.003
aris-0.003
ues-0.003
lic-0.003
oke-0.003
Token found
Token ID1043
Feature activation+2.42e+00

Pos logit contributions
aw+0.028
aris+0.028
ues+0.026
lic+0.024
eway+0.024
Neg logit contributions
 thumb-0.022
 mummy-0.018
 Teddy-0.018
 Sister-0.018
 baby-0.018
Token a
Token ID257
Feature activation+1.05e+00

Pos logit contributions
aw+0.079
aris+0.078
ues+0.074
lic+0.071
oke+0.070
Neg logit contributions
 thumb-0.049
 mummy-0.040
 Sister-0.039
 Teddy-0.039
 baby-0.038
Token pe
Token ID613
Feature activation+5.44e+00

Pos logit contributions
aw+0.031
aris+0.031
ues+0.029
lic+0.028
oke+0.028
Neg logit contributions
 thumb-0.024
 mummy-0.020
 Sister-0.020
 Teddy-0.020
 baby-0.019
Tokenb
Token ID65
Feature activation+1.32e+00

Pos logit contributions
aris+0.137
aw+0.122
ues+0.115
hatt+0.113
arium+0.112
Neg logit contributions
 thumb-0.159
 mummy-0.134
 baby-0.130
 arm-0.124
 Ginny-0.122
Tokenble
Token ID903
Feature activation+4.24e-01

Pos logit contributions
aris+0.053
aw+0.053
ues+0.051
hatt+0.049
lic+0.049
Neg logit contributions
 thumb-0.017
 mummy-0.012
 Teddy-0.011
 baby-0.011
 Sister-0.011
Token at
Token ID379
Feature activation+4.11e-01

Pos logit contributions
aris+0.013
aw+0.013
ues+0.012
hatt+0.012
lic+0.012
Neg logit contributions
 thumb-0.010
 mummy-0.008
 baby-0.008
 Teddy-0.008
 Sister-0.007
Token the
Token ID262
Feature activation+2.30e+00

Pos logit contributions
aris+0.013
aw+0.013
ues+0.012
arium+0.011
eway+0.011
Neg logit contributions
 thumb-0.008
 Sister-0.007
 mummy-0.006
 Teddy-0.006
 baby-0.006
Token beach
Token ID10481
Feature activation+2.53e+00

Pos logit contributions
aris+0.074
aw+0.073
ues+0.070
lic+0.066
oke+0.066
Neg logit contributions
 thumb-0.050
 mummy-0.042
 baby-0.041
 Teddy-0.040
 Sister-0.040
Token.
Token ID13
Feature activation+8.32e-01

Pos logit contributions
aw+0.030
aris+0.029
ues+0.027
lic+0.026
hatt+0.026
Neg logit contributions
 thumb-0.028
 mummy-0.024
 Teddy-0.024
 Sister-0.023
 baby-0.023
Token He
Token ID679
Feature activation+1.15e+00

Pos logit contributions
aw+0.024
aris+0.024
ues+0.022
eway+0.020
oke+0.020
Neg logit contributions
 thumb-0.020
 mummy-0.018
 Teddy-0.018
 Sister-0.017
 baby-0.017
Token looked
Token ID3114
Feature activation+6.11e-01

Pos logit contributions
aris+0.034
aw+0.032
ues+0.031
eway+0.029
oke+0.029
Neg logit contributions
 thumb-0.028
 Sister-0.024
 mummy-0.024
 Teddy-0.024
 baby-0.023
Token for
Token ID329
Feature activation+1.94e+00

Pos logit contributions
aw+0.017
aris+0.017
ues+0.016
lic+0.015
oke+0.015
Neg logit contributions
 thumb-0.015
 mummy-0.013
 Sister-0.013
 Teddy-0.013
 baby-0.012
Token another
Token ID1194
Feature activation-1.10e-01

Pos logit contributions
aw+0.060
aris+0.058
ues+0.056
lic+0.053
hatt+0.053
Neg logit contributions
 thumb-0.043
 Sister-0.034
 mummy-0.033
 Teddy-0.033
 baby-0.032
Token pe
Token ID613
Feature activation+5.41e+00

Pos logit contributions
 thumb+0.003
 mummy+0.002
 baby+0.002
 Sister+0.002
 Teddy+0.002
Neg logit contributions
aris-0.003
aw-0.003
ues-0.003
lic-0.003
hatt-0.003
Tokenb
Token ID65
Feature activation+1.09e+00

Pos logit contributions
aris+0.160
arium+0.137
aw+0.136
hatt+0.134
lic+0.133
Neg logit contributions
 thumb-0.130
bing-0.101
 mummy-0.101
 arm-0.099
el-0.098
Tokenble
Token ID903
Feature activation+3.64e-01

Pos logit contributions
aris+0.045
aw+0.044
ues+0.043
hatt+0.042
lic+0.041
Neg logit contributions
 thumb-0.013
 mummy-0.008
 baby-0.008
 Teddy-0.007
 Sister-0.007
Token that
Token ID326
Feature activation-9.86e-02

Pos logit contributions
aris+0.012
lic+0.012
ues+0.012
aw+0.012
hatt+0.011
Neg logit contributions
 thumb-0.007
 baby-0.005
 Teddy-0.005
 mummy-0.005
 arm-0.005
Token was
Token ID373
Feature activation-1.14e-01

Pos logit contributions
 thumb+0.002
 Teddy+0.002
 baby+0.002
 mummy+0.002
 Sister+0.002
Neg logit contributions
aris-0.003
ues-0.003
aw-0.003
lic-0.003
ari-0.003
Token smaller
Token ID4833
Feature activation+4.37e-03

Pos logit contributions
 thumb+0.002
 mummy+0.002
 Teddy+0.002
 baby+0.002
 Sister+0.002
Neg logit contributions
aris-0.004
aw-0.004
ues-0.004
oke-0.004
ari-0.004
Token other
Token ID584
Feature activation-9.82e-01

Pos logit contributions
 thumb+0.004
 mummy+0.003
 baby+0.003
 Sister+0.003
 Teddy+0.003
Neg logit contributions
aris-0.005
aw-0.005
ues-0.005
lic-0.005
oke-0.005
Token plants
Token ID6134
Feature activation-1.86e-01

Pos logit contributions
 thumb+0.023
 mummy+0.019
 baby+0.019
 Sister+0.019
 Teddy+0.018
Neg logit contributions
aris-0.029
aw-0.029
ues-0.028
lic-0.026
hatt-0.026
Token."
Token ID526
Feature activation-2.16e-01

Pos logit contributions
 thumb+0.004
 mummy+0.004
 baby+0.004
 Teddy+0.004
 Sister+0.003
Neg logit contributions
aw-0.005
aris-0.005
ues-0.005
hatt-0.005
lic-0.005
Token The
Token ID383
Feature activation-2.42e-02

Pos logit contributions
 thumb+0.003
 Teddy+0.002
 mummy+0.002
 Baby+0.002
 Sister+0.002
Neg logit contributions
ues-0.009
aris-0.009
aw-0.009
eway-0.008
oke-0.008
Token f
Token ID277
Feature activation+3.78e+00

Pos logit contributions
 thumb+0.001
 mummy+0.000
 Sister+0.000
 baby+0.000
 Teddy+0.000
Neg logit contributions
aw-0.001
aris-0.001
ues-0.001
lic-0.001
oke-0.001
Tokenauc
Token ID14272
Feature activation+5.38e+00

Pos logit contributions
aris+0.066
aw+0.055
arium+0.054
 facts+0.054
 mate+0.054
Neg logit contributions
 thumb-0.127
 mummy-0.108
el-0.106
 baby-0.104
bing-0.103
Tokenet
Token ID316
Feature activation+2.74e+00

Pos logit contributions
aris+0.142
ues+0.120
ari+0.116
aw+0.112
arium+0.111
Neg logit contributions
 thumb-0.154
 arm-0.124
 baby-0.124
 Sister-0.119
 herself-0.117
Token said
Token ID531
Feature activation+2.19e+00

Pos logit contributions
aris+0.096
ues+0.090
aw+0.087
ount+0.083
 inconvenience+0.083
Neg logit contributions
 thumb-0.058
 mummy-0.046
 baby-0.045
 Sister-0.042
 Teddy-0.041
Token,
Token ID11
Feature activation+1.23e+00

Pos logit contributions
aris+0.075
aw+0.073
ues+0.069
hatt+0.068
ount+0.066
Neg logit contributions
 thumb-0.043
 mummy-0.037
 baby-0.035
 Teddy-0.035
 Sister-0.033
Token "
Token ID366
Feature activation+1.25e-01

Pos logit contributions
aris+0.035
aw+0.035
ues+0.032
eway+0.030
hatt+0.030
Neg logit contributions
 thumb-0.031
 mummy-0.027
 baby-0.027
 Teddy-0.027
 Sister-0.027
TokenYes
Token ID5297
Feature activation+1.20e+00

Pos logit contributions
aris+0.004
ues+0.004
aw+0.004
oke+0.004
eway+0.004
Neg logit contributions
 thumb-0.003
 mummy-0.002
 baby-0.002
 Sister-0.002
 Teddy-0.002
Token children
Token ID1751
Feature activation+1.04e+00

Pos logit contributions
aris+0.034
aw+0.034
ues+0.033
lic+0.031
oke+0.030
Neg logit contributions
 thumb-0.025
 mummy-0.021
 baby-0.021
 Sister-0.021
 Teddy-0.021
Token agreed
Token ID4987
Feature activation+2.70e-01

Pos logit contributions
aris+0.033
aw+0.032
ues+0.031
lic+0.030
eway+0.029
Neg logit contributions
 thumb-0.022
 mummy-0.019
 baby-0.018
 Sister-0.018
 Teddy-0.018
Token and
Token ID290
Feature activation+1.61e+00

Pos logit contributions
aris+0.009
aw+0.009
ues+0.008
lic+0.008
oke+0.008
Neg logit contributions
 thumb-0.006
 mummy-0.005
 baby-0.005
 Teddy-0.005
 Sister-0.005
Token let
Token ID1309
Feature activation-2.03e+00

Pos logit contributions
aris+0.051
aw+0.050
ues+0.048
oke+0.046
eway+0.045
Neg logit contributions
 thumb-0.034
 mummy-0.032
 Teddy-0.032
 Sister-0.031
 baby-0.031
Token the
Token ID262
Feature activation+2.25e+00

Pos logit contributions
 thumb+0.044
 mummy+0.039
 Sister+0.038
 baby+0.038
 Teddy+0.038
Neg logit contributions
aris-0.064
aw-0.062
ues-0.061
lic-0.057
oke-0.057
Token pe
Token ID613
Feature activation+5.37e+00

Pos logit contributions
aris+0.077
aw+0.076
ues+0.074
lic+0.070
oke+0.069
Neg logit contributions
 thumb-0.043
 mummy-0.035
 baby-0.035
 Sister-0.034
 Teddy-0.032
Tokenb
Token ID65
Feature activation+1.42e+00

Pos logit contributions
aris+0.162
aw+0.138
arium+0.138
ari+0.132
hatt+0.130
Neg logit contributions
 thumb-0.124
 mummy-0.108
 herself-0.104
 baby-0.104
 two-0.101
Tokenble
Token ID903
Feature activation+1.61e+00

Pos logit contributions
aris+0.048
aw+0.045
arium+0.045
ues+0.043
hatt+0.042
Neg logit contributions
 thumb-0.028
 mummy-0.024
 baby-0.023
 herself-0.022
 two-0.021
Token help
Token ID1037
Feature activation-7.30e-01

Pos logit contributions
aris+0.056
aw+0.053
oke+0.051
ues+0.050
lic+0.050
Neg logit contributions
 thumb-0.032
 mummy-0.028
 baby-0.027
 herself-0.024
 Teddy-0.024
Token measure
Token ID3953
Feature activation+1.95e+00

Pos logit contributions
 thumb+0.015
 mummy+0.013
 baby+0.013
 Teddy+0.013
 Sister+0.013
Neg logit contributions
aris-0.024
aw-0.023
ues-0.022
lic-0.021
hatt-0.021
Token the
Token ID262
Feature activation+5.10e-01

Pos logit contributions
aris+0.069
aw+0.067
ues+0.063
hatt+0.063
lic+0.063
Neg logit contributions
 thumb-0.034
 mummy-0.029
 baby-0.028
 Teddy-0.027
 Baby-0.026
Token always
Token ID1464
Feature activation+6.32e-01

Pos logit contributions
 thumb+0.018
 mummy+0.016
 Sister+0.015
 Teddy+0.015
 baby+0.015
Neg logit contributions
aris-0.019
aw-0.019
ues-0.018
eway-0.016
hatt-0.016
Token brought
Token ID3181
Feature activation-1.63e+00

Pos logit contributions
aw+0.017
aris+0.017
ues+0.015
hatt+0.014
eway+0.014
Neg logit contributions
 thumb-0.017
 mummy-0.015
 Sister-0.015
 Teddy-0.014
 baby-0.014
Token her
Token ID607
Feature activation-8.38e-01

Pos logit contributions
 thumb+0.028
 mummy+0.023
 baby+0.022
 Sister+0.022
 Teddy+0.022
Neg logit contributions
aris-0.058
aw-0.058
ues-0.055
lic-0.053
hatt-0.053
Token two
Token ID734
Feature activation-3.10e+00

Pos logit contributions
 thumb+0.020
 Teddy+0.017
 Sister+0.017
 mummy+0.016
 Baby+0.016
Neg logit contributions
aw-0.025
aris-0.024
ues-0.023
oke-0.021
lic-0.021
Token high
Token ID1029
Feature activation+1.69e+00

Pos logit contributions
 thumb+0.076
 mummy+0.064
 Sister+0.064
 Teddy+0.064
 baby+0.062
Neg logit contributions
aw-0.088
aris-0.087
ues-0.082
lic-0.077
oke-0.077
Token pe
Token ID613
Feature activation+5.37e+00

Pos logit contributions
aris+0.049
aw+0.048
ues+0.046
lic+0.045
hatt+0.044
Neg logit contributions
 thumb-0.040
 mummy-0.034
 baby-0.034
 Sister-0.033
 Teddy-0.032
Tokenaches
Token ID3694
Feature activation+1.02e-01

Pos logit contributions
aris+0.135
arium+0.119
hatt+0.119
aw+0.118
lic+0.115
Neg logit contributions
 thumb-0.141
 herself-0.122
 mummy-0.120
 baby-0.120
 Ginny-0.114
Token every
Token ID790
Feature activation-1.79e-01

Pos logit contributions
aw+0.003
aris+0.003
ues+0.003
hatt+0.003
lic+0.003
Neg logit contributions
 thumb-0.002
 mummy-0.002
 Teddy-0.002
 baby-0.002
 Sister-0.002
Token week
Token ID1285
Feature activation-7.53e-01

Pos logit contributions
 thumb+0.005
 mummy+0.004
 baby+0.004
 Sister+0.004
 Baby+0.004
Neg logit contributions
aris-0.005
aw-0.005
ues-0.005
lic-0.005
oke-0.005
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
 thumb+0.016
 baby+0.014
 mummy+0.014
 Teddy+0.013
 Baby+0.013
Neg logit contributions
aw-0.023
aris-0.023
hatt-0.022
ues-0.022
lic-0.022
Token She
Token ID1375
Feature activation+5.11e-01

Pos logit contributions
 mummy+0.003
 thumb+0.003
 Baby+0.003
 Sister+0.003
 baby+0.003
Neg logit contributions
aw-0.005
ues-0.005
aris-0.005
lic-0.005
oke-0.005
Token,
Token ID11
Feature activation+4.10e-01

Pos logit contributions
aw+0.021
aris+0.020
ues+0.019
lic+0.018
oke+0.018
Neg logit contributions
 thumb-0.017
 Sister-0.014
 mummy-0.014
 Teddy-0.014
 baby-0.014
Token stop
Token ID2245
Feature activation+1.09e+00

Pos logit contributions
aris+0.013
aw+0.012
ues+0.012
lic+0.011
ari+0.011
Neg logit contributions
 thumb-0.010
 baby-0.008
 mummy-0.008
 Teddy-0.008
 Baby-0.008
Token it
Token ID340
Feature activation-4.43e-02

Pos logit contributions
aris+0.031
aw+0.031
ues+0.029
lic+0.027
hatt+0.027
Neg logit contributions
 thumb-0.027
 mummy-0.023
 Teddy-0.023
 Sister-0.023
 baby-0.022
Token!"
Token ID2474
Feature activation+1.79e+00

Pos logit contributions
 thumb+0.001
 baby+0.001
 mummy+0.001
 Teddy+0.001
 Sister+0.001
Neg logit contributions
aris-0.001
aw-0.001
ues-0.001
hatt-0.001
 facts-0.001
Token a
Token ID257
Feature activation+1.74e+00

Pos logit contributions
aw+0.050
aris+0.049
ues+0.047
lic+0.044
oke+0.043
Neg logit contributions
 thumb-0.045
 mummy-0.039
 Sister-0.038
 Teddy-0.038
 baby-0.038
Token voice
Token ID3809
Feature activation+5.36e+00

Pos logit contributions
aris+0.062
aw+0.061
ues+0.057
ount+0.055
ets+0.054
Neg logit contributions
 thumb-0.035
 baby-0.033
 mummy-0.031
 Sister-0.028
 helpless-0.027
Token shouts
Token ID34757
Feature activation+2.37e+00

Pos logit contributions
aris+0.144
ues+0.126
aw+0.125
ari+0.116
arium+0.113
Neg logit contributions
 thumb-0.137
 baby-0.127
 Teddy-0.126
 mummy-0.124
 herself-0.119
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
aris+0.069
aw+0.066
ues+0.064
lic+0.062
hatt+0.061
Neg logit contributions
 thumb-0.057
 Teddy-0.049
 mummy-0.048
 baby-0.048
 Sister-0.047
Token It
Token ID632
Feature activation+1.51e+00

Pos logit contributions
aris+0.030
aw+0.030
ues+0.028
hatt+0.026
oke+0.025
Neg logit contributions
 thumb-0.026
 Teddy-0.023
 mummy-0.023
 Sister-0.022
 baby-0.022
Token is
Token ID318
Feature activation+1.02e+00

Pos logit contributions
aris+0.052
ues+0.047
aw+0.047
ari+0.043
adows+0.043
Neg logit contributions
 thumb-0.027
 baby-0.027
 Teddy-0.025
 scrap-0.024
 two-0.024
Token Mom
Token ID11254
Feature activation+7.46e-01

Pos logit contributions
aris+0.031
aw+0.030
ues+0.029
oke+0.027
lic+0.027
Neg logit contributions
 thumb-0.024
 Teddy-0.021
 mummy-0.021
 Sister-0.021
 baby-0.021
Token just
Token ID655
Feature activation+1.65e+00

Pos logit contributions
aris+0.013
aw+0.013
ues+0.013
oke+0.012
lic+0.012
Neg logit contributions
 thumb-0.007
 Teddy-0.006
 mummy-0.006
 Sister-0.006
 baby-0.006
Token me
Token ID502
Feature activation+1.43e+00

Pos logit contributions
ues+0.064
aris+0.064
aw+0.061
oke+0.059
lic+0.058
Neg logit contributions
 thumb-0.026
 Teddy-0.023
 baby-0.021
 mummy-0.021
 Baby-0.020
Token,"
Token ID553
Feature activation+2.14e-01

Pos logit contributions
aw+0.041
aris+0.041
ues+0.039
lic+0.037
oke+0.037
Neg logit contributions
 thumb-0.034
 Sister-0.028
 mummy-0.028
 Teddy-0.028
 baby-0.027
Token a
Token ID257
Feature activation+1.73e+00

Pos logit contributions
aris+0.006
aw+0.006
ues+0.006
oke+0.006
ount+0.006
Neg logit contributions
 thumb-0.005
 Teddy-0.005
 mummy-0.005
 Sister-0.005
 baby-0.005
Token small
Token ID1402
Feature activation+1.50e+00

Pos logit contributions
aw+0.062
aris+0.062
ues+0.059
ets+0.056
ount+0.056
Neg logit contributions
 thumb-0.034
 baby-0.030
 mummy-0.029
 Sister-0.026
 Teddy-0.025
Token voice
Token ID3809
Feature activation+5.36e+00

Pos logit contributions
aris+0.059
aw+0.057
ues+0.056
ount+0.054
eway+0.053
Neg logit contributions
 thumb-0.028
 baby-0.024
 mummy-0.022
 bunny-0.020
 Sister-0.019
Token replied
Token ID8712
Feature activation+1.62e+00

Pos logit contributions
aris+0.176
ues+0.159
aw+0.159
 facts+0.145
ari+0.145
Neg logit contributions
 thumb-0.117
 baby-0.105
 Teddy-0.102
 mummy-0.099
 helpless-0.094
Token.
Token ID13
Feature activation+6.41e-01

Pos logit contributions
aris+0.049
aw+0.048
ues+0.046
ari+0.043
oke+0.043
Neg logit contributions
 thumb-0.039
 Teddy-0.034
 mummy-0.033
 baby-0.032
 Sister-0.032
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
aw+0.022
aris+0.021
ues+0.020
 facts+0.019
ets+0.019
Neg logit contributions
 thumb-0.012
 Teddy-0.012
 Baby-0.011
 mummy-0.011
 Sister-0.010
Token
Token ID198
Feature activation-9.89e-01

Pos logit contributions
 thumb+0.003
 Teddy+0.003
 mummy+0.002
 Baby+0.002
 Sister+0.002
Neg logit contributions
aw-0.005
aris-0.005
ues-0.004
 facts-0.004
hatt-0.004
TokenTim
Token ID14967
Feature activation+4.51e-02

Pos logit contributions
 thumb+0.023
 Teddy+0.020
 mummy+0.019
 Sister+0.019
 baby+0.019
Neg logit contributions
aris-0.029
aw-0.028
ues-0.027
 facts-0.025
oke-0.025
Token young
Token ID1862
Feature activation-1.92e+00

Pos logit contributions
 thumb+0.001
 mummy+0.001
 baby+0.001
 Sister+0.001
 Teddy+0.001
Neg logit contributions
aris-0.001
aw-0.001
ues-0.001
hatt-0.001
oke-0.001
Token girl
Token ID2576
Feature activation+4.66e-01

Pos logit contributions
 thumb+0.046
 mummy+0.039
 Sister+0.039
 Teddy+0.038
 baby+0.038
Neg logit contributions
aw-0.055
aris-0.055
ues-0.052
lic-0.049
hatt-0.048
Token had
Token ID550
Feature activation-2.90e-01

Pos logit contributions
aris+0.014
aw+0.014
ues+0.014
lic+0.013
oke+0.013
Neg logit contributions
 thumb-0.011
 mummy-0.009
 Teddy-0.009
 baby-0.009
 Sister-0.008
Token caught
Token ID4978
Feature activation-4.98e-01

Pos logit contributions
 thumb+0.006
 mummy+0.005
 baby+0.005
 Teddy+0.005
 Sister+0.005
Neg logit contributions
aris-0.010
ues-0.009
aw-0.009
oke-0.009
hatt-0.008
Token a
Token ID257
Feature activation-6.36e-01

Pos logit contributions
 thumb+0.009
 mummy+0.007
 Sister+0.007
 Teddy+0.007
 baby+0.007
Neg logit contributions
aris-0.017
aw-0.017
ues-0.016
lic-0.015
oke-0.015
Token severe
Token ID6049
Feature activation-4.88e+00

Pos logit contributions
 thumb+0.014
 mummy+0.012
 Sister+0.012
 Teddy+0.012
 baby+0.011
Neg logit contributions
aw-0.019
aris-0.019
ues-0.018
lic-0.017
oke-0.017
Token case
Token ID1339
Feature activation-1.69e+00

Pos logit contributions
 thumb+0.116
 Teddy+0.105
 Sister+0.102
 mummy+0.101
 Midnight+0.094
Neg logit contributions
aw-0.122
aris-0.115
ues-0.110
bank-0.110
oke-0.108
Token of
Token ID286
Feature activation-5.18e-02

Pos logit contributions
 thumb+0.041
 Teddy+0.034
 mummy+0.034
 baby+0.033
 Sister+0.033
Neg logit contributions
aris-0.048
aw-0.048
ues-0.045
lic-0.043
hatt-0.043
Token hyp
Token ID5328
Feature activation-8.06e-01

Pos logit contributions
 thumb+0.001
 mummy+0.001
 Sister+0.001
 Teddy+0.001
 baby+0.001
Neg logit contributions
aw-0.002
aris-0.002
ues-0.001
lic-0.001
oke-0.001
Tokenother
Token ID847
Feature activation+1.51e-01

Pos logit contributions
 thumb+0.022
 Sister+0.019
 mummy+0.019
 Teddy+0.019
 baby+0.019
Neg logit contributions
aris-0.020
aw-0.020
ues-0.019
lic-0.018
oke-0.018
Tokenmia
Token ID20730
Feature activation-1.38e+00

Pos logit contributions
aw+0.005
aris+0.005
ues+0.004
lic+0.004
oke+0.004
Neg logit contributions
 thumb-0.003
 mummy-0.003
 Sister-0.003
 Teddy-0.003
 baby-0.003
Token so
Token ID523
Feature activation-4.13e-01

Pos logit contributions
 thumb+0.008
 Sister+0.007
 mummy+0.007
 Teddy+0.006
 baby+0.006
Neg logit contributions
aw-0.013
aris-0.012
ues-0.012
lic-0.012
hatt-0.011
Token grateful
Token ID14066
Feature activation+2.53e-01

Pos logit contributions
 thumb+0.010
 Sister+0.009
 Teddy+0.008
 mummy+0.008
 Ginny+0.008
Neg logit contributions
aw-0.012
aris-0.011
ues-0.010
lic-0.010
oke-0.010
Token that
Token ID326
Feature activation-1.29e+00

Pos logit contributions
aris+0.009
ues+0.009
aw+0.008
lic+0.008
hatt+0.008
Neg logit contributions
 thumb-0.005
 mummy-0.004
 Teddy-0.004
 Sister-0.004
 baby-0.004
Token he
Token ID339
Feature activation-7.65e-01

Pos logit contributions
 thumb+0.028
 mummy+0.025
 Teddy+0.024
 baby+0.023
 Sister+0.023
Neg logit contributions
aris-0.042
aw-0.042
ues-0.040
lic-0.038
oke-0.037
Token became
Token ID2627
Feature activation+7.42e-02

Pos logit contributions
 thumb+0.019
 mummy+0.016
 Sister+0.016
 Teddy+0.016
 baby+0.016
Neg logit contributions
aw-0.021
aris-0.021
ues-0.019
lic-0.018
oke-0.018
Token Teddy
Token ID29345
Feature activation-4.85e+00

Pos logit contributions
aw+0.002
aris+0.002
ues+0.002
lic+0.002
oke+0.002
Neg logit contributions
 thumb-0.002
 mummy-0.001
 Sister-0.001
 Teddy-0.001
 baby-0.001
Token's
Token ID338
Feature activation-1.76e+00

Pos logit contributions
 thumb+0.116
 Sister+0.103
 mummy+0.101
 Ginny+0.100
 Baby+0.099
Neg logit contributions
aw-0.126
aris-0.121
ues-0.112
oke-0.109
ari-0.108
Token friend
Token ID1545
Feature activation-2.09e+00

Pos logit contributions
 thumb+0.036
 Sister+0.033
 Ginny+0.032
 Baby+0.032
 Teddy+0.031
Neg logit contributions
aris-0.047
aw-0.046
hatt-0.044
ues-0.042
ari-0.042
Token and
Token ID290
Feature activation-2.91e-02

Pos logit contributions
 thumb+0.051
 mummy+0.043
 Teddy+0.043
 Sister+0.043
 baby+0.042
Neg logit contributions
aw-0.059
aris-0.059
ues-0.056
lic-0.053
hatt-0.052
Token they
Token ID484
Feature activation-1.85e+00

Pos logit contributions
 thumb+0.001
 mummy+0.001
 Teddy+0.001
 baby+0.001
 Sister+0.001
Neg logit contributions
aris-0.001
aw-0.001
ues-0.001
oke-0.001
lic-0.001
Token played
Token ID2826
Feature activation-1.06e+00

Pos logit contributions
 thumb+0.041
 mummy+0.034
 Teddy+0.034
 Sister+0.033
 baby+0.033
Neg logit contributions
aris-0.058
aw-0.057
ues-0.055
oke-0.052
lic-0.052
Token cry
Token ID3960
Feature activation-1.78e+00

Pos logit contributions
 thumb+0.035
 Sister+0.030
 Teddy+0.029
 mummy+0.028
 Ginny+0.028
Neg logit contributions
aw-0.060
aris-0.059
ues-0.056
hatt-0.053
lic-0.052
Token.
Token ID13
Feature activation+1.91e-01

Pos logit contributions
 thumb+0.052
 Sister+0.046
 mummy+0.046
 Teddy+0.044
 Baby+0.044
Neg logit contributions
aw-0.041
aris-0.039
ues-0.038
lic-0.035
oke-0.034
Token Lily
Token ID20037
Feature activation-1.31e+00

Pos logit contributions
aw+0.006
aris+0.005
ues+0.005
lic+0.005
oke+0.005
Neg logit contributions
 thumb-0.005
 mummy-0.004
 Sister-0.004
 Teddy-0.004
 baby-0.004
Token was
Token ID373
Feature activation+5.78e-02

Pos logit contributions
 thumb+0.035
 Sister+0.031
 mummy+0.031
 Ginny+0.030
 Baby+0.030
Neg logit contributions
aw-0.034
aris-0.030
lic-0.029
ues-0.028
oke-0.027
Token holding
Token ID4769
Feature activation-8.31e-01

Pos logit contributions
aw+0.002
aris+0.002
ues+0.002
lic+0.002
oke+0.002
Neg logit contributions
 thumb-0.001
 Sister-0.001
 mummy-0.001
 Teddy-0.001
 Baby-0.001
Token Ruby
Token ID10888
Feature activation-4.57e+00

Pos logit contributions
 thumb+0.019
 Sister+0.018
ivery+0.017
 sudden+0.017
Baby+0.016
Neg logit contributions
aw-0.022
ks-0.019
aris-0.018
ues-0.017
osh-0.016
Token and
Token ID290
Feature activation-7.67e-01

Pos logit contributions
 Sister+0.108
 thumb+0.105
 Ginny+0.102
 Baby+0.099
 mummy+0.099
Neg logit contributions
aw-0.110
aris-0.103
ks-0.103
ues-0.100
adow-0.093
Token laughing
Token ID14376
Feature activation-6.70e-02

Pos logit contributions
 thumb+0.016
 Sister+0.013
 mummy+0.012
 Teddy+0.012
 baby+0.012
Neg logit contributions
aw-0.024
aris-0.024
ues-0.023
lic-0.022
hatt-0.022
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
 thumb+0.002
 Teddy+0.001
 baby+0.001
 mummy+0.001
 Sister+0.001
Neg logit contributions
aris-0.002
aw-0.002
ues-0.002
oke-0.002
hatt-0.002
Token She
Token ID1375
Feature activation+2.43e-02

Pos logit contributions
aw+0.004
aris+0.004
ues+0.004
lic+0.004
oke+0.004
Neg logit contributions
 thumb-0.003
 Sister-0.002
 mummy-0.002
 Teddy-0.002
 baby-0.002
Token had
Token ID550
Feature activation+5.23e-01

Pos logit contributions
aw+0.001
aris+0.001
ues+0.001
lic+0.001
oke+0.001
Neg logit contributions
 thumb-0.001
 mummy-0.001
 Sister-0.001
 Teddy-0.001
 baby-0.001
Token Lily
Token ID20037
Feature activation-1.71e+00

Pos logit contributions
aris+0.001
aw+0.001
ues+0.001
oke+0.001
hatt+0.001
Neg logit contributions
 thumb-0.001
 Sister-0.001
 mummy-0.001
 Ginny-0.001
 baby-0.001
Token made
Token ID925
Feature activation+2.00e-01

Pos logit contributions
 thumb+0.044
 mummy+0.038
 Sister+0.038
 Baby+0.037
 baby+0.037
Neg logit contributions
aw-0.046
aris-0.044
ues-0.040
oke-0.039
lic-0.038
Token sure
Token ID1654
Feature activation-1.20e+00

Pos logit contributions
aw+0.006
aris+0.006
ues+0.006
lic+0.006
hatt+0.006
Neg logit contributions
 thumb-0.004
 mummy-0.004
 Sister-0.004
 Teddy-0.003
 baby-0.003
Token she
Token ID673
Feature activation+7.35e-01

Pos logit contributions
 thumb+0.033
 Teddy+0.030
 mummy+0.029
 baby+0.029
 Sister+0.029
Neg logit contributions
aw-0.030
aris-0.030
ues-0.029
lic-0.027
oke-0.026
Token held
Token ID2714
Feature activation-5.24e-01

Pos logit contributions
aw+0.019
aris+0.018
ues+0.017
lic+0.016
hatt+0.016
Neg logit contributions
 thumb-0.020
 Sister-0.017
 mummy-0.017
 baby-0.017
 Baby-0.017
Token Max
Token ID5436
Feature activation-4.54e+00

Pos logit contributions
 thumb+0.013
 Sister+0.010
 mummy+0.010
 Baby+0.010
 sudden+0.010
Neg logit contributions
aw-0.014
aris-0.013
ks-0.012
ues-0.011
hatt-0.011
Token's
Token ID338
Feature activation-1.70e+00

Pos logit contributions
 thumb+0.101
 Sister+0.093
 mummy+0.088
 Baby+0.086
 Ginny+0.084
Neg logit contributions
aw-0.129
aris-0.127
ues-0.116
ks-0.110
arium-0.108
Token handle
Token ID5412
Feature activation-1.20e+00

Pos logit contributions
 thumb+0.027
 Sister+0.027
 Baby+0.026
 Teddy+0.025
 Ginny+0.025
Neg logit contributions
aw-0.052
aris-0.051
hatt-0.048
 mate-0.047
ari-0.046
Token tightly
Token ID17707
Feature activation-3.29e+00

Pos logit contributions
 thumb+0.028
 Sister+0.025
 mummy+0.023
 Ginny+0.023
 Baby+0.023
Neg logit contributions
aw-0.035
aris-0.034
ues-0.032
hatt-0.030
ari-0.029
Token so
Token ID523
Feature activation+9.92e-01

Pos logit contributions
 thumb+0.083
 Sister+0.076
 mummy+0.072
 Ginny+0.070
 Baby+0.070
Neg logit contributions
aw-0.086
aris-0.084
ues-0.077
ks-0.071
eway-0.071
Token he
Token ID339
Feature activation+2.41e-01

Pos logit contributions
aw+0.027
aris+0.025
ues+0.023
hatt+0.022
oke+0.022
Neg logit contributions
 thumb-0.027
 Sister-0.023
 mummy-0.022
 baby-0.022
 Teddy-0.021
Token,
Token ID11
Feature activation-8.41e-01

Pos logit contributions
 thumb+0.019
 mummy+0.015
 Sister+0.015
 Teddy+0.015
 baby+0.015
Neg logit contributions
aw-0.029
aris-0.028
ues-0.027
lic-0.025
oke-0.025
Token the
Token ID262
Feature activation-1.28e+00

Pos logit contributions
 thumb+0.016
 mummy+0.013
 Sister+0.013
 Teddy+0.013
 baby+0.013
Neg logit contributions
aw-0.028
aris-0.028
ues-0.027
lic-0.025
oke-0.025
Token sea
Token ID5417
Feature activation+2.81e-01

Pos logit contributions
 thumb+0.031
 Sister+0.026
 mummy+0.026
 Teddy+0.026
 baby+0.025
Neg logit contributions
aw-0.037
aris-0.036
ues-0.034
lic-0.032
hatt-0.032
Token became
Token ID2627
Feature activation-3.09e+00

Pos logit contributions
aris+0.010
ues+0.009
aw+0.009
rets+0.009
ount+0.009
Neg logit contributions
 thumb-0.005
 mummy-0.005
 baby-0.004
 Teddy-0.004
 helpless-0.004
Token cho
Token ID1727
Feature activation+1.32e+00

Pos logit contributions
 thumb+0.065
 Sister+0.053
 Teddy+0.052
 mummy+0.052
 baby+0.049
Neg logit contributions
aw-0.098
aris-0.095
ues-0.089
lic-0.087
hatt-0.085
Tokenppy
Token ID14097
Feature activation-4.51e+00

Pos logit contributions
aw+0.031
aris+0.030
ues+0.029
 facts+0.028
hatt+0.027
Neg logit contributions
 thumb-0.038
 Teddy-0.033
 Sister-0.033
 mummy-0.031
 baby-0.031
Token and
Token ID290
Feature activation-1.64e+00

Pos logit contributions
 thumb+0.096
 mummy+0.078
 baby+0.077
 Teddy+0.076
 Sister+0.074
Neg logit contributions
aris-0.143
aw-0.143
ues-0.136
lic-0.131
hatt-0.129
Token it
Token ID340
Feature activation-1.78e+00

Pos logit contributions
 thumb+0.034
 mummy+0.027
 Teddy+0.027
 Sister+0.027
 baby+0.027
Neg logit contributions
aw-0.054
aris-0.053
ues-0.051
oke-0.048
lic-0.048
Token started
Token ID2067
Feature activation-2.24e+00

Pos logit contributions
 thumb+0.034
 Teddy+0.028
 baby+0.028
 mummy+0.028
 scrap+0.026
Neg logit contributions
aris-0.060
ues-0.059
aw-0.057
oke-0.054
 facts-0.054
Token to
Token ID284
Feature activation-1.35e+00

Pos logit contributions
 thumb+0.058
 baby+0.051
 Teddy+0.050
 mummy+0.050
 Sister+0.048
Neg logit contributions
aw-0.061
aris-0.060
ues-0.058
oke-0.055
lic-0.053
Token rain
Token ID6290
Feature activation-8.75e-02

Pos logit contributions
 thumb+0.031
 mummy+0.026
 Teddy+0.026
 baby+0.025
 Sister+0.025
Neg logit contributions
aris-0.041
aw-0.041
ues-0.039
oke-0.036
lic-0.036
Token on
Token ID319
Feature activation-1.08e+00

Pos logit contributions
 thumb+0.032
 Sister+0.026
 Teddy+0.024
 mummy+0.024
 poppy+0.024
Neg logit contributions
aw-0.033
aris-0.031
br-0.030
oke-0.028
lic-0.028
Token,
Token ID11
Feature activation-9.00e-02

Pos logit contributions
 thumb+0.031
 Sister+0.025
 infected+0.024
 Teddy+0.024
 mummy+0.024
Neg logit contributions
aris-0.025
aw-0.025
ues-0.023
oke-0.022
arium-0.022
Token the
Token ID262
Feature activation+1.46e-01

Pos logit contributions
 thumb+0.002
 Sister+0.002
 mummy+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aris-0.003
aw-0.003
ues-0.003
oke-0.002
hatt-0.002
Token diamond
Token ID15291
Feature activation-3.64e-01

Pos logit contributions
aw+0.003
 contest+0.003
hatt+0.003
aris+0.003
 circus+0.003
Neg logit contributions
 Sister-0.003
 thumb-0.003
 infected-0.003
 Ginny-0.003
 Cathy-0.003
Token became
Token ID2627
Feature activation-1.56e+00

Pos logit contributions
 thumb+0.008
 mummy+0.007
 Teddy+0.007
 baby+0.006
 Sister+0.006
Neg logit contributions
aris-0.011
aw-0.011
ues-0.011
lic-0.010
oke-0.010
Token Lucy
Token ID22162
Feature activation-4.50e+00

Pos logit contributions
 thumb+0.033
 Sister+0.026
 mummy+0.025
 Teddy+0.025
 Baby+0.024
Neg logit contributions
aw-0.050
aris-0.048
ues-0.045
lic-0.043
hatt-0.043
Token's
Token ID338
Feature activation-2.56e+00

Pos logit contributions
 thumb+0.107
 Sister+0.091
 mummy+0.091
 Ginny+0.090
 Baby+0.089
Neg logit contributions
aw-0.125
aris-0.123
ues-0.110
oke-0.109
ari-0.108
Token favorite
Token ID4004
Feature activation-9.51e-01

Pos logit contributions
 Sister+0.057
 thumb+0.056
 Midnight+0.054
 Cathy+0.054
 Ginny+0.054
Neg logit contributions
aris-0.063
aw-0.062
ari-0.055
hatt-0.055
ues-0.055
Token toy
Token ID13373
Feature activation-2.29e+00

Pos logit contributions
 thumb+0.026
 Sister+0.026
 Teddy+0.024
 infected+0.024
 Ginny+0.024
Neg logit contributions
aw-0.020
aris-0.019
ues-0.017
 facts-0.017
eway-0.016
Token to
Token ID284
Feature activation-8.70e-01

Pos logit contributions
 thumb+0.056
 Sister+0.049
 mummy+0.046
 Baby+0.046
 Teddy+0.046
Neg logit contributions
aw-0.064
aris-0.062
ues-0.057
oke-0.054
ari-0.054
Token play
Token ID711
Feature activation-4.55e-01

Pos logit contributions
 thumb+0.022
 mummy+0.019
 Sister+0.019
 Teddy+0.018
 baby+0.018
Neg logit contributions
aw-0.024
aris-0.024
ues-0.023
lic-0.021
oke-0.021
Token Bob
Token ID5811
Feature activation-3.02e+00

Pos logit contributions
 thumb+0.010
 mummy+0.008
 Teddy+0.008
 Sister+0.008
 baby+0.008
Neg logit contributions
aw-0.018
aris-0.018
ues-0.017
lic-0.016
oke-0.016
Token,
Token ID11
Feature activation-5.30e-01

Pos logit contributions
 thumb+0.082
 Sister+0.071
 mummy+0.071
 Teddy+0.068
 Ginny+0.068
Neg logit contributions
aw-0.075
aris-0.073
ues-0.066
oke-0.064
lic-0.062
Token her
Token ID607
Feature activation-4.40e-01

Pos logit contributions
 thumb+0.011
 mummy+0.009
 Sister+0.009
 Teddy+0.009
 baby+0.009
Neg logit contributions
aw-0.017
aris-0.017
ues-0.016
lic-0.015
oke-0.015
Token ball
Token ID2613
Feature activation-2.10e+00

Pos logit contributions
 thumb+0.009
 mummy+0.008
 baby+0.008
 Teddy+0.008
 Sister+0.007
Neg logit contributions
aw-0.014
aris-0.014
ues-0.014
lic-0.013
hatt-0.013
Token was
Token ID373
Feature activation-9.05e-01

Pos logit contributions
 thumb+0.048
 Teddy+0.040
 mummy+0.040
 baby+0.039
 Sister+0.038
Neg logit contributions
aris-0.064
aw-0.063
ues-0.061
hatt-0.058
lic-0.057
Token Charlie
Token ID11526
Feature activation-4.48e+00

Pos logit contributions
 thumb+0.018
 mummy+0.014
 Teddy+0.014
 Sister+0.014
 baby+0.014
Neg logit contributions
aw-0.030
aris-0.030
ues-0.029
lic-0.027
oke-0.027
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
 thumb+0.129
 Sister+0.115
 mummy+0.112
 Teddy+0.109
 Ginny+0.109
Neg logit contributions
aw-0.100
aris-0.097
ues-0.088
oke-0.083
ks-0.081
Token her
Token ID607
Feature activation-1.21e+00

Pos logit contributions
 thumb+0.026
 Teddy+0.023
 mummy+0.023
 baby+0.022
 Sister+0.022
Neg logit contributions
aw-0.030
aris-0.030
ues-0.029
oke-0.026
lic-0.026
Token book
Token ID1492
Feature activation-1.41e+00

Pos logit contributions
 thumb+0.026
 mummy+0.022
 baby+0.021
 Teddy+0.021
 Sister+0.021
Neg logit contributions
aw-0.039
aris-0.038
ues-0.037
lic-0.035
oke-0.035
Token was
Token ID373
Feature activation-9.22e-01

Pos logit contributions
 thumb+0.029
 Teddy+0.025
 mummy+0.024
 tightly+0.023
 baby+0.023
Neg logit contributions
aw-0.044
aris-0.044
ues-0.044
oke-0.042
hatt-0.042
Token Dave
Token ID9935
Feature activation-2.59e+00

Pos logit contributions
 thumb+0.018
 Teddy+0.015
 mummy+0.015
 Sister+0.014
 baby+0.014
Neg logit contributions
aris-0.031
aw-0.031
ues-0.029
oke-0.028
hatt-0.028
Token
Token ID198
Feature activation-4.32e-01

Pos logit contributions
aw+0.008
aris+0.008
ues+0.008
lic+0.007
oke+0.007
Neg logit contributions
 thumb-0.008
 mummy-0.007
 Sister-0.006
 Teddy-0.006
 baby-0.006
TokenThe
Token ID464
Feature activation-9.71e-01

Pos logit contributions
 thumb+0.008
 mummy+0.006
 Sister+0.006
 Teddy+0.006
 baby+0.006
Neg logit contributions
aris-0.015
aw-0.015
ues-0.014
oke-0.013
lic-0.013
Token boy
Token ID2933
Feature activation+5.78e-01

Pos logit contributions
 thumb+0.017
 Teddy+0.016
 Ginny+0.016
 Junior+0.015
bing+0.015
Neg logit contributions
aw-0.027
hatt-0.025
 contest-0.025
 ranger-0.024
 worker-0.024
Token and
Token ID290
Feature activation-2.24e+00

Pos logit contributions
aris+0.018
aw+0.018
ues+0.017
lic+0.016
hatt+0.016
Neg logit contributions
 thumb-0.013
 mummy-0.011
 Teddy-0.010
 Sister-0.010
 baby-0.010
Token his
Token ID465
Feature activation-1.85e+00

Pos logit contributions
 thumb+0.045
 mummy+0.038
 infected+0.037
 Teddy+0.037
 Sister+0.036
Neg logit contributions
aw-0.066
aris-0.064
hatt-0.058
ues-0.058
oke-0.057
Token little
Token ID1310
Feature activation-4.47e+00

Pos logit contributions
 thumb+0.037
 Teddy+0.032
 infected+0.032
 Baby+0.031
 Sister+0.031
Neg logit contributions
aw-0.054
aris-0.053
ari-0.048
ues-0.047
 facts-0.046
Token friend
Token ID1545
Feature activation-6.25e-01

Pos logit contributions
 thumb+0.088
 Teddy+0.075
 mummy+0.073
 Sister+0.073
 Ginny+0.070
Neg logit contributions
aw-0.141
aris-0.136
ues-0.125
hatt-0.122
oke-0.120
Token were
Token ID547
Feature activation-4.80e-01

Pos logit contributions
 thumb+0.015
 mummy+0.013
 Teddy+0.012
 Sister+0.012
 baby+0.012
Neg logit contributions
aris-0.018
aw-0.018
ues-0.017
lic-0.016
hatt-0.016
Token always
Token ID1464
Feature activation-8.65e-01

Pos logit contributions
 thumb+0.008
 mummy+0.006
 baby+0.006
 Sister+0.006
 Teddy+0.006
Neg logit contributions
aris-0.017
aw-0.017
ues-0.017
lic-0.016
hatt-0.016
Token together
Token ID1978
Feature activation-6.09e-01

Pos logit contributions
 thumb+0.019
 mummy+0.016
 baby+0.016
 Sister+0.015
 Teddy+0.015
Neg logit contributions
aw-0.027
aris-0.027
ues-0.026
hatt-0.024
lic-0.024
Token and
Token ID290
Feature activation-1.06e-01

Pos logit contributions
 thumb+0.012
 mummy+0.010
 baby+0.010
 Teddy+0.010
 Sister+0.009
Neg logit contributions
aw-0.020
aris-0.019
ues-0.019
hatt-0.019
lic-0.019
Token ran
Token ID4966
Feature activation-9.34e-02

Pos logit contributions
aris+0.027
ues+0.025
aw+0.025
eway+0.025
ount+0.023
Neg logit contributions
 thumb-0.019
 mummy-0.016
 Teddy-0.015
 baby-0.015
 Sister-0.015
Token to
Token ID284
Feature activation-6.86e-01

Pos logit contributions
 thumb+0.002
 Teddy+0.002
 baby+0.002
 tightly+0.002
 mummy+0.002
Neg logit contributions
aw-0.003
aris-0.003
ues-0.003
oke-0.003
lic-0.002
Token Lily
Token ID20037
Feature activation-8.41e-01

Pos logit contributions
 thumb+0.015
 Sister+0.013
 infected+0.012
 Baby+0.011
 mummy+0.011
Neg logit contributions
aris-0.019
ues-0.018
aw-0.018
arium-0.017
hatt-0.017
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
 thumb+0.017
 mummy+0.014
 Teddy+0.014
 Sister+0.014
 baby+0.014
Neg logit contributions
aw-0.027
aris-0.027
ues-0.026
lic-0.024
oke-0.024
Token snatched
Token ID43276
Feature activation+6.69e-01

Pos logit contributions
aris+0.028
aw+0.028
ues+0.026
eway+0.025
oke+0.024
Neg logit contributions
 thumb-0.026
 Teddy-0.023
 mummy-0.022
 Sister-0.022
 baby-0.022
Token Ruby
Token ID10888
Feature activation-4.45e+00

Pos logit contributions
aw+0.020
aris+0.018
ues+0.017
ks+0.017
hatt+0.016
Neg logit contributions
 thumb-0.015
 Sister-0.013
 mummy-0.012
bing-0.012
 injured-0.011
Token from
Token ID422
Feature activation-9.09e-01

Pos logit contributions
 thumb+0.102
 Sister+0.096
 mummy+0.092
 Baby+0.090
 Teddy+0.089
Neg logit contributions
aw-0.122
aris-0.116
ues-0.111
ks-0.103
hatt-0.101
Token her
Token ID607
Feature activation-7.77e-01

Pos logit contributions
 thumb+0.023
 Sister+0.019
 ankle+0.018
 infected+0.017
 severe+0.017
Neg logit contributions
aw-0.021
aris-0.020
ks-0.020
arium-0.020
ues-0.020
Token hands
Token ID2832
Feature activation-2.93e+00

Pos logit contributions
 thumb+0.015
 Sister+0.013
 mummy+0.012
 Teddy+0.012
 baby+0.012
Neg logit contributions
aw-0.025
aris-0.025
ues-0.024
oke-0.023
hatt-0.023
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
 thumb+0.086
 Sister+0.078
 mummy+0.078
 Ginny+0.076
 Baby+0.074
Neg logit contributions
aw-0.065
aris-0.060
ues-0.056
oke-0.051
ks-0.051
Token She
Token ID1375
Feature activation+3.74e-01

Pos logit contributions
 thumb+0.005
 Teddy+0.004
 mummy+0.004
 Sister+0.004
 baby+0.004
Neg logit contributions
aw-0.008
aris-0.008
ues-0.007
oke-0.007
lic-0.007
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
 thumb+0.011
 Sister+0.009
 mummy+0.009
 Teddy+0.009
 baby+0.009
Neg logit contributions
aw-0.013
aris-0.012
ues-0.012
lic-0.011
hatt-0.011
Token Lily
Token ID20037
Feature activation-1.70e+00

Pos logit contributions
 thumb+0.004
 Teddy+0.004
 mummy+0.004
 Sister+0.004
 baby+0.004
Neg logit contributions
aw-0.006
aris-0.006
ues-0.006
oke-0.005
eway-0.005
Token laughed
Token ID13818
Feature activation-1.44e+00

Pos logit contributions
 thumb+0.044
 Sister+0.037
 mummy+0.037
 Teddy+0.036
 Ginny+0.036
Neg logit contributions
aw-0.045
aris-0.043
ues-0.040
lic-0.039
oke-0.039
Token and
Token ID290
Feature activation+3.78e-01

Pos logit contributions
 thumb+0.033
 Sister+0.028
 mummy+0.027
 Baby+0.026
 Ginny+0.026
Neg logit contributions
aw-0.044
aris-0.041
ues-0.039
lic-0.037
hatt-0.036
Token hugged
Token ID41130
Feature activation-1.74e+00

Pos logit contributions
aw+0.009
aris+0.009
ues+0.008
lic+0.008
hatt+0.008
Neg logit contributions
 thumb-0.011
 mummy-0.009
 Sister-0.009
 baby-0.009
 Teddy-0.009
Token Max
Token ID5436
Feature activation-4.43e+00

Pos logit contributions
 thumb+0.048
 Ginny+0.038
 infected+0.037
 Sister+0.037
 poppy+0.037
Neg logit contributions
aw-0.044
aris-0.039
ues-0.037
ks-0.035
 facts-0.034
Token.
Token ID13
Feature activation-3.74e-01

Pos logit contributions
 thumb+0.125
 Sister+0.113
 Ginny+0.109
 Baby+0.107
 mummy+0.106
Neg logit contributions
aw-0.100
aris-0.097
ues-0.088
ks-0.085
ari-0.078
Token Then
Token ID3244
Feature activation-1.73e+00

Pos logit contributions
 thumb+0.011
 baby+0.008
 mummy+0.008
 Ginny+0.008
 Sister+0.008
Neg logit contributions
aris-0.009
aw-0.009
ues-0.008
hatt-0.008
lic-0.008
Token,
Token ID11
Feature activation-2.86e-01

Pos logit contributions
 thumb+0.048
 Sister+0.040
 Ginny+0.040
 injured+0.039
 infected+0.038
Neg logit contributions
aw-0.040
aris-0.038
ues-0.036
hatt-0.033
oke-0.032
Token they
Token ID484
Feature activation-1.59e+00

Pos logit contributions
 thumb+0.007
 Sister+0.006
 mummy+0.006
 Teddy+0.006
 baby+0.005
Neg logit contributions
aw-0.008
aris-0.008
ues-0.008
lic-0.007
hatt-0.007
Token all
Token ID477
Feature activation-1.64e-01

Pos logit contributions
 thumb+0.040
 Sister+0.034
 mummy+0.034
 Teddy+0.034
 baby+0.033
Neg logit contributions
aw-0.044
aris-0.043
ues-0.040
lic-0.038
hatt-0.038
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
aw+0.044
aris+0.044
ues+0.041
lic+0.039
hatt+0.039
Neg logit contributions
 thumb-0.045
 mummy-0.039
 Teddy-0.038
 Sister-0.038
 baby-0.038
Token They
Token ID1119
Feature activation-9.68e-01

Pos logit contributions
aw+0.007
aris+0.007
ues+0.006
oke+0.006
lic+0.006
Neg logit contributions
 thumb-0.005
 Teddy-0.005
 mummy-0.005
 Sister-0.005
 Baby-0.005
Token got
Token ID1392
Feature activation+2.43e-02

Pos logit contributions
 thumb+0.025
 mummy+0.022
 Sister+0.021
 Teddy+0.021
 baby+0.021
Neg logit contributions
aw-0.026
aris-0.026
ues-0.024
lic-0.022
oke-0.022
Token their
Token ID511
Feature activation-1.27e+00

Pos logit contributions
aw+0.001
aris+0.001
ues+0.001
lic+0.001
oke+0.001
Neg logit contributions
 thumb-0.000
 mummy-0.000
 Sister-0.000
 Teddy-0.000
 baby-0.000
Token back
Token ID736
Feature activation-1.29e+00

Pos logit contributions
 thumb+0.030
 Sister+0.025
 mummy+0.025
 Teddy+0.025
 baby+0.024
Neg logit contributions
aris-0.037
aw-0.037
ues-0.035
hatt-0.033
lic-0.032
Tokenpacks
Token ID32377
Feature activation-4.42e+00

Pos logit contributions
 thumb+0.030
 mummy+0.025
 Teddy+0.025
 Sister+0.025
 baby+0.024
Neg logit contributions
aw-0.038
aris-0.038
ues-0.036
lic-0.034
oke-0.034
Token from
Token ID422
Feature activation-1.22e+00

Pos logit contributions
 thumb+0.097
 Sister+0.081
 mummy+0.080
 Teddy+0.078
 baby+0.077
Neg logit contributions
aw-0.135
aris-0.135
ues-0.126
hatt-0.118
ari-0.117
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
 thumb+0.027
 Sister+0.021
 Teddy+0.021
 mummy+0.021
 Ginny+0.020
Neg logit contributions
aw-0.037
aris-0.035
ues-0.034
hatt-0.032
arium-0.032
Token trunk
Token ID21427
Feature activation-4.63e-01

Pos logit contributions
aris+0.032
aw+0.032
ues+0.031
lic+0.029
oke+0.028
Neg logit contributions
 thumb-0.030
 baby-0.026
 mummy-0.026
 Teddy-0.025
 Sister-0.025
Token.
Token ID13
Feature activation+8.49e-02

Pos logit contributions
 thumb+0.009
 tightly+0.007
 baby+0.007
 arm+0.007
 mummy+0.007
Neg logit contributions
aris-0.015
aw-0.015
ues-0.015
lic-0.015
hatt-0.014
Token They
Token ID1119
Feature activation-1.18e+00

Pos logit contributions
aw+0.002
aris+0.002
ues+0.002
oke+0.002
lic+0.002
Neg logit contributions
 thumb-0.002
 Teddy-0.002
 Sister-0.002
 mummy-0.002
 Baby-0.002
Token shoulder
Token ID8163
Feature activation-2.52e-01

Pos logit contributions
 Sister+0.020
 infected+0.019
 thumb+0.018
 Baby+0.018
 Midnight+0.018
Neg logit contributions
aris-0.028
aw-0.026
 tour-0.025
ia-0.025
 mate-0.025
Token.
Token ID13
Feature activation+5.86e-01

Pos logit contributions
 thumb+0.006
 mummy+0.005
 Teddy+0.005
 baby+0.005
 Sister+0.005
Neg logit contributions
aw-0.008
aris-0.007
ues-0.007
oke-0.007
hatt-0.007
Token He
Token ID679
Feature activation+3.26e-01

Pos logit contributions
aw+0.019
aris+0.019
ues+0.018
hatt+0.017
 facts+0.017
Neg logit contributions
 thumb-0.011
 Teddy-0.011
 mummy-0.010
 Sister-0.010
 Baby-0.010
Token felt
Token ID2936
Feature activation+1.39e-01

Pos logit contributions
aris+0.010
aw+0.010
ues+0.009
oke+0.009
hatt+0.009
Neg logit contributions
 thumb-0.007
 mummy-0.006
 Teddy-0.006
 baby-0.006
 Sister-0.006
Token their
Token ID511
Feature activation-1.95e+00

Pos logit contributions
aw+0.005
aris+0.005
ues+0.004
lic+0.004
hatt+0.004
Neg logit contributions
 thumb-0.003
 Sister-0.002
 mummy-0.002
 Teddy-0.002
 baby-0.002
Token little
Token ID1310
Feature activation-4.42e+00

Pos logit contributions
 thumb+0.037
 Sister+0.031
 Teddy+0.030
 mummy+0.029
 Ginny+0.028
Neg logit contributions
aw-0.063
aris-0.063
ues-0.060
hatt-0.057
eway-0.056
Token hands
Token ID2832
Feature activation-2.20e+00

Pos logit contributions
 thumb+0.088
 Sister+0.074
 Teddy+0.074
 mummy+0.071
 Baby+0.068
Neg logit contributions
aw-0.140
aris-0.137
ues-0.130
hatt-0.122
oke-0.122
Token tick
Token ID4378
Feature activation-2.45e-01

Pos logit contributions
 thumb+0.049
 Sister+0.042
 mummy+0.041
 Teddy+0.040
 Ginny+0.039
Neg logit contributions
aw-0.065
aris-0.064
ues-0.061
lic-0.059
hatt-0.057
Tokenling
Token ID1359
Feature activation+4.83e-02

Pos logit contributions
 thumb+0.007
 mummy+0.007
 Sister+0.006
 baby+0.006
 Teddy+0.006
Neg logit contributions
aw-0.006
aris-0.005
ues-0.005
lic-0.005
oke-0.005
Token his
Token ID465
Feature activation-1.88e+00

Pos logit contributions
aris+0.002
aw+0.002
ues+0.002
oke+0.002
hatt+0.002
Neg logit contributions
 thumb-0.001
 mummy-0.001
 baby-0.001
 Teddy-0.001
 Sister-0.001
Token neck
Token ID7393
Feature activation-1.14e+00

Pos logit contributions
 Sister+0.034
 thumb+0.033
 Cathy+0.031
 Baby+0.030
 Ginny+0.030
Neg logit contributions
aw-0.057
aris-0.054
ues-0.052
ks-0.050
ows-0.049
Token loyal
Token ID9112
Feature activation-2.25e+00

Pos logit contributions
 thumb+0.036
 mummy+0.030
 Sister+0.030
 Teddy+0.029
 baby+0.029
Neg logit contributions
aw-0.045
aris-0.045
ues-0.043
lic-0.041
oke-0.040
Token dog
Token ID3290
Feature activation-1.82e+00

Pos logit contributions
 thumb+0.053
 baby+0.046
 mummy+0.045
 Sister+0.044
 Teddy+0.043
Neg logit contributions
aw-0.067
aris-0.066
ues-0.064
lic-0.062
oke-0.060
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
 thumb+0.046
 mummy+0.040
 Teddy+0.039
 Sister+0.039
 baby+0.039
Neg logit contributions
aw-0.050
aris-0.050
ues-0.047
lic-0.044
hatt-0.044
Token He
Token ID679
Feature activation-6.55e-02

Pos logit contributions
aw+0.005
aris+0.005
ues+0.005
lic+0.004
oke+0.004
Neg logit contributions
 thumb-0.004
 mummy-0.003
 Teddy-0.003
 Sister-0.003
 baby-0.003
Token hugged
Token ID41130
Feature activation-1.88e+00

Pos logit contributions
 thumb+0.002
 Sister+0.001
 mummy+0.001
 Teddy+0.001
 baby+0.001
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
lic-0.002
hatt-0.002
Token Max
Token ID5436
Feature activation-4.41e+00

Pos logit contributions
 thumb+0.048
 mummy+0.037
 Sister+0.037
 Ginny+0.037
 infected+0.036
Neg logit contributions
aw-0.050
aris-0.047
ues-0.044
hatt-0.042
lic-0.041
Token and
Token ID290
Feature activation+6.86e-01

Pos logit contributions
 thumb+0.108
 Sister+0.092
 Ginny+0.089
 mummy+0.088
 Baby+0.086
Neg logit contributions
aw-0.119
aris-0.113
ues-0.104
ari-0.100
arium-0.098
Token said
Token ID531
Feature activation+1.20e+00

Pos logit contributions
aris+0.018
aw+0.018
ues+0.017
lic+0.016
oke+0.016
Neg logit contributions
 thumb-0.018
 mummy-0.016
 Teddy-0.016
 Sister-0.016
 baby-0.015
Token,
Token ID11
Feature activation+7.53e-01

Pos logit contributions
aris+0.036
aw+0.036
ues+0.034
hatt+0.032
lic+0.031
Neg logit contributions
 thumb-0.028
 mummy-0.025
 Teddy-0.025
 baby-0.024
 Sister-0.023
Token "
Token ID366
Feature activation-6.10e-01

Pos logit contributions
aw+0.020
aris+0.019
ues+0.018
lic+0.016
hatt+0.016
Neg logit contributions
 thumb-0.021
 Teddy-0.018
 mummy-0.018
 Sister-0.018
 baby-0.018
TokenI
Token ID40
Feature activation+1.40e-01

Pos logit contributions
 thumb+0.014
 Sister+0.012
 mummy+0.012
 Teddy+0.012
 baby+0.012
Neg logit contributions
aris-0.018
aw-0.018
ues-0.017
oke-0.016
lic-0.016
Token happy
Token ID3772
Feature activation-9.20e-01

Pos logit contributions
 thumb+0.007
 Sister+0.006
 mummy+0.006
 Teddy+0.006
 Baby+0.005
Neg logit contributions
aw-0.008
aris-0.007
ues-0.007
lic-0.007
hatt-0.007
Token too
Token ID1165
Feature activation+6.48e-01

Pos logit contributions
 thumb+0.018
 Teddy+0.017
 mummy+0.016
 baby+0.015
 herself+0.014
Neg logit contributions
aris-0.032
aw-0.031
ues-0.030
lic-0.029
eway-0.029
Token.
Token ID13
Feature activation+7.04e-01

Pos logit contributions
aw+0.012
aris+0.010
oke+0.009
ues+0.009
ks+0.009
Neg logit contributions
 thumb-0.022
 Sister-0.020
 scrap-0.020
 Ginny-0.020
 mummy-0.019
Token She
Token ID1375
Feature activation-3.03e-01

Pos logit contributions
aris+0.020
aw+0.020
ues+0.018
lic+0.017
hatt+0.017
Neg logit contributions
 thumb-0.017
 mummy-0.014
 Sister-0.014
 baby-0.014
 Baby-0.014
Token hugged
Token ID41130
Feature activation-2.20e+00

Pos logit contributions
 thumb+0.007
 Teddy+0.006
 mummy+0.006
 Sister+0.006
 baby+0.006
Neg logit contributions
aris-0.009
aw-0.009
ues-0.008
eway-0.008
oke-0.008
Token Max
Token ID5436
Feature activation-4.40e+00

Pos logit contributions
 thumb+0.060
 Sister+0.050
 Ginny+0.049
 Baby+0.048
 mummy+0.048
Neg logit contributions
aw-0.054
aris-0.049
ues-0.043
ks-0.042
hatt-0.042
Token and
Token ID290
Feature activation+7.83e-01

Pos logit contributions
 thumb+0.102
 Sister+0.087
 mummy+0.085
 Ginny+0.083
 Baby+0.082
Neg logit contributions
aw-0.128
aris-0.124
ues-0.115
oke-0.107
ks-0.107
Token said
Token ID531
Feature activation+1.03e+00

Pos logit contributions
aris+0.021
aw+0.021
ues+0.019
lic+0.018
oke+0.018
Neg logit contributions
 thumb-0.021
 mummy-0.018
 Teddy-0.018
 Sister-0.018
 baby-0.018
Token,
Token ID11
Feature activation+1.09e+00

Pos logit contributions
aris+0.032
aw+0.032
ues+0.031
lic+0.029
hatt+0.029
Neg logit contributions
 thumb-0.022
 Teddy-0.019
 mummy-0.019
 baby-0.018
 Sister-0.018
Token "
Token ID366
Feature activation-6.45e-01

Pos logit contributions
aw+0.027
aris+0.027
ues+0.025
lic+0.023
hatt+0.023
Neg logit contributions
 thumb-0.031
 Teddy-0.027
 mummy-0.027
 Sister-0.026
 baby-0.026
TokenYou
Token ID1639
Feature activation+6.01e-01

Pos logit contributions
 thumb+0.016
 mummy+0.013
 Sister+0.013
 Teddy+0.013
 baby+0.013
Neg logit contributions
aw-0.019
aris-0.018
ues-0.017
lic-0.016
hatt-0.016
Token very
Token ID845
Feature activation-9.90e-01

Pos logit contributions
aris+0.004
aw+0.004
ues+0.004
oke+0.003
hatt+0.003
Neg logit contributions
 thumb-0.002
 baby-0.001
 mummy-0.001
 Teddy-0.001
 Sister-0.001
Token happy
Token ID3772
Feature activation-9.60e-01

Pos logit contributions
 thumb+0.014
 baby+0.014
 mummy+0.013
 helpless+0.012
 Sister+0.011
Neg logit contributions
aw-0.037
aris-0.037
ues-0.035
eway-0.035
hatt-0.033
Token.
Token ID13
Feature activation+3.78e-01

Pos logit contributions
 thumb+0.014
 mummy+0.012
 Teddy+0.012
 baby+0.011
 herself+0.011
Neg logit contributions
aris-0.037
lic-0.036
aw-0.036
ues-0.036
hatt-0.035
Token She
Token ID1375
Feature activation+1.86e-02

Pos logit contributions
aw+0.012
aris+0.012
ues+0.012
lic+0.011
oke+0.011
Neg logit contributions
 thumb-0.007
 Teddy-0.006
 mummy-0.006
 Sister-0.006
 Baby-0.006
Token holds
Token ID6622
Feature activation-1.27e+00

Pos logit contributions
aris+0.000
ues+0.000
aw+0.000
eway+0.000
lic+0.000
Neg logit contributions
 thumb-0.000
 Teddy-0.000
 mummy-0.000
 baby-0.000
 Sister-0.000
Token Daisy
Token ID40355
Feature activation-4.40e+00

Pos logit contributions
 thumb+0.027
 Sister+0.021
 mummy+0.020
 infected+0.020
 Teddy+0.020
Neg logit contributions
aw-0.040
aris-0.038
ues-0.036
ks-0.034
hatt-0.034
Token and
Token ID290
Feature activation-6.50e-01

Pos logit contributions
 thumb+0.102
 Sister+0.097
 Ginny+0.091
 mummy+0.090
 Baby+0.090
Neg logit contributions
aw-0.115
aris-0.113
ues-0.100
ks-0.097
arium-0.096
Token talks
Token ID6130
Feature activation+3.65e-01

Pos logit contributions
 thumb+0.016
 mummy+0.014
 Teddy+0.014
 Sister+0.014
 baby+0.014
Neg logit contributions
aris-0.018
aw-0.018
ues-0.018
lic-0.017
oke-0.017
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
oke+0.011
hatt+0.011
aris+0.011
cod+0.011
ues+0.011
Neg logit contributions
 thumb-0.007
 herself-0.007
 mummy-0.007
 Teddy-0.007
 tightly-0.006
Token her
Token ID607
Feature activation-1.50e+00

Pos logit contributions
 thumb+0.021
 mummy+0.018
 Sister+0.017
 Teddy+0.017
 baby+0.017
Neg logit contributions
aw-0.033
aris-0.033
ues-0.031
lic-0.030
oke-0.030
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
 thumb+0.033
 mummy+0.029
 baby+0.028
 Teddy+0.027
 Sister+0.027
Neg logit contributions
aw-0.046
aris-0.046
ues-0.044
lic-0.043
oke-0.042
Token am
Token ID716
Feature activation+7.68e-01

Pos logit contributions
aris+0.018
aw+0.017
ues+0.017
eway+0.016
oke+0.016
Neg logit contributions
 thumb-0.014
 Teddy-0.012
 baby-0.012
 mummy-0.012
 Sister-0.011
Token Sara
Token ID24799
Feature activation-2.07e+00

Pos logit contributions
aris+0.023
ues+0.023
aw+0.022
eway+0.021
hatt+0.021
Neg logit contributions
 thumb-0.017
 Teddy-0.016
 mummy-0.015
 baby-0.015
 Sister-0.015
Token.
Token ID13
Feature activation+3.78e-01

Pos logit contributions
 thumb+0.048
 mummy+0.040
 Sister+0.040
 Teddy+0.040
 baby+0.039
Neg logit contributions
aw-0.061
aris-0.061
ues-0.058
lic-0.054
hatt-0.054
Token This
Token ID770
Feature activation+7.39e-01

Pos logit contributions
aw+0.012
aris+0.011
ues+0.011
lic+0.010
eway+0.010
Neg logit contributions
 thumb-0.008
 Teddy-0.008
 mummy-0.007
 Sister-0.007
 baby-0.007
Token is
Token ID318
Feature activation-2.66e-01

Pos logit contributions
aw+0.016
aris+0.015
ues+0.013
hatt+0.013
lic+0.013
Neg logit contributions
 thumb-0.023
 mummy-0.021
 Sister-0.020
 Teddy-0.020
 Baby-0.020
Token Max
Token ID5436
Feature activation-4.39e+00

Pos logit contributions
 thumb+0.005
 Teddy+0.004
 mummy+0.004
 baby+0.004
 Sister+0.004
Neg logit contributions
aris-0.009
aw-0.009
ues-0.009
lic-0.008
oke-0.008
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
 thumb+0.119
 mummy+0.103
 Sister+0.103
 Teddy+0.101
 baby+0.099
Neg logit contributions
aw-0.113
aris-0.110
ues-0.103
oke-0.096
lic-0.096
Token He
Token ID679
Feature activation-5.85e-01

Pos logit contributions
aw+0.005
aris+0.005
ues+0.005
lic+0.005
oke+0.004
Neg logit contributions
 thumb-0.005
 Teddy-0.004
 mummy-0.004
 Sister-0.004
 baby-0.004
Token is
Token ID318
Feature activation+6.07e-01

Pos logit contributions
 thumb+0.015
 Teddy+0.014
 baby+0.013
 Sister+0.013
 mummy+0.013
Neg logit contributions
aris-0.016
ues-0.016
aw-0.015
eway-0.015
lic-0.014
Token my
Token ID616
Feature activation-1.70e+00

Pos logit contributions
aris+0.020
aw+0.020
ues+0.019
lic+0.018
oke+0.017
Neg logit contributions
 thumb-0.012
 Teddy-0.010
 mummy-0.010
 Sister-0.010
 baby-0.010
Token puppy
Token ID26188
Feature activation-3.33e+00

Pos logit contributions
 thumb+0.043
 Sister+0.037
bing+0.037
 infected+0.036
 Baby+0.036
Neg logit contributions
aris-0.043
aw-0.042
ari-0.037
 mate-0.036
ues-0.036
Token would
Token ID561
Feature activation-1.45e+00

Pos logit contributions
 thumb+0.072
 mummy+0.061
 Sister+0.059
 Ginny+0.058
bing+0.058
Neg logit contributions
aw-0.060
aris-0.056
ues-0.047
oke-0.047
ari-0.046
Token wear
Token ID5806
Feature activation-1.95e+00

Pos logit contributions
 thumb+0.039
 Sister+0.034
 mummy+0.033
 Teddy+0.033
 baby+0.032
Neg logit contributions
aw-0.036
aris-0.035
ues-0.034
hatt-0.031
lic-0.030
Token their
Token ID511
Feature activation-8.92e-01

Pos logit contributions
 thumb+0.055
 Sister+0.046
 mummy+0.046
 Ginny+0.044
 baby+0.044
Neg logit contributions
aw-0.049
aris-0.048
ues-0.044
lic-0.041
 facts-0.040
Token bath
Token ID7837
Feature activation-1.73e+00

Pos logit contributions
 thumb+0.022
 Ginny+0.020
 Cathy+0.019
 infected+0.019
 Sister+0.019
Neg logit contributions
aris-0.021
aw-0.020
ues-0.018
 facts-0.018
ag-0.018
Tokenro
Token ID305
Feature activation-7.46e-01

Pos logit contributions
 thumb+0.042
 Teddy+0.037
 mummy+0.037
 Sister+0.035
 baby+0.034
Neg logit contributions
aw-0.050
aris-0.048
ues-0.046
oke-0.045
hatt-0.044
Tokenbes
Token ID12636
Feature activation-4.39e+00

Pos logit contributions
 thumb+0.016
 Teddy+0.013
 mummy+0.012
 Sister+0.012
 baby+0.012
Neg logit contributions
aw-0.024
aris-0.024
oke-0.022
ues-0.022
hatt-0.021
Token together
Token ID1978
Feature activation-1.01e+00

Pos logit contributions
 thumb+0.098
 Teddy+0.084
 mummy+0.083
 Sister+0.080
 baby+0.079
Neg logit contributions
aw-0.130
aris-0.127
ues-0.125
oke-0.121
hatt-0.120
Token and
Token ID290
Feature activation+1.79e-01

Pos logit contributions
 thumb+0.021
 mummy+0.018
 Teddy+0.017
 baby+0.017
 Sister+0.017
Neg logit contributions
aw-0.032
aris-0.032
ues-0.031
lic-0.030
hatt-0.030
Token play
Token ID711
Feature activation-2.58e-01

Pos logit contributions
aw+0.005
aris+0.005
ues+0.005
lic+0.005
oke+0.005
Neg logit contributions
 thumb-0.004
 mummy-0.004
 Teddy-0.004
 Sister-0.004
 baby-0.004
Token games
Token ID1830
Feature activation-9.94e-01

Pos logit contributions
 thumb+0.007
 Teddy+0.006
 mummy+0.006
 baby+0.006
 Midnight+0.006
Neg logit contributions
aris-0.007
aw-0.006
oke-0.006
hatt-0.006
ues-0.006
Token.
Token ID13
Feature activation-9.21e-01

Pos logit contributions
 thumb+0.014
 Teddy+0.014
 both+0.014
 tightly+0.013
 herself+0.013
Neg logit contributions
hatt-0.034
oke-0.034
aw-0.033
lic-0.032
aris-0.032
Token and
Token ID290
Feature activation-1.81e-01

Pos logit contributions
 thumb+0.034
 mummy+0.028
 Teddy+0.028
 Sister+0.027
 baby+0.027
Neg logit contributions
aw-0.056
aris-0.056
ues-0.053
hatt-0.051
oke-0.051
Token found
Token ID1043
Feature activation+1.06e+00

Pos logit contributions
 thumb+0.004
 Teddy+0.004
 mummy+0.004
 Sister+0.004
 baby+0.004
Neg logit contributions
aw-0.005
aris-0.005
ues-0.005
oke-0.005
lic-0.005
Token the
Token ID262
Feature activation+8.54e-02

Pos logit contributions
aw+0.032
aris+0.031
ues+0.029
hatt+0.028
lic+0.028
Neg logit contributions
 thumb-0.024
 Sister-0.020
 mummy-0.019
 baby-0.019
 Teddy-0.018
Token candy
Token ID18550
Feature activation-2.49e+00

Pos logit contributions
aw+0.002
aris+0.002
ues+0.002
hatt+0.002
lic+0.002
Neg logit contributions
 thumb-0.002
 mummy-0.002
 Sister-0.002
 Teddy-0.002
 Baby-0.002
Token wra
Token ID7917
Feature activation-2.24e+00

Pos logit contributions
 thumb+0.056
 Teddy+0.047
 mummy+0.046
 baby+0.046
 Sister+0.044
Neg logit contributions
aris-0.076
aw-0.075
ues-0.071
lic-0.069
hatt-0.068
Tokenppers
Token ID11799
Feature activation-4.36e+00

Pos logit contributions
 thumb+0.062
 Sister+0.060
 mummy+0.058
 Ginny+0.057
 baby+0.056
Neg logit contributions
aris-0.053
ues-0.052
aw-0.052
ari-0.048
lic-0.047
Token.
Token ID13
Feature activation-2.57e-01

Pos logit contributions
 thumb+0.105
 Sister+0.089
 mummy+0.089
 Teddy+0.087
 baby+0.085
Neg logit contributions
aw-0.125
aris-0.123
ues-0.116
oke-0.108
lic-0.108
Token
Token ID198
Feature activation+4.09e-01

Pos logit contributions
 thumb+0.005
 Teddy+0.005
 mummy+0.005
 Sister+0.005
 Baby+0.004
Neg logit contributions
aw-0.008
aris-0.008
ues-0.008
oke-0.007
lic-0.007
Token
Token ID198
Feature activation-5.48e-01

Pos logit contributions
aw+0.012
aris+0.012
ues+0.011
oke+0.010
hatt+0.010
Neg logit contributions
 thumb-0.010
 Teddy-0.008
 mummy-0.008
 Sister-0.008
 baby-0.008
TokenL
Token ID43
Feature activation+5.49e-01

Pos logit contributions
 thumb+0.013
 Teddy+0.011
 mummy+0.011
 Sister+0.011
 baby+0.011
Neg logit contributions
aris-0.016
aw-0.016
ues-0.015
oke-0.014
 facts-0.014
Tokenily
Token ID813
Feature activation-1.03e+00

Pos logit contributions
aris+0.013
aw+0.012
ues+0.011
 skysc+0.011
hatt+0.011
Neg logit contributions
 thumb-0.016
 Teddy-0.014
 Sister-0.014
 mummy-0.014
 herself-0.014
Token the
Token ID262
Feature activation-8.44e-01

Pos logit contributions
 thumb+0.021
 Sister+0.017
 mummy+0.017
 Teddy+0.017
 baby+0.017
Neg logit contributions
aw-0.028
aris-0.028
ues-0.026
hatt-0.025
lic-0.025
Token water
Token ID1660
Feature activation-7.66e-01

Pos logit contributions
 thumb+0.020
 Teddy+0.018
 Sister+0.017
 mummy+0.017
 baby+0.017
Neg logit contributions
aw-0.024
aris-0.023
ues-0.022
hatt-0.021
oke-0.020
Token was
Token ID373
Feature activation-1.60e+00

Pos logit contributions
 thumb+0.017
 mummy+0.014
 Teddy+0.014
 Sister+0.014
 baby+0.014
Neg logit contributions
aris-0.024
aw-0.024
ues-0.023
lic-0.021
hatt-0.021
Token getting
Token ID1972
Feature activation-2.42e+00

Pos logit contributions
 thumb+0.033
 Sister+0.027
 mummy+0.027
 Teddy+0.026
 baby+0.026
Neg logit contributions
aw-0.051
aris-0.051
ues-0.049
lic-0.046
hatt-0.046
Token cho
Token ID1727
Feature activation+1.34e+00

Pos logit contributions
 thumb+0.055
 Sister+0.046
 mummy+0.044
 Teddy+0.044
 Midnight+0.043
Neg logit contributions
aw-0.071
aris-0.068
ues-0.066
lic-0.064
hatt-0.061
Tokenppy
Token ID14097
Feature activation-4.35e+00

Pos logit contributions
aw+0.033
aris+0.032
ues+0.031
hatt+0.029
 facts+0.028
Neg logit contributions
 thumb-0.037
 Teddy-0.032
 Sister-0.032
 mummy-0.031
 baby-0.030
Token.
Token ID13
Feature activation-1.91e-01

Pos logit contributions
 thumb+0.094
 mummy+0.077
 Sister+0.077
 Teddy+0.076
 baby+0.075
Neg logit contributions
aw-0.135
aris-0.134
ues-0.128
lic-0.121
oke-0.120
Token The
Token ID383
Feature activation-7.12e-02

Pos logit contributions
 thumb+0.004
 mummy+0.004
 Sister+0.003
 Teddy+0.003
 Baby+0.003
Neg logit contributions
aw-0.006
aris-0.006
ues-0.006
lic-0.005
oke-0.005
Token wind
Token ID2344
Feature activation+1.34e+00

Pos logit contributions
 thumb+0.002
 Teddy+0.002
 Midnight+0.001
 Sister+0.001
 Ginny+0.001
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
hatt-0.002
oke-0.002
Token was
Token ID373
Feature activation-1.74e+00

Pos logit contributions
aris+0.044
aw+0.042
ues+0.040
lic+0.037
 facts+0.037
Neg logit contributions
 thumb-0.030
 mummy-0.024
 baby-0.024
 Sister-0.024
 Teddy-0.024
Token getting
Token ID1972
Feature activation-2.65e+00

Pos logit contributions
 thumb+0.036
 Sister+0.029
 mummy+0.029
 Teddy+0.029
 baby+0.028
Neg logit contributions
aw-0.055
aris-0.054
ues-0.052
lic-0.050
hatt-0.049
Token,
Token ID11
Feature activation+9.31e-01

Pos logit contributions
 thumb+0.015
 Sister+0.012
 mummy+0.012
 Ginny+0.012
 Baby+0.012
Neg logit contributions
aw-0.014
aris-0.014
ues-0.013
oke-0.012
ari-0.012
Token Anna
Token ID11735
Feature activation-1.67e+00

Pos logit contributions
aw+0.024
aris+0.024
ues+0.023
oke+0.022
lic+0.022
Neg logit contributions
 thumb-0.024
 Sister-0.020
 mummy-0.020
 Baby-0.019
 Ginny-0.019
Token.
Token ID13
Feature activation+7.63e-01

Pos logit contributions
 thumb+0.045
 mummy+0.039
 Teddy+0.038
 Sister+0.038
 baby+0.038
Neg logit contributions
aw-0.043
aris-0.043
ues-0.040
lic-0.038
hatt-0.038
Token This
Token ID770
Feature activation+9.42e-01

Pos logit contributions
aw+0.023
aris+0.022
ues+0.021
lic+0.020
oke+0.020
Neg logit contributions
 thumb-0.018
 Teddy-0.015
 mummy-0.015
 Sister-0.015
 baby-0.015
Token is
Token ID318
Feature activation-3.97e-01

Pos logit contributions
aris+0.027
aw+0.027
ues+0.026
lic+0.025
eway+0.024
Neg logit contributions
 thumb-0.023
 baby-0.021
 Teddy-0.020
 mummy-0.020
 Midnight-0.019
Token Elsa
Token ID19226
Feature activation-4.35e+00

Pos logit contributions
 thumb+0.008
 Teddy+0.007
 mummy+0.007
 baby+0.007
 Sister+0.007
Neg logit contributions
aris-0.013
aw-0.013
ues-0.012
oke-0.012
lic-0.012
Token.
Token ID13
Feature activation+2.67e-01

Pos logit contributions
 thumb+0.126
 Sister+0.111
 mummy+0.109
 Baby+0.107
 Teddy+0.107
Neg logit contributions
aw-0.102
aris-0.100
ues-0.094
oke-0.086
lic-0.085
Token She
Token ID1375
Feature activation+3.60e-02

Pos logit contributions
aw+0.008
aris+0.008
ues+0.007
lic+0.007
oke+0.007
Neg logit contributions
 thumb-0.006
 mummy-0.005
 Sister-0.005
 Teddy-0.005
 baby-0.005
Token is
Token ID318
Feature activation+4.43e-01

Pos logit contributions
aris+0.001
aw+0.001
ues+0.001
eway+0.001
lic+0.001
Neg logit contributions
 thumb-0.001
 Teddy-0.001
 mummy-0.001
 baby-0.001
 Sister-0.001
Token your
Token ID534
Feature activation-1.74e+00

Pos logit contributions
aw+0.014
aris+0.014
ues+0.013
lic+0.013
oke+0.013
Neg logit contributions
 thumb-0.009
 Sister-0.007
 mummy-0.007
 Teddy-0.007
 baby-0.007
Token sister
Token ID6621
Feature activation-3.10e+00

Pos logit contributions
 thumb+0.040
 Sister+0.034
 mummy+0.033
 Teddy+0.033
 baby+0.032
Neg logit contributions
aw-0.051
aris-0.051
ues-0.048
hatt-0.045
lic-0.045
Token,
Token ID11
Feature activation+4.90e-01

Pos logit contributions
aris+0.104
aw+0.101
ues+0.099
hatt+0.097
eway+0.096
Neg logit contributions
 thumb-0.065
 Teddy-0.056
 mummy-0.053
 baby-0.053
 Sister-0.053
Token c
Token ID269
Feature activation+5.09e-01

Pos logit contributions
aris+0.014
aw+0.014
ues+0.013
lic+0.012
hatt+0.012
Neg logit contributions
 thumb-0.013
 mummy-0.011
 Teddy-0.011
 baby-0.010
 Sister-0.010
Tokenaw
Token ID707
Feature activation+3.48e+00

Pos logit contributions
aris+0.011
eway+0.011
hatt+0.010
 facts+0.010
oke+0.010
Neg logit contributions
 thumb-0.014
 Teddy-0.012
 mummy-0.012
bing-0.012
 Sister-0.012
Token,
Token ID11
Feature activation+3.30e-01

Pos logit contributions
aris+0.119
hatt+0.112
aw+0.112
ues+0.111
eway+0.110
Neg logit contributions
 thumb-0.062
 Teddy-0.054
 baby-0.050
 mummy-0.049
 Sister-0.048
Token c
Token ID269
Feature activation+3.85e-01

Pos logit contributions
aris+0.009
aw+0.009
ues+0.009
lic+0.008
eway+0.008
Neg logit contributions
 thumb-0.009
 Teddy-0.007
 mummy-0.007
 baby-0.007
 Sister-0.007
Tokenaw
Token ID707
Feature activation+3.52e+00

Pos logit contributions
aris+0.008
eway+0.008
hatt+0.008
 facts+0.007
ues+0.007
Neg logit contributions
 thumb-0.011
 Teddy-0.010
 mummy-0.010
 Sister-0.009
bing-0.009
Token".
Token ID1911
Feature activation+3.70e-01

Pos logit contributions
aris+0.119
hatt+0.112
aw+0.111
 facts+0.111
eway+0.111
Neg logit contributions
 thumb-0.063
 Teddy-0.055
 baby-0.051
 mummy-0.050
 Sister-0.049
Token<|endoftext|>
Token ID50256
Feature activation+1.24e+00

Pos logit contributions
aw+0.009
aris+0.009
ues+0.008
lic+0.008
oke+0.008
Neg logit contributions
 thumb-0.011
 mummy-0.009
 Sister-0.009
 Teddy-0.009
 baby-0.009
TokenAnna
Token ID31160
Feature activation+1.92e-01

Pos logit contributions
ues+0.034
aris+0.033
aw+0.033
hatt+0.031
lic+0.030
Neg logit contributions
 thumb-0.030
 Teddy-0.027
 mummy-0.026
 Sister-0.025
 baby-0.025
Token and
Token ID290
Feature activation-6.25e-01

Pos logit contributions
aris+0.006
aw+0.006
ues+0.006
lic+0.006
eway+0.006
Neg logit contributions
 thumb-0.004
 Teddy-0.003
 Sister-0.003
 mummy-0.003
 baby-0.003
Token Ben
Token ID3932
Feature activation-7.04e-01

Pos logit contributions
 thumb+0.018
 mummy+0.015
bing+0.015
 Sister+0.015
 Teddy+0.015
Neg logit contributions
aw-0.015
aris-0.014
ues-0.013
hatt-0.013
oke-0.012
Token suddenly
Token ID6451
Feature activation+5.74e-01

Pos logit contributions
 thumb+0.003
 Sister+0.002
 mummy+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aw-0.003
aris-0.003
ues-0.003
lic-0.003
oke-0.003
Token he
Token ID339
Feature activation+2.95e-01

Pos logit contributions
aris+0.018
aw+0.018
ues+0.017
lic+0.016
hatt+0.016
Neg logit contributions
 thumb-0.012
 mummy-0.010
 Teddy-0.010
 Sister-0.010
 baby-0.010
Token heard
Token ID2982
Feature activation+8.88e-01

Pos logit contributions
aw+0.007
aris+0.007
ues+0.007
lic+0.006
oke+0.006
Neg logit contributions
 thumb-0.008
 Sister-0.007
 mummy-0.007
 Teddy-0.007
 baby-0.007
Token a
Token ID257
Feature activation+1.64e+00

Pos logit contributions
aris+0.036
ues+0.035
oke+0.034
aw+0.033
hatt+0.032
Neg logit contributions
 thumb-0.011
 Teddy-0.009
 mummy-0.009
 baby-0.009
 two-0.008
Token loud
Token ID7812
Feature activation+2.60e+00

Pos logit contributions
aris+0.056
aw+0.054
ues+0.052
ount+0.049
hatt+0.048
Neg logit contributions
 thumb-0.035
 baby-0.030
 mummy-0.029
 Teddy-0.027
 helpless-0.026
Token voice
Token ID3809
Feature activation+4.25e+00

Pos logit contributions
aris+0.094
aw+0.085
ues+0.084
ari+0.078
ount+0.077
Neg logit contributions
 thumb-0.056
 baby-0.049
 Teddy-0.046
 helpless-0.044
 bunny-0.043
Token saying
Token ID2282
Feature activation+2.44e+00

Pos logit contributions
aris+0.154
ues+0.142
aw+0.139
Deal+0.128
 facts+0.128
Neg logit contributions
 thumb-0.078
 baby-0.062
 Teddy-0.061
 mummy-0.060
 helpless-0.056
Token:
Token ID25
Feature activation+1.80e+00

Pos logit contributions
aris+0.094
aw+0.088
ues+0.087
hatt+0.087
ets+0.087
Neg logit contributions
 thumb-0.036
 Teddy-0.033
 mummy-0.031
 baby-0.028
 helpless-0.024
Token "
Token ID366
Feature activation-5.84e-01

Pos logit contributions
aris+0.054
aw+0.053
ues+0.050
ets+0.048
ari+0.046
Neg logit contributions
 thumb-0.043
 Teddy-0.039
 mummy-0.039
 Sister-0.036
 baby-0.036
TokenYou
Token ID1639
Feature activation+1.38e+00

Pos logit contributions
 thumb+0.012
 Teddy+0.010
 Sister+0.010
 baby+0.010
 mummy+0.010
Neg logit contributions
aris-0.019
ues-0.018
aw-0.018
oke-0.017
lic-0.016
Token cannot
Token ID2314
Feature activation+1.56e+00

Pos logit contributions
aw+0.041
aris+0.041
ues+0.039
lic+0.037
hatt+0.036
Neg logit contributions
 thumb-0.032
 mummy-0.027
 Teddy-0.026
 baby-0.026
 Sister-0.026
Token.
Token ID13
Feature activation-7.56e-02

Pos logit contributions
aris+0.051
aw+0.050
ues+0.047
lic+0.046
oke+0.046
Neg logit contributions
 thumb-0.043
 mummy-0.037
 Teddy-0.036
 baby-0.036
 Sister-0.035
Token The
Token ID383
Feature activation-6.43e-01

Pos logit contributions
 thumb+0.002
 mummy+0.002
 Sister+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
lic-0.002
hatt-0.002
Token man
Token ID582
Feature activation+1.87e+00

Pos logit contributions
 thumb+0.016
 mummy+0.014
 Sister+0.014
 Teddy+0.014
 baby+0.013
Neg logit contributions
aw-0.018
aris-0.017
ues-0.016
lic-0.015
oke-0.015
Token at
Token ID379
Feature activation+3.52e-01

Pos logit contributions
aris+0.054
aw+0.052
ues+0.050
eway+0.047
lic+0.047
Neg logit contributions
 thumb-0.046
 mummy-0.039
 baby-0.039
 Teddy-0.038
 Sister-0.038
Token the
Token ID262
Feature activation+2.39e+00

Pos logit contributions
aw+0.010
aris+0.010
ues+0.009
arium+0.009
ari+0.009
Neg logit contributions
 thumb-0.008
 mummy-0.006
 Sister-0.006
 infected-0.006
bing-0.006
Token stand
Token ID1302
Feature activation+3.24e+00

Pos logit contributions
aw+0.066
aris+0.065
ues+0.062
lic+0.058
oke+0.057
Neg logit contributions
 thumb-0.060
 mummy-0.051
 Sister-0.051
 Teddy-0.051
 baby-0.050
Token said
Token ID531
Feature activation+1.80e+00

Pos logit contributions
aris+0.115
aw+0.111
lic+0.108
ues+0.108
ount+0.107
Neg logit contributions
 thumb-0.053
 mummy-0.040
 tightly-0.039
 baby-0.039
 arm-0.039
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
aris+0.058
aw+0.054
ues+0.053
hatt+0.052
eway+0.051
Neg logit contributions
 thumb-0.038
 mummy-0.034
 baby-0.034
 Teddy-0.034
 Baby-0.033
Token "
Token ID366
Feature activation-1.92e-01

Pos logit contributions
aris+0.031
aw+0.031
ues+0.028
eway+0.027
hatt+0.027
Neg logit contributions
 thumb-0.027
 mummy-0.024
 Teddy-0.024
 baby-0.024
 Sister-0.024
TokenYou
Token ID1639
Feature activation+9.43e-01

Pos logit contributions
 thumb+0.004
 Sister+0.003
 baby+0.003
 Teddy+0.003
 mummy+0.003
Neg logit contributions
aris-0.006
ues-0.006
aw-0.006
oke-0.006
eway-0.005
Token have
Token ID423
Feature activation+9.03e-02

Pos logit contributions
aw+0.027
aris+0.026
ues+0.025
lic+0.023
oke+0.023
Neg logit contributions
 thumb-0.023
 Sister-0.020
 mummy-0.020
 Teddy-0.019
 baby-0.019
Token Suddenly
Token ID24975
Feature activation+1.40e-01

Pos logit contributions
 thumb+0.006
 Teddy+0.005
 mummy+0.005
 Sister+0.005
 baby+0.005
Neg logit contributions
aw-0.009
aris-0.008
ues-0.008
ount-0.008
oke-0.008
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
aw+0.004
aris+0.004
ues+0.004
hatt+0.004
lic+0.004
Neg logit contributions
 thumb-0.003
 mummy-0.002
 Teddy-0.002
 Sister-0.002
 baby-0.002
Token Brian
Token ID8403
Feature activation-4.31e-01

Pos logit contributions
 thumb+0.003
 Sister+0.003
 mummy+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aw-0.004
aris-0.004
ues-0.004
lic-0.003
hatt-0.003
Token heard
Token ID2982
Feature activation+6.06e-01

Pos logit contributions
 thumb+0.011
 mummy+0.010
 Sister+0.010
 Teddy+0.010
 baby+0.009
Neg logit contributions
aw-0.011
aris-0.011
ues-0.011
lic-0.010
oke-0.010
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
aris+0.024
ues+0.024
oke+0.023
aw+0.023
ount+0.022
Neg logit contributions
 thumb-0.007
 Teddy-0.006
 mummy-0.006
 baby-0.006
 two-0.005
Token voice
Token ID3809
Feature activation+3.99e+00

Pos logit contributions
aris+0.041
aw+0.039
ues+0.038
ount+0.035
hatt+0.035
Neg logit contributions
 thumb-0.028
 baby-0.023
 mummy-0.023
 Teddy-0.021
 helpless-0.020
Token.
Token ID13
Feature activation-4.45e-01

Pos logit contributions
aris+0.141
ues+0.130
aw+0.128
ari+0.117
lic+0.117
Neg logit contributions
 thumb-0.078
 baby-0.062
 mummy-0.061
 Teddy-0.058
 herself-0.057
Token The
Token ID383
Feature activation+1.48e-02

Pos logit contributions
 thumb+0.010
 Teddy+0.009
 mummy+0.008
 Sister+0.008
 baby+0.008
Neg logit contributions
aw-0.014
aris-0.014
ues-0.013
ount-0.012
hatt-0.012
Token voice
Token ID3809
Feature activation+3.58e+00

Pos logit contributions
aris+0.000
aw+0.000
ues+0.000
ount+0.000
ets+0.000
Neg logit contributions
 thumb-0.000
 mummy-0.000
 baby-0.000
 Teddy-0.000
 helpless-0.000
Token was
Token ID373
Feature activation-5.42e-01

Pos logit contributions
aris+0.103
aw+0.096
ues+0.095
hatt+0.085
 facts+0.084
Neg logit contributions
 thumb-0.088
 mummy-0.078
 baby-0.077
 Teddy-0.074
 Sister-0.070
Token mild
Token ID11607
Feature activation-8.54e-01

Pos logit contributions
 thumb+0.011
 mummy+0.009
 Teddy+0.009
 baby+0.009
 Sister+0.009
Neg logit contributions
aris-0.018
aw-0.018
ues-0.017
oke-0.016
hatt-0.016
Token need
Token ID761
Feature activation+4.15e-01

Pos logit contributions
aris+0.011
aw+0.011
ues+0.010
eway+0.010
lic+0.010
Neg logit contributions
 thumb-0.007
 baby-0.006
 Teddy-0.006
 mummy-0.005
 Sister-0.005
Token coins
Token ID10796
Feature activation-6.97e-01

Pos logit contributions
aris+0.012
aw+0.012
ues+0.011
lic+0.011
oke+0.011
Neg logit contributions
 thumb-0.010
 mummy-0.008
 Teddy-0.008
 Sister-0.008
 baby-0.008
Token to
Token ID284
Feature activation+1.19e-02

Pos logit contributions
 thumb+0.018
 mummy+0.015
 Teddy+0.015
 Sister+0.015
 baby+0.015
Neg logit contributions
aw-0.019
aris-0.019
ues-0.018
lic-0.017
hatt-0.017
Token buy
Token ID2822
Feature activation-1.63e+00

Pos logit contributions
aris+0.000
aw+0.000
ues+0.000
lic+0.000
oke+0.000
Neg logit contributions
 thumb-0.000
 mummy-0.000
 Teddy-0.000
 baby-0.000
 Sister-0.000
Token more
Token ID517
Feature activation+2.47e-01

Pos logit contributions
 thumb+0.037
 Teddy+0.032
 mummy+0.032
 baby+0.031
 Sister+0.031
Neg logit contributions
aris-0.048
aw-0.047
ues-0.045
lic-0.044
hatt-0.043
Token pe
Token ID613
Feature activation+3.58e+00

Pos logit contributions
aris+0.007
aw+0.007
lic+0.007
ues+0.007
hatt+0.006
Neg logit contributions
 thumb-0.006
 baby-0.005
 Teddy-0.005
 mummy-0.005
 Sister-0.005
Tokenaches
Token ID3694
Feature activation-1.06e+00

Pos logit contributions
aris+0.086
aw+0.082
hatt+0.078
lic+0.075
eway+0.075
Neg logit contributions
 thumb-0.098
 baby-0.083
 mummy-0.082
 infected-0.080
bing-0.079
Token and
Token ID290
Feature activation+8.77e-01

Pos logit contributions
 thumb+0.027
 mummy+0.023
 Teddy+0.023
 Sister+0.023
 baby+0.023
Neg logit contributions
aw-0.029
aris-0.029
ues-0.027
lic-0.026
hatt-0.026
Token other
Token ID584
Feature activation-5.88e-01

Pos logit contributions
aris+0.027
aw+0.026
ues+0.025
lic+0.024
oke+0.024
Neg logit contributions
 thumb-0.020
 mummy-0.016
 baby-0.016
 Teddy-0.016
 Sister-0.016
Token things
Token ID1243
Feature activation-9.89e-01

Pos logit contributions
 thumb+0.013
 baby+0.011
 Teddy+0.010
 mummy+0.010
 Baby+0.010
Neg logit contributions
aris-0.018
ues-0.018
aw-0.017
lic-0.017
hatt-0.017
Token."
Token ID526
Feature activation+2.73e-01

Pos logit contributions
 thumb+0.019
 Teddy+0.018
 baby+0.016
 herself+0.016
 mummy+0.016
Neg logit contributions
aris-0.031
aw-0.031
hatt-0.030
lic-0.030
eway-0.029
Token.
Token ID13
Feature activation-8.41e-02

Pos logit contributions
aris+0.007
aw+0.006
ues+0.006
lic+0.006
hatt+0.006
Neg logit contributions
 thumb-0.005
 mummy-0.004
 baby-0.004
 Teddy-0.004
 herself-0.004
Token She
Token ID1375
Feature activation+6.72e-01

Pos logit contributions
 thumb+0.002
 Sister+0.002
 mummy+0.002
 Teddy+0.002
 baby+0.002
Neg logit contributions
aw-0.003
aris-0.003
ues-0.002
lic-0.002
oke-0.002
Token wants
Token ID3382
Feature activation+1.23e-01

Pos logit contributions
aris+0.017
aw+0.015
ues+0.015
eway+0.014
lic+0.014
Neg logit contributions
 thumb-0.019
 Sister-0.017
 baby-0.017
 Teddy-0.016
 mummy-0.016
Token her
Token ID607
Feature activation-6.42e-01

Pos logit contributions
aris+0.004
aw+0.004
ues+0.004
lic+0.003
oke+0.003
Neg logit contributions
 thumb-0.003
 baby-0.003
 mummy-0.003
 Teddy-0.002
 Sister-0.002
Token mom
Token ID1995
Feature activation-9.44e-01

Pos logit contributions
 thumb+0.016
 Baby+0.016
 Sister+0.016
 Ginny+0.016
 Teddy+0.015
Neg logit contributions
aris-0.015
aw-0.014
ues-0.014
 facts-0.013
 contest-0.013
Token to
Token ID284
Feature activation+7.77e-01

Pos logit contributions
 thumb+0.024
 baby+0.020
 mummy+0.020
 Teddy+0.020
 Sister+0.020
Neg logit contributions
aris-0.026
aw-0.026
ues-0.025
lic-0.023
hatt-0.023
Token see
Token ID766
Feature activation+1.08e+00

Pos logit contributions
aris+0.024
aw+0.023
ues+0.022
lic+0.021
oke+0.021
Neg logit contributions
 thumb-0.018
 mummy-0.015
 baby-0.015
 Teddy-0.015
 Sister-0.015
Token her
Token ID607
Feature activation-1.03e+00

Pos logit contributions
aris+0.039
aw+0.039
ues+0.037
lic+0.036
hatt+0.035
Neg logit contributions
 thumb-0.018
 mummy-0.014
 Teddy-0.014
 baby-0.014
 Sister-0.014
Token trophy
Token ID16383
Feature activation-5.51e-01

Pos logit contributions
 thumb+0.027
 Sister+0.024
 Teddy+0.024
 mummy+0.023
 Baby+0.023
Neg logit contributions
aw-0.026
aris-0.026
ues-0.025
oke-0.023
hatt-0.023
Token.
Token ID13
Feature activation+3.66e-02

Pos logit contributions
 thumb+0.012
 baby+0.010
 mummy+0.010
 Teddy+0.009
 herself+0.009
Neg logit contributions
aris-0.018
aw-0.017
lic-0.017
hatt-0.017
ues-0.016
Token She
Token ID1375
Feature activation+7.62e-01

Pos logit contributions
aw+0.001
aris+0.001
ues+0.001
lic+0.001
oke+0.001
Neg logit contributions
 thumb-0.001
 mummy-0.001
 Sister-0.001
 Teddy-0.001
 baby-0.001
Token the
Token ID262
Feature activation+1.18e-01

Pos logit contributions
 thumb+0.021
 Teddy+0.017
 mummy+0.017
 Sister+0.016
 baby+0.016
Neg logit contributions
aris-0.047
ues-0.046
aw-0.044
oke-0.044
lic-0.043
Token best
Token ID1266
Feature activation+7.67e-01

Pos logit contributions
aw+0.004
aris+0.004
ues+0.004
lic+0.004
oke+0.004
Neg logit contributions
 thumb-0.002
 mummy-0.002
 Sister-0.002
 Teddy-0.002
 baby-0.002
Token knees
Token ID14475
Feature activation-9.88e-01

Pos logit contributions
aris+0.022
ues+0.021
aw+0.021
lic+0.021
oke+0.020
Neg logit contributions
 thumb-0.019
 mummy-0.017
 baby-0.016
 Sister-0.015
 Teddy-0.015
Token in
Token ID287
Feature activation-1.26e+00

Pos logit contributions
 thumb+0.023
 baby+0.019
 mummy+0.019
 Teddy+0.019
 Sister+0.018
Neg logit contributions
aris-0.030
aw-0.029
ues-0.028
lic-0.027
hatt-0.026
Token the
Token ID262
Feature activation-6.16e-01

Pos logit contributions
 thumb+0.024
 mummy+0.020
 Teddy+0.019
 Sister+0.019
 baby+0.019
Neg logit contributions
aw-0.043
aris-0.043
ues-0.041
lic-0.039
oke-0.039
Token school
Token ID1524
Feature activation+9.09e-01

Pos logit contributions
 thumb+0.016
 Sister+0.013
 mummy+0.013
 Teddy+0.013
 baby+0.013
Neg logit contributions
aw-0.017
aris-0.016
ues-0.015
hatt-0.014
lic-0.014
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
lic+0.029
aris+0.029
cod+0.029
ues+0.028
aw+0.028
Neg logit contributions
 thumb-0.017
 mummy-0.014
 Teddy-0.013
 arm-0.013
 baby-0.012
Token They
Token ID1119
Feature activation-1.62e+00

Pos logit contributions
 thumb+0.028
 Sister+0.024
 Teddy+0.024
 mummy+0.024
 baby+0.023
Neg logit contributions
aw-0.036
aris-0.036
ues-0.034
lic-0.034
oke-0.033
Token were
Token ID547
Feature activation-1.32e+00

Pos logit contributions
 thumb+0.040
 mummy+0.034
 Teddy+0.034
 Sister+0.033
 baby+0.033
Neg logit contributions
aw-0.045
aris-0.045
ues-0.043
lic-0.040
oke-0.040
Token big
Token ID1263
Feature activation-4.21e-01

Pos logit contributions
 thumb+0.024
 Sister+0.019
 Teddy+0.018
 mummy+0.018
 baby+0.017
Neg logit contributions
aw-0.046
aris-0.045
ues-0.042
lic-0.040
hatt-0.040
Token and
Token ID290
Feature activation-1.73e+00

Pos logit contributions
 thumb+0.009
 Sister+0.007
 mummy+0.007
 Teddy+0.007
 baby+0.007
Neg logit contributions
aw-0.013
aris-0.013
ues-0.012
oke-0.012
lic-0.011
Token fun
Token ID1257
Feature activation+1.83e+00

Pos logit contributions
 thumb+0.011
 baby+0.009
 mummy+0.009
 Teddy+0.009
 Sister+0.009
Neg logit contributions
aris-0.019
aw-0.018
ues-0.017
lic-0.017
oke-0.016
Token toy
Token ID13373
Feature activation-9.80e-01

Pos logit contributions
aw+0.063
aris+0.062
ount+0.057
oke+0.056
ues+0.055
Neg logit contributions
 thumb-0.044
 baby-0.036
 Teddy-0.036
 mummy-0.036
 arm-0.034
Token.
Token ID13
Feature activation+3.28e-02

Pos logit contributions
 thumb+0.023
 Teddy+0.020
 baby+0.019
 mummy+0.019
 Sister+0.017
Neg logit contributions
aris-0.030
aw-0.029
ues-0.028
lic-0.028
hatt-0.027
Token They
Token ID1119
Feature activation-9.83e-01

Pos logit contributions
aris+0.001
aw+0.001
ues+0.001
ari+0.001
oke+0.001
Neg logit contributions
 thumb-0.001
 Teddy-0.001
 mummy-0.001
 Sister-0.001
 Baby-0.001
Token do
Token ID466
Feature activation+2.61e+00

Pos logit contributions
 thumb+0.024
 mummy+0.020
 Teddy+0.020
 Sister+0.019
 baby+0.019
Neg logit contributions
aris-0.029
aw-0.028
ues-0.027
lic-0.026
oke-0.025
Token not
Token ID407
Feature activation+5.80e-01

Pos logit contributions
aris+0.094
aw+0.092
lic+0.083
ues+0.082
oke+0.082
Neg logit contributions
 thumb-0.047
 mummy-0.039
 Teddy-0.037
 baby-0.036
 Sister-0.035
Token want
Token ID765
Feature activation+8.32e-01

Pos logit contributions
aris+0.018
aw+0.018
ues+0.017
eway+0.016
lic+0.016
Neg logit contributions
 thumb-0.014
 baby-0.011
 Teddy-0.011
 mummy-0.011
 Sister-0.010
Token to
Token ID284
Feature activation+2.29e+00

Pos logit contributions
aris+0.022
aw+0.022
ues+0.021
lic+0.020
oke+0.020
Neg logit contributions
 thumb-0.022
 Teddy-0.020
 mummy-0.020
 baby-0.019
 Sister-0.019
Token read
Token ID1100
Feature activation-7.98e-01

Pos logit contributions
aw+0.056
aris+0.054
ues+0.053
hatt+0.048
lic+0.047
Neg logit contributions
 thumb-0.060
 Sister-0.053
 mummy-0.051
 Ginny-0.050
 Teddy-0.050
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
 thumb+0.017
 Teddy+0.014
 mummy+0.014
 baby+0.014
 Sister+0.013
Neg logit contributions
aris-0.026
aw-0.025
ues-0.024
lic-0.023
hatt-0.023
Token books
Token ID3835
Feature activation-1.11e+00

Pos logit contributions
aw+0.042
aris+0.042
ues+0.040
lic+0.039
hatt+0.039
Neg logit contributions
 thumb-0.029
 Sister-0.024
 mummy-0.024
 Baby-0.024
 Ginny-0.023
Token the
Token ID262
Feature activation+1.08e+00

Pos logit contributions
aris+0.052
aw+0.052
ues+0.050
lic+0.049
oke+0.048
Neg logit contributions
 thumb-0.023
 Teddy-0.018
 baby-0.018
 mummy-0.018
 Sister-0.017
Token statue
Token ID15207
Feature activation+1.26e+00

Pos logit contributions
aris+0.031
ues+0.031
aw+0.031
lic+0.030
ount+0.027
Neg logit contributions
 thumb-0.028
 baby-0.024
 mummy-0.023
 Teddy-0.022
 bunny-0.021
Token.
Token ID13
Feature activation+8.91e-01

Pos logit contributions
lic+0.043
aris+0.043
ues+0.042
aw+0.041
hatt+0.041
Neg logit contributions
 thumb-0.022
 baby-0.018
 Teddy-0.017
 tightly-0.017
 mummy-0.017
Token He
Token ID679
Feature activation+5.72e-01

Pos logit contributions
aw+0.031
ues+0.030
aris+0.030
ile+0.029
ets+0.028
Neg logit contributions
 Teddy-0.015
 thumb-0.014
 mummy-0.014
 Sister-0.013
 Baby-0.012
Token says
Token ID1139
Feature activation+2.56e+00

Pos logit contributions
aris+0.016
lic+0.015
eway+0.015
ues+0.014
aw+0.014
Neg logit contributions
 thumb-0.014
 baby-0.012
 mummy-0.012
 Teddy-0.012
 Sister-0.012
Token,
Token ID11
Feature activation+1.75e+00

Pos logit contributions
aris+0.099
aw+0.094
hatt+0.094
ount+0.092
lic+0.091
Neg logit contributions
 thumb-0.037
 mummy-0.034
 Teddy-0.032
 baby-0.031
 two-0.026
Token "
Token ID366
Feature activation-2.40e-01

Pos logit contributions
aris+0.049
aw+0.049
ues+0.045
lic+0.042
hatt+0.042
Neg logit contributions
 thumb-0.045
 Teddy-0.039
 mummy-0.039
 Sister-0.038
 baby-0.038
TokenOkay
Token ID16454
Feature activation-2.17e+00

Pos logit contributions
 thumb+0.005
 Sister+0.004
 Teddy+0.004
 baby+0.004
 mummy+0.004
Neg logit contributions
aris-0.008
ues-0.008
lic-0.008
oke-0.007
aw-0.007
Token,
Token ID11
Feature activation+5.98e-02

Pos logit contributions
 thumb+0.050
 mummy+0.041
 Sister+0.041
 Teddy+0.041
 baby+0.040
Neg logit contributions
aw-0.065
aris-0.065
ues-0.061
lic-0.058
oke-0.057
Token mom
Token ID1995
Feature activation+2.11e-01

Pos logit contributions
aris+0.002
aw+0.002
ues+0.002
lic+0.002
oke+0.002
Neg logit contributions
 thumb-0.001
 mummy-0.001
 Teddy-0.001
 baby-0.001
 Sister-0.000
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
ues+0.007
aw+0.007
aris+0.007
eway+0.007
lic+0.007
Neg logit contributions
 thumb-0.003
 Teddy-0.003
 mummy-0.003
 baby-0.003
 two-0.002
Token nodded
Token ID14464
Feature activation-6.34e-02

Pos logit contributions
 thumb+0.007
 Sister+0.006
 mummy+0.006
 Teddy+0.006
 baby+0.006
Neg logit contributions
aris-0.010
aw-0.010
ues-0.009
lic-0.009
eway-0.009
Token.
Token ID13
Feature activation-2.74e-01

Pos logit contributions
 thumb+0.002
 Sister+0.001
 Teddy+0.001
 mummy+0.001
 baby+0.001
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
lic-0.002
hatt-0.001
Token She
Token ID1375
Feature activation+7.53e-01

Pos logit contributions
 thumb+0.006
 mummy+0.005
 Sister+0.005
 Teddy+0.005
 baby+0.005
Neg logit contributions
aw-0.009
aris-0.009
ues-0.008
lic-0.008
oke-0.008
Token went
Token ID1816
Feature activation+1.53e-01

Pos logit contributions
aris+0.022
aw+0.021
ues+0.020
eway+0.019
oke+0.019
Neg logit contributions
 thumb-0.019
 mummy-0.016
 Sister-0.016
 Teddy-0.015
 baby-0.015
Token to
Token ID284
Feature activation-2.32e-01

Pos logit contributions
aw+0.005
aris+0.004
oke+0.004
ues+0.004
eway+0.004
Neg logit contributions
 thumb-0.003
 mummy-0.003
 Teddy-0.003
 baby-0.003
 Sister-0.003
Token the
Token ID262
Feature activation+1.95e+00

Pos logit contributions
 thumb+0.005
 Sister+0.004
 mummy+0.003
 Teddy+0.003
 Ginny+0.003
Neg logit contributions
aris-0.007
aw-0.007
ues-0.007
hatt-0.007
lic-0.007
Token living
Token ID2877
Feature activation+1.95e+00

Pos logit contributions
aris+0.069
aw+0.068
ues+0.066
oke+0.062
lic+0.062
Neg logit contributions
 thumb-0.037
 mummy-0.030
 baby-0.030
 Sister-0.028
 Teddy-0.028
Token room
Token ID2119
Feature activation+5.42e-01

Pos logit contributions
aris+0.064
aw+0.063
ues+0.059
lic+0.058
oke+0.058
Neg logit contributions
 thumb-0.041
 mummy-0.034
 baby-0.034
 Sister-0.032
 Teddy-0.032
Token and
Token ID290
Feature activation+8.56e-01

Pos logit contributions
aw+0.020
aris+0.020
oke+0.019
lic+0.019
cod+0.018
Neg logit contributions
 thumb-0.009
 mummy-0.007
 herself-0.007
 arm-0.007
 tightly-0.007
Token played
Token ID2826
Feature activation-6.58e-01

Pos logit contributions
aris+0.027
aw+0.027
ues+0.025
oke+0.024
eway+0.024
Neg logit contributions
 thumb-0.020
 mummy-0.017
 Teddy-0.017
 baby-0.017
 Sister-0.017
Token with
Token ID351
Feature activation-8.28e-01

Pos logit contributions
 thumb+0.012
 mummy+0.010
 herself+0.010
 Teddy+0.010
 baby+0.009
Neg logit contributions
aris-0.024
aw-0.023
oke-0.022
hatt-0.022
ari-0.022
Token knew
Token ID2993
Feature activation-6.31e-02

Pos logit contributions
 thumb+0.008
 mummy+0.006
 baby+0.006
 Teddy+0.006
 Sister+0.006
Neg logit contributions
aris-0.010
ues-0.009
aw-0.009
oke-0.009
lic-0.009
Token what
Token ID644
Feature activation-7.27e-01

Pos logit contributions
 thumb+0.001
 mummy+0.001
 Teddy+0.001
 baby+0.001
 Sister+0.001
Neg logit contributions
aris-0.002
aw-0.002
ues-0.002
lic-0.002
oke-0.002
Token to
Token ID284
Feature activation+8.78e-01

Pos logit contributions
 thumb+0.017
 mummy+0.014
 baby+0.014
 Teddy+0.014
 Sister+0.013
Neg logit contributions
ues-0.024
aris-0.023
aw-0.023
ount-0.022
lic-0.021
Token do
Token ID466
Feature activation+1.41e+00

Pos logit contributions
aw+0.022
aris+0.021
ues+0.020
hatt+0.018
oke+0.018
Neg logit contributions
 thumb-0.024
 Sister-0.022
 Teddy-0.021
 mummy-0.021
 baby-0.020
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
aw+0.042
aris+0.042
ues+0.039
lic+0.038
hatt+0.038
Neg logit contributions
 thumb-0.033
 Teddy-0.028
 mummy-0.027
 baby-0.026
 Sister-0.026
Token He
Token ID679
Feature activation+2.92e-02

Pos logit contributions
ues+0.006
aris+0.006
aw+0.006
hatt+0.006
lic+0.006
Neg logit contributions
 thumb-0.004
 Teddy-0.004
 mummy-0.003
 Sister-0.003
 Baby-0.003
Token spoke
Token ID5158
Feature activation-8.97e-02

Pos logit contributions
aris+0.001
ues+0.001
aw+0.001
oke+0.001
eway+0.001
Neg logit contributions
 thumb-0.001
 baby-0.001
 mummy-0.001
 Teddy-0.001
 Sister-0.001
Token into
Token ID656
Feature activation+1.12e+00

Pos logit contributions
 thumb+0.002
 mummy+0.002
 Teddy+0.002
 baby+0.002
 Sister+0.002
Neg logit contributions
aris-0.002
aw-0.002
ues-0.002
oke-0.002
hatt-0.002
Token his
Token ID465
Feature activation-1.20e+00

Pos logit contributions
aw+0.037
aris+0.037
ues+0.035
lic+0.034
hatt+0.033
Neg logit contributions
 thumb-0.022
 mummy-0.017
 Sister-0.017
 Teddy-0.017
 baby-0.017
Token radio
Token ID5243
Feature activation-9.25e-01

Pos logit contributions
 thumb+0.022
 mummy+0.017
 baby+0.017
 Sister+0.016
 Teddy+0.016
Neg logit contributions
aw-0.043
aris-0.043
ues-0.041
lic-0.041
oke-0.040
Token to
Token ID284
Feature activation-1.25e+00

Pos logit contributions
 thumb+0.018
 mummy+0.014
 baby+0.014
 Teddy+0.014
 tightly+0.013
Neg logit contributions
aris-0.032
aw-0.031
lic-0.030
ues-0.030
hatt-0.030
Token toes
Token ID23932
Feature activation-5.03e-01

Pos logit contributions
aw+0.032
aris+0.032
ues+0.031
lic+0.030
oke+0.029
Neg logit contributions
 thumb-0.012
 mummy-0.009
 Teddy-0.008
 Sister-0.008
 baby-0.008
Token and
Token ID290
Feature activation+4.29e-01

Pos logit contributions
 thumb+0.010
 mummy+0.008
 Sister+0.008
 Teddy+0.008
 baby+0.008
Neg logit contributions
aw-0.016
aris-0.016
ues-0.015
lic-0.015
oke-0.015
Token stretched
Token ID19110
Feature activation-8.39e-01

Pos logit contributions
aw+0.012
aris+0.011
ues+0.011
hatt+0.010
lic+0.010
Neg logit contributions
 thumb-0.011
 Sister-0.009
 mummy-0.009
 Teddy-0.009
 baby-0.009
Token out
Token ID503
Feature activation+3.16e+00

Pos logit contributions
 thumb+0.015
 Sister+0.012
 mummy+0.012
 Teddy+0.012
 baby+0.011
Neg logit contributions
aw-0.029
aris-0.029
ues-0.028
lic-0.026
hatt-0.026
Token her
Token ID607
Feature activation-8.89e-01

Pos logit contributions
aw+0.123
aris+0.123
ues+0.117
oke+0.114
lic+0.111
Neg logit contributions
 thumb-0.045
 mummy-0.035
 baby-0.033
 Teddy-0.033
 Sister-0.032
Token hands
Token ID2832
Feature activation-1.38e+00

Pos logit contributions
 Sister+0.014
 Ginny+0.014
 Cathy+0.013
 Midnight+0.013
 thumb+0.013
Neg logit contributions
aris-0.027
aw-0.026
hatt-0.024
ues-0.024
br-0.023
Token.
Token ID13
Feature activation-4.37e-01

Pos logit contributions
 thumb+0.038
 mummy+0.033
 Sister+0.033
 Teddy+0.032
 baby+0.032
Neg logit contributions
aw-0.035
aris-0.034
ues-0.032
lic-0.030
hatt-0.030
Token Snap
Token ID16026
Feature activation+8.41e-01

Pos logit contributions
 thumb+0.011
 mummy+0.009
 Sister+0.009
 Teddy+0.009
 baby+0.009
Neg logit contributions
aw-0.013
aris-0.012
ues-0.012
lic-0.011
oke-0.011
Token!
Token ID0
Feature activation+3.12e-01

Pos logit contributions
aris+0.025
aw+0.024
ues+0.023
hatt+0.023
eway+0.022
Neg logit contributions
 thumb-0.020
 Teddy-0.017
 mummy-0.016
 baby-0.016
 Sister-0.016
Token Anna
Token ID11735
Feature activation-1.04e+00

Pos logit contributions
aw+0.010
aris+0.009
ues+0.009
hatt+0.008
oke+0.008
Neg logit contributions
 thumb-0.007
 Teddy-0.006
 mummy-0.006
 Sister-0.006
 baby-0.006
Token cl
Token ID537
Feature activation+1.79e+00

Pos logit contributions
 thumb+0.025
 mummy+0.021
 Teddy+0.021
 baby+0.020
 Sister+0.020
Neg logit contributions
aris-0.030
aw-0.030
ues-0.029
lic-0.027
oke-0.027
Token said
Token ID531
Feature activation+1.97e+00

Pos logit contributions
aris+0.031
aw+0.031
ues+0.029
lic+0.027
oke+0.027
Neg logit contributions
 thumb-0.033
 mummy-0.028
 Sister-0.028
 Teddy-0.028
 baby-0.027
Token she
Token ID673
Feature activation+1.35e+00

Pos logit contributions
aw+0.059
aris+0.059
ues+0.055
lic+0.052
hatt+0.052
Neg logit contributions
 thumb-0.045
 mummy-0.038
 Sister-0.037
 Teddy-0.037
 baby-0.037
Token was
Token ID373
Feature activation+6.57e-01

Pos logit contributions
aw+0.035
aris+0.034
ues+0.032
lic+0.030
oke+0.030
Neg logit contributions
 thumb-0.036
 Sister-0.031
 mummy-0.031
 Teddy-0.030
 baby-0.030
Token making
Token ID1642
Feature activation-3.07e-01

Pos logit contributions
aw+0.020
aris+0.020
ues+0.019
lic+0.018
oke+0.018
Neg logit contributions
 thumb-0.014
 Sister-0.011
 Teddy-0.011
 mummy-0.011
 baby-0.010
Token some
Token ID617
Feature activation-2.69e-02

Pos logit contributions
 thumb+0.006
 Sister+0.005
 mummy+0.005
 Teddy+0.005
 baby+0.005
Neg logit contributions
aw-0.010
aris-0.010
ues-0.009
lic-0.009
hatt-0.009
Token y
Token ID331
Feature activation-6.59e-01

Pos logit contributions
 thumb+0.001
 Sister+0.001
 Teddy+0.001
 mummy+0.001
 baby+0.001
Neg logit contributions
aw-0.001
aris-0.001
ues-0.001
lic-0.001
oke-0.001
Tokenummy
Token ID13513
Feature activation-4.57e-01

Pos logit contributions
 thumb+0.013
 Teddy+0.011
 Sister+0.010
 baby+0.010
 mummy+0.010
Neg logit contributions
aw-0.023
aris-0.021
ues-0.020
lic-0.019
oke-0.019
Token breakfast
Token ID12607
Feature activation-7.45e-01

Pos logit contributions
 thumb+0.012
 Sister+0.010
 mummy+0.010
 Teddy+0.010
 baby+0.009
Neg logit contributions
aw-0.012
aris-0.012
ues-0.011
lic-0.011
oke-0.011
Token and
Token ID290
Feature activation+9.48e-01

Pos logit contributions
 thumb+0.016
 mummy+0.014
 Teddy+0.014
 baby+0.013
 herself+0.013
Neg logit contributions
aris-0.024
aw-0.023
hatt-0.022
ues-0.021
lic-0.021
Token asked
Token ID1965
Feature activation-6.76e-01

Pos logit contributions
aris+0.030
aw+0.029
ues+0.028
lic+0.026
oke+0.026
Neg logit contributions
 thumb-0.021
 mummy-0.019
 Teddy-0.018
 baby-0.018
 Sister-0.018
Token him
Token ID683
Feature activation+1.64e+00

Pos logit contributions
 thumb+0.016
 Sister+0.013
 mummy+0.013
 Teddy+0.013
 baby+0.013
Neg logit contributions
aw-0.020
aris-0.019
ues-0.018
oke-0.017
lic-0.017
Token me
Token ID502
Feature activation+1.29e+00

Pos logit contributions
 thumb+0.016
 Sister+0.014
 mummy+0.013
 Ginny+0.013
 baby+0.013
Neg logit contributions
aw-0.014
aris-0.013
ues-0.012
arium-0.011
hatt-0.011
Token."
Token ID526
Feature activation+3.64e-01

Pos logit contributions
aw+0.037
aris+0.036
ues+0.034
lic+0.032
oke+0.032
Neg logit contributions
 thumb-0.032
 Sister-0.027
 mummy-0.026
 Teddy-0.026
 baby-0.026
Token So
Token ID1406
Feature activation-6.96e-01

Pos logit contributions
aw+0.011
aris+0.011
ues+0.011
lic+0.010
hatt+0.010
Neg logit contributions
 thumb-0.008
 mummy-0.007
 Sister-0.007
 Teddy-0.007
 baby-0.006
Token they
Token ID484
Feature activation-2.72e-01

Pos logit contributions
 thumb+0.017
 Sister+0.014
 infected+0.013
 injured+0.013
 Baby+0.012
Neg logit contributions
aris-0.019
aw-0.019
ues-0.018
arium-0.017
lic-0.017
Token went
Token ID1816
Feature activation+5.65e-02

Pos logit contributions
 thumb+0.006
 mummy+0.005
 Teddy+0.005
 Sister+0.005
 baby+0.005
Neg logit contributions
aw-0.008
aris-0.008
ues-0.008
oke-0.007
lic-0.007
Token outside
Token ID2354
Feature activation+4.58e-01

Pos logit contributions
aw+0.002
aris+0.002
ues+0.001
oke+0.001
lic+0.001
Neg logit contributions
 thumb-0.001
 Teddy-0.001
 mummy-0.001
 baby-0.001
 Sister-0.001
Token and
Token ID290
Feature activation-5.45e-02

Pos logit contributions
aw+0.016
aris+0.015
ues+0.014
lic+0.014
hatt+0.014
Neg logit contributions
 thumb-0.009
 mummy-0.008
 baby-0.008
 Teddy-0.008
 Sister-0.007
Token they
Token ID484
Feature activation-1.44e+00

Pos logit contributions
 thumb+0.001
 Teddy+0.001
 mummy+0.001
 Sister+0.001
 baby+0.001
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
oke-0.001
lic-0.001
Token looked
Token ID3114
Feature activation-3.42e-02

Pos logit contributions
 thumb+0.036
 mummy+0.032
 Teddy+0.032
 baby+0.031
 Sister+0.031
Neg logit contributions
aris-0.040
aw-0.039
ues-0.038
oke-0.035
eway-0.035
Token and
Token ID290
Feature activation+1.51e-01

Pos logit contributions
 thumb+0.001
 mummy+0.001
 Teddy+0.001
 Sister+0.001
 baby+0.001
Neg logit contributions
aw-0.001
aris-0.001
ues-0.001
oke-0.001
lic-0.001
Token looked
Token ID3114
Feature activation+1.57e-01

Pos logit contributions
aw+0.004
aris+0.004
ues+0.004
oke+0.004
lic+0.004
Neg logit contributions
 thumb-0.004
 mummy-0.003
 Teddy-0.003
 baby-0.003
 Sister-0.003
Token,
Token ID11
Feature activation-7.68e-02

Pos logit contributions
 thumb+0.005
 Teddy+0.004
 mummy+0.004
 Sister+0.004
 baby+0.004
Neg logit contributions
aw-0.007
aris-0.007
ues-0.007
lic-0.006
hatt-0.006
Token he
Token ID339
Feature activation-2.21e-01

Pos logit contributions
 thumb+0.002
 Sister+0.002
 baby+0.002
 Teddy+0.002
 mummy+0.002
Neg logit contributions
aris-0.002
aw-0.002
ues-0.002
hatt-0.002
oke-0.002
Token would
Token ID561
Feature activation-1.39e+00

Pos logit contributions
 thumb+0.005
 mummy+0.004
 Teddy+0.004
 Sister+0.004
 baby+0.004
Neg logit contributions
aris-0.006
aw-0.006
ues-0.006
lic-0.006
oke-0.006
Token take
Token ID1011
Feature activation-7.55e-02

Pos logit contributions
 thumb+0.032
 mummy+0.027
 Teddy+0.025
 baby+0.025
 Sister+0.025
Neg logit contributions
aw-0.043
aris-0.043
ues-0.041
oke-0.040
lic-0.039
Token it
Token ID340
Feature activation-1.22e+00

Pos logit contributions
 thumb+0.002
 mummy+0.001
 Sister+0.001
 Teddy+0.001
 baby+0.001
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
lic-0.002
oke-0.002
Token down
Token ID866
Feature activation+2.51e-01

Pos logit contributions
 thumb+0.025
 mummy+0.021
 Teddy+0.021
 baby+0.020
 Sister+0.020
Neg logit contributions
aw-0.040
aris-0.038
ues-0.038
oke-0.037
lic-0.036
Token and
Token ID290
Feature activation+6.08e-01

Pos logit contributions
aw+0.008
aris+0.008
ues+0.008
oke+0.008
lic+0.008
Neg logit contributions
 thumb-0.005
 mummy-0.004
 Teddy-0.004
 Sister-0.004
 baby-0.004
Token test
Token ID1332
Feature activation+1.57e+00

Pos logit contributions
aw+0.019
aris+0.019
ues+0.019
oke+0.018
lic+0.018
Neg logit contributions
 thumb-0.013
 mummy-0.011
 Teddy-0.011
 Sister-0.011
 baby-0.011
Token it
Token ID340
Feature activation-4.50e-01

Pos logit contributions
aw+0.050
aris+0.049
ues+0.047
lic+0.044
oke+0.044
Neg logit contributions
 thumb-0.033
 mummy-0.027
 Sister-0.027
 Teddy-0.026
 baby-0.026
Token.
Token ID13
Feature activation-2.49e-02

Pos logit contributions
 thumb+0.009
 Teddy+0.007
 mummy+0.007
 herself+0.007
 baby+0.007
Neg logit contributions
aw-0.015
aris-0.015
oke-0.014
ues-0.014
hatt-0.014
Token He
Token ID679
Feature activation-1.08e-01

Pos logit contributions
 thumb+0.001
 mummy+0.001
 Teddy+0.001
 Sister+0.001
 Baby+0.001
Neg logit contributions
aw-0.001
aris-0.001
ues-0.001
lic-0.001
oke-0.001
Token on
Token ID319
Feature activation-9.77e-01

Pos logit contributions
aris+0.011
aw+0.011
ues+0.010
lic+0.010
ari+0.010
Neg logit contributions
 thumb-0.010
 baby-0.009
 mummy-0.009
 Teddy-0.008
 Sister-0.008
Token your
Token ID534
Feature activation+2.27e-01

Pos logit contributions
 thumb+0.022
 Sister+0.018
 Teddy+0.018
 mummy+0.018
 Ginny+0.017
Neg logit contributions
aw-0.029
aris-0.027
ues-0.026
eway-0.024
hatt-0.023
Token plate
Token ID7480
Feature activation-1.41e+00

Pos logit contributions
aw+0.007
aris+0.007
ues+0.006
hatt+0.006
oke+0.006
Neg logit contributions
 thumb-0.005
 Sister-0.004
 Teddy-0.004
 mummy-0.004
 baby-0.004
Token.
Token ID13
Feature activation+6.82e-01

Pos logit contributions
 thumb+0.033
 mummy+0.028
 Teddy+0.027
 baby+0.027
 Sister+0.026
Neg logit contributions
aris-0.042
aw-0.041
ues-0.040
hatt-0.038
lic-0.038
Token Bro
Token ID2806
Feature activation+5.82e-01

Pos logit contributions
aw+0.017
aris+0.017
ues+0.016
oke+0.015
hatt+0.015
Neg logit contributions
 thumb-0.019
 mummy-0.016
 Sister-0.016
 baby-0.015
 Teddy-0.015
Tokenccoli
Token ID34544
Feature activation-2.47e+00

Pos logit contributions
aris+0.014
aw+0.014
ues+0.013
hatt+0.012
lic+0.012
Neg logit contributions
 thumb-0.017
 mummy-0.015
 Sister-0.015
 Teddy-0.015
 baby-0.014
Token is
Token ID318
Feature activation+4.05e-03

Pos logit contributions
 thumb+0.073
 mummy+0.063
 Teddy+0.063
 Sister+0.062
 baby+0.062
Neg logit contributions
aris-0.058
aw-0.057
ues-0.054
lic-0.050
hatt-0.050
Token not
Token ID407
Feature activation-1.16e+00

Pos logit contributions
aw+0.000
aris+0.000
ues+0.000
lic+0.000
oke+0.000
Neg logit contributions
 thumb-0.000
 mummy-0.000
 Sister-0.000
 Teddy-0.000
 baby-0.000
Token that
Token ID326
Feature activation-2.05e-01

Pos logit contributions
 thumb+0.026
 baby+0.022
 Teddy+0.022
 mummy+0.021
 Sister+0.021
Neg logit contributions
aris-0.036
aw-0.035
ues-0.034
hatt-0.032
eway-0.031
Token bad
Token ID2089
Feature activation+9.23e-01

Pos logit contributions
 thumb+0.005
 mummy+0.004
 baby+0.004
 Teddy+0.004
 Sister+0.004
Neg logit contributions
aris-0.006
aw-0.006
ues-0.006
lic-0.005
hatt-0.005
Token.
Token ID13
Feature activation+4.85e-01

Pos logit contributions
aris+0.028
aw+0.027
ues+0.026
lic+0.025
hatt+0.025
Neg logit contributions
 thumb-0.022
 baby-0.019
 mummy-0.019
 Teddy-0.019
 Sister-0.018
Token dragon
Token ID10441
Feature activation+3.37e-01

Pos logit contributions
 thumb+0.016
 mummy+0.014
 baby+0.013
 Sister+0.013
 Teddy+0.013
Neg logit contributions
aris-0.021
aw-0.021
ues-0.020
lic-0.019
oke-0.019
Tokenflies
Token ID27959
Feature activation+2.19e-01

Pos logit contributions
aris+0.011
aw+0.010
ues+0.010
 facts+0.010
ount+0.009
Neg logit contributions
 thumb-0.007
 mummy-0.006
 baby-0.006
 Teddy-0.006
 bunny-0.005
Token that
Token ID326
Feature activation-5.29e-01

Pos logit contributions
aris+0.007
aw+0.007
ues+0.006
ari+0.006
hatt+0.006
Neg logit contributions
 thumb-0.005
 mummy-0.004
 baby-0.004
 Teddy-0.004
 Sister-0.004
Token were
Token ID547
Feature activation-1.26e+00

Pos logit contributions
 thumb+0.011
 mummy+0.010
 Teddy+0.010
 baby+0.010
 Baby+0.009
Neg logit contributions
aris-0.017
ues-0.017
aw-0.017
ari-0.016
lic-0.016
Token sk
Token ID1341
Feature activation+8.83e-01

Pos logit contributions
 thumb+0.024
 mummy+0.020
 baby+0.020
 Teddy+0.019
 Sister+0.019
Neg logit contributions
aris-0.043
aw-0.042
ues-0.041
oke-0.039
lic-0.038
Tokenimming
Token ID27428
Feature activation-2.66e+00

Pos logit contributions
aris+0.025
aw+0.025
ues+0.023
oke+0.022
hatt+0.022
Neg logit contributions
 thumb-0.022
 mummy-0.018
 Sister-0.018
 Teddy-0.018
 baby-0.017
Token the
Token ID262
Feature activation-8.02e-01

Pos logit contributions
 thumb+0.052
 mummy+0.043
 baby+0.042
 Teddy+0.040
 tightly+0.040
Neg logit contributions
aris-0.090
ues-0.087
aw-0.085
oke-0.085
ari-0.084
Token surface
Token ID4417
Feature activation-1.02e+00

Pos logit contributions
 thumb+0.019
 mummy+0.015
 baby+0.015
 Sister+0.015
 Teddy+0.015
Neg logit contributions
aris-0.024
aw-0.024
ues-0.023
lic-0.022
oke-0.021
Token of
Token ID286
Feature activation-1.53e-01

Pos logit contributions
 thumb+0.024
 mummy+0.020
 baby+0.020
 Teddy+0.019
 Baby+0.019
Neg logit contributions
aris-0.030
aw-0.029
ues-0.028
hatt-0.027
oke-0.026
Token the
Token ID262
Feature activation-3.09e-01

Pos logit contributions
 thumb+0.003
 mummy+0.002
 baby+0.002
 Teddy+0.002
 Sister+0.002
Neg logit contributions
aris-0.006
aw-0.006
ues-0.005
oke-0.005
lic-0.005
Token water
Token ID1660
Feature activation-6.25e-01

Pos logit contributions
 thumb+0.008
 mummy+0.007
 baby+0.007
 Sister+0.006
 Teddy+0.006
Neg logit contributions
aris-0.009
aw-0.008
ues-0.008
lic-0.008
oke-0.008
Token time
Token ID640
Feature activation+1.36e+00

Pos logit contributions
aris+0.046
aw+0.046
ues+0.044
lic+0.041
oke+0.041
Neg logit contributions
 thumb-0.045
 mummy-0.038
 Sister-0.038
 Teddy-0.038
 baby-0.038
Token,
Token ID11
Feature activation-1.04e-01

Pos logit contributions
aw+0.044
aris+0.043
ues+0.041
lic+0.039
hatt+0.039
Neg logit contributions
 thumb-0.028
 mummy-0.024
 Teddy-0.024
 baby-0.023
 Sister-0.023
Token there
Token ID612
Feature activation-4.27e-01

Pos logit contributions
 thumb+0.003
 Sister+0.003
 mummy+0.002
 Teddy+0.002
 Ginny+0.002
Neg logit contributions
aw-0.002
aris-0.002
ues-0.002
oke-0.002
lic-0.002
Token was
Token ID373
Feature activation-7.57e-01

Pos logit contributions
 thumb+0.012
 Sister+0.011
 mummy+0.010
 Teddy+0.010
 Ginny+0.010
Neg logit contributions
aw-0.010
aris-0.010
ues-0.009
oke-0.009
hatt-0.009
Token a
Token ID257
Feature activation-1.21e+00

Pos logit contributions
 thumb+0.021
 Sister+0.018
bing+0.017
 ankle+0.017
 mummy+0.017
Neg logit contributions
aw-0.020
aris-0.017
hatt-0.016
lic-0.015
eh-0.015
Token little
Token ID1310
Feature activation-2.24e+00

Pos logit contributions
 thumb+0.020
 Sister+0.016
 Teddy+0.015
 mummy+0.015
 Ginny+0.015
Neg logit contributions
aw-0.042
aris-0.041
ues-0.039
lic-0.039
oke-0.038
Token girl
Token ID2576
Feature activation+2.08e-01

Pos logit contributions
 thumb+0.051
 Sister+0.044
 mummy+0.043
 Teddy+0.043
 Ginny+0.042
Neg logit contributions
aw-0.065
aris-0.062
ues-0.057
oke-0.056
lic-0.055
Token named
Token ID3706
Feature activation+1.55e-01

Pos logit contributions
aris+0.004
aw+0.004
ues+0.004
lic+0.004
oke+0.004
Neg logit contributions
 thumb-0.007
 mummy-0.006
 Teddy-0.006
 Sister-0.006
 baby-0.006
Token Lily
Token ID20037
Feature activation-1.32e+00

Pos logit contributions
aris+0.004
aw+0.004
ues+0.004
lic+0.003
hatt+0.003
Neg logit contributions
 thumb-0.004
 Sister-0.004
 mummy-0.004
 Teddy-0.003
 baby-0.003
Token.
Token ID13
Feature activation-1.46e+00

Pos logit contributions
 thumb+0.038
 Sister+0.033
 mummy+0.033
 Teddy+0.033
 baby+0.032
Neg logit contributions
aw-0.032
aris-0.031
ues-0.029
hatt-0.027
lic-0.027
Token She
Token ID1375
Feature activation-2.88e-01

Pos logit contributions
 thumb+0.038
 Sister+0.032
 mummy+0.031
 baby+0.031
 Ginny+0.030
Neg logit contributions
aris-0.039
aw-0.038
ues-0.035
lic-0.034
hatt-0.034
Token some
Token ID617
Feature activation-1.11e+00

Pos logit contributions
 thumb+0.009
 mummy+0.008
 Teddy+0.007
 Sister+0.007
 baby+0.007
Neg logit contributions
aw-0.017
aris-0.017
ues-0.016
oke-0.015
lic-0.015
Token food
Token ID2057
Feature activation-1.68e+00

Pos logit contributions
 thumb+0.029
 Sister+0.025
 Teddy+0.024
 mummy+0.024
 baby+0.023
Neg logit contributions
aw-0.030
aris-0.029
ues-0.027
lic-0.026
hatt-0.025
Token to
Token ID284
Feature activation-1.34e+00

Pos logit contributions
 thumb+0.035
 Teddy+0.031
 mummy+0.030
 baby+0.029
 Sister+0.028
Neg logit contributions
aris-0.054
aw-0.053
ues-0.051
hatt-0.049
oke-0.049
Token eat
Token ID4483
Feature activation-1.82e+00

Pos logit contributions
 thumb+0.032
 Sister+0.027
 mummy+0.026
 Teddy+0.026
 baby+0.025
Neg logit contributions
aw-0.038
aris-0.038
ues-0.036
lic-0.034
hatt-0.034
Token.
Token ID13
Feature activation-3.94e-02

Pos logit contributions
 thumb+0.049
 mummy+0.042
 Teddy+0.042
 Sister+0.042
 baby+0.042
Neg logit contributions
aris-0.047
aw-0.047
ues-0.044
lic-0.041
oke-0.041
Token Fl
Token ID1610
Feature activation-3.07e+00

Pos logit contributions
 thumb+0.001
 mummy+0.001
 Sister+0.001
 Teddy+0.001
 baby+0.001
Neg logit contributions
aw-0.001
aris-0.001
ues-0.001
lic-0.001
oke-0.001
Tokenuffy
Token ID15352
Feature activation-1.06e+00

Pos logit contributions
 thumb+0.085
 Sister+0.074
 mummy+0.073
 Teddy+0.073
 baby+0.072
Neg logit contributions
aw-0.078
aris-0.077
ues-0.072
lic-0.067
oke-0.067
Token was
Token ID373
Feature activation-3.22e-01

Pos logit contributions
 thumb+0.026
 mummy+0.022
 Sister+0.022
 Teddy+0.022
 baby+0.022
Neg logit contributions
aw-0.030
aris-0.029
ues-0.028
lic-0.026
oke-0.026
Token happy
Token ID3772
Feature activation-6.71e-01

Pos logit contributions
 thumb+0.009
 Sister+0.008
 Teddy+0.007
 mummy+0.007
bing+0.007
Neg logit contributions
aw-0.008
lic-0.007
aris-0.007
ues-0.007
ks-0.007
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
 thumb+0.014
 Teddy+0.012
 mummy+0.012
 baby+0.011
 Sister+0.011
Neg logit contributions
aris-0.022
aw-0.022
ues-0.021
lic-0.020
hatt-0.020
Token started
Token ID2067
Feature activation+2.17e-01

Pos logit contributions
aw+0.003
aris+0.003
ues+0.003
lic+0.003
hatt+0.002
Neg logit contributions
 thumb-0.003
 Sister-0.002
 mummy-0.002
 Teddy-0.002
 baby-0.002
Token.
Token ID13
Feature activation-4.41e-01

Pos logit contributions
aris+0.022
oke+0.022
lic+0.021
ues+0.021
rets+0.021
Neg logit contributions
 thumb-0.012
 baby-0.011
 mummy-0.010
 tightly-0.009
 arm-0.009
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
 thumb+0.007
 Teddy+0.007
 mummy+0.007
 Sister+0.007
 Baby+0.007
Neg logit contributions
aw-0.016
ues-0.015
aris-0.015
lic-0.015
oke-0.014
Token
Token ID198
Feature activation-9.61e-01

Pos logit contributions
aw+0.003
aris+0.003
ues+0.003
oke+0.003
hatt+0.003
Neg logit contributions
 thumb-0.002
 mummy-0.002
 Teddy-0.002
 baby-0.002
 Sister-0.002
TokenOne
Token ID3198
Feature activation+9.97e-01

Pos logit contributions
 thumb+0.017
 mummy+0.015
 baby+0.015
 Teddy+0.014
Mom+0.014
Neg logit contributions
aris-0.033
aw-0.032
ues-0.031
oke-0.030
 facts-0.028
Token day
Token ID1110
Feature activation-3.45e-01

Pos logit contributions
aris+0.029
aw+0.029
ues+0.028
lic+0.026
oke+0.025
Neg logit contributions
 thumb-0.025
 mummy-0.021
 baby-0.021
 Sister-0.021
 Baby-0.020
Token when
Token ID618
Feature activation-3.07e+00

Pos logit contributions
 thumb+0.007
 mummy+0.006
 Teddy+0.006
 Sister+0.006
 baby+0.006
Neg logit contributions
aris-0.011
aw-0.011
ues-0.010
lic-0.010
hatt-0.010
Token they
Token ID484
Feature activation-5.58e-01

Pos logit contributions
 thumb+0.088
 Sister+0.073
 Teddy+0.071
 Ginny+0.070
 mummy+0.069
Neg logit contributions
aw-0.071
aris-0.069
ues-0.061
hatt-0.061
 contest-0.059
Token arrived
Token ID5284
Feature activation-5.38e-01

Pos logit contributions
 thumb+0.014
 Sister+0.012
 Teddy+0.012
 mummy+0.012
 Midnight+0.012
Neg logit contributions
aw-0.015
aris-0.014
lic-0.013
oke-0.013
ues-0.013
Token at
Token ID379
Feature activation+2.06e-01

Pos logit contributions
 thumb+0.015
 Sister+0.013
 mummy+0.013
 Teddy+0.012
 baby+0.012
Neg logit contributions
aw-0.014
aris-0.014
ues-0.013
oke-0.012
lic-0.012
Token the
Token ID262
Feature activation+1.32e+00

Pos logit contributions
aw+0.006
aris+0.006
ues+0.006
hatt+0.006
eway+0.006
Neg logit contributions
 thumb-0.004
 Sister-0.003
 mummy-0.003
 Ginny-0.003
 Teddy-0.003
Token mill
Token ID3939
Feature activation+2.02e+00

Pos logit contributions
aw+0.029
aris+0.028
ues+0.026
lic+0.024
hatt+0.024
Neg logit contributions
 thumb-0.041
 mummy-0.036
 Sister-0.036
 Teddy-0.036
 baby-0.035