TOP ACTIVATIONS
MAX = 0.082

They are better than the old ones . They
wasn 't sure what the old woman meant , but she
It works better than the old one . Have a nice
It is better than the old one ." Mom
couldn 't believe what the old anchor had taught her .
back on the zip - line , z ipping all around
interesting things about the unknown ear . He still visits it
table is better than the old one ," said the son
brighter and better than the old gate . The old man
coming from inside the unknown ear . It was a very
to deliver it to the kindergarten , but it fell out
was interested in what the old man had to say and
ocked even louder than the old one . Lily was so
lo vel ier than my old net !" M
saw the great big Fer ris wheel and all the other
becoming a lawyer and was naturally talented at it .
he didn 't want the old man to know that .
kisses , just like the first time when mom received the
bigger and brighter than the first one . She smiled and
blue shells . The her mit crab was so excited !

MIN ACTIVATIONS
MIN = -0.078

time , there was a y ummy place filled with lots
that the net held a y ummy nut ! He grabbed
. He thought it looked y ummy and wanted to try
bag . It was a y ummy cookie . Spot wanted
snack . They ate a y ummy treat to give them
. He thought it looked y ummy , so he tried
smelled funny and turned a y ucky colour .
Tweet ie thought it looked y ummy , but it was
boy . He saw a y ummy cel ery on the
Inside the bone was a y ummy sausage .
time , there was a y ummy cake . It was
cone . It looked so y ummy that she asked if
ball . It was so boun cy and fun to play
time , there was a y ummy treat . It was
day , she smelled something y ummy coming from the kitchen
treat . It was a y ummy cookie , all soft
Her grandma made her a y ummy cake . Lily loved
Tim 's mom made a y ummy steak for dinner .
Once , there was a y ummy books he lf in
. He thought it looked y ummy . He smiled and

INTERVAL 0.042 - 0.082
CONTAINS 0.201%

One day , the bald man was walking down the
He 's better than your old toy . You don 't
and most beautiful tree Lily had ever seen . She was
was very curious . He had bright eyes with sharp pupils
. Ch ant elle smiled and said , "

INTERVAL 0.002 - 0.042
CONTAINS 43.218%

watched . Soon , she had gathered a whole bag full
he loved to play on . One day J ax had
of you ," Mom said . " Thank you
. But on their way home , they got into a
and was now running towards them . L

INTERVAL -0.038 - 0.002
CONTAINS 56.264%

climb on top of it . But when he
decided to take a walk around the park . Joey looked
the rain drops with his tongue and jumped in all the
One day , the farmer was too busy to take the
sees her fall and runs after her . He is scared

INTERVAL -0.078 - -0.038
CONTAINS 0.317%

my and took the car from him . She sc olded
together every day and always helped each other when they needed
big missile that can shoot from a launcher .
Tim my poured himself a bowl of cereal and sat down
They laughed and cl apped their hands when they finished their
Token They
Token ID1119
Feature activation-4.57e-03

Pos logit contributions
one+0.015
 wizard+0.013
lor+0.013
uan+0.013
 robe+0.013
Neg logit contributions
 cartoons-0.011
Deal-0.011
girls-0.011
idents-0.009
 inviting-0.009
Token are
Token ID389
Feature activation-5.24e-03

Pos logit contributions
Deal+0.008
 cartoons+0.008
idents+0.008
girls+0.008
icious+0.008
Neg logit contributions
one-0.007
 wizard-0.006
 robe-0.006
uan-0.006
 ago-0.005
Token better
Token ID1365
Feature activation+1.45e-02

Pos logit contributions
Deal+0.008
 cartoons+0.008
idents+0.008
girls+0.007
icious+0.007
Neg logit contributions
one-0.009
 wizard-0.008
uan-0.008
 ago-0.008
 robe-0.008
Token than
Token ID621
Feature activation-7.71e-03

Pos logit contributions
one+0.028
uan+0.024
lor+0.024
 wizard+0.023
enna+0.022
Neg logit contributions
Deal-0.021
 cartoons-0.021
girls-0.020
boys-0.018
idents-0.018
Token the
Token ID262
Feature activation+3.31e-02

Pos logit contributions
Deal+0.013
 cartoons+0.012
girls+0.012
idents+0.012
icious+0.012
Neg logit contributions
one-0.013
 wizard-0.011
uan-0.011
 ago-0.011
em-0.010
Token old
Token ID1468
Feature activation+8.24e-02

Pos logit contributions
one+0.049
uan+0.039
lor+0.039
 wizard+0.039
em+0.037
Neg logit contributions
Deal-0.063
 cartoons-0.063
girls-0.059
idents-0.056
icious-0.055
Token ones
Token ID3392
Feature activation+1.59e-02

Pos logit contributions
one+0.136
uan+0.118
lor+0.116
alks+0.113
ittle+0.112
Neg logit contributions
 cartoons-0.140
Deal-0.139
idents-0.122
girls-0.121
 forth-0.120
Token.
Token ID13
Feature activation+5.04e-03

Pos logit contributions
one+0.024
 wizard+0.020
uan+0.019
 ago+0.019
lor+0.018
Neg logit contributions
 cartoons-0.030
Deal-0.030
girls-0.028
idents-0.027
icious-0.027
Token
Token ID198
Feature activation+9.72e-03

Pos logit contributions
one+0.009
 wizard+0.008
lor+0.008
uan+0.008
 robe+0.007
Neg logit contributions
 cartoons-0.008
Deal-0.008
girls-0.008
idents-0.007
 inviting-0.007
Token
Token ID198
Feature activation+1.10e-02

Pos logit contributions
one+0.011
 wizard+0.009
uan+0.009
lor+0.008
 robe+0.008
Neg logit contributions
Deal-0.021
 cartoons-0.021
girls-0.020
idents-0.020
icious-0.019
TokenThey
Token ID2990
Feature activation-8.79e-04

Pos logit contributions
one+0.023
 wizard+0.019
uan+0.019
lor+0.019
em+0.018
Neg logit contributions
 cartoons-0.015
Deal-0.015
girls-0.014
idents-0.014
 forth-0.012
Token wasn
Token ID2492
Feature activation+5.16e-03

Pos logit contributions
one+0.049
uan+0.042
alks+0.041
ooter+0.041
lor+0.041
Neg logit contributions
Deal-0.042
 cartoons-0.041
girls-0.038
 forth-0.037
boys-0.037
Token't
Token ID470
Feature activation+2.85e-02

Pos logit contributions
one+0.008
 wizard+0.006
uan+0.006
lor+0.006
 robe+0.006
Neg logit contributions
Deal-0.010
 cartoons-0.010
girls-0.009
idents-0.009
icious-0.009
Token sure
Token ID1654
Feature activation+2.61e-02

Pos logit contributions
one+0.056
lor+0.056
anger+0.052
alks+0.050
ooter+0.050
Neg logit contributions
 cartoons-0.038
 inviting-0.033
 y-0.033
 forth-0.031
Deal-0.031
Token what
Token ID644
Feature activation-1.01e-02

Pos logit contributions
one+0.046
 wizard+0.039
uan+0.039
lor+0.038
 robe+0.037
Neg logit contributions
Deal-0.042
 cartoons-0.041
girls-0.039
idents-0.037
icious-0.035
Token the
Token ID262
Feature activation+3.53e-02

Pos logit contributions
Deal+0.021
 cartoons+0.020
girls+0.020
idents+0.019
icious+0.019
Neg logit contributions
one-0.014
 wizard-0.011
uan-0.011
 ago-0.010
lor-0.010
Token old
Token ID1468
Feature activation+7.86e-02

Pos logit contributions
one+0.050
uan+0.039
lor+0.039
 wizard+0.039
em+0.037
Neg logit contributions
 cartoons-0.070
Deal-0.070
girls-0.065
idents-0.063
icious-0.061
Token woman
Token ID2415
Feature activation+4.49e-02

Pos logit contributions
one+0.118
lor+0.100
uan+0.094
alks+0.092
ittle+0.091
Neg logit contributions
Deal-0.144
 cartoons-0.142
idents-0.127
 forth-0.125
 inviting-0.124
Token meant
Token ID4001
Feature activation+2.08e-02

Pos logit contributions
one+0.070
 wizard+0.058
uan+0.056
lor+0.054
ired+0.053
Neg logit contributions
 cartoons-0.082
Deal-0.082
girls-0.078
idents-0.074
icious-0.073
Token,
Token ID11
Feature activation+3.41e-03

Pos logit contributions
one+0.034
lor+0.029
uan+0.029
 wizard+0.029
 begg+0.028
Neg logit contributions
 cartoons-0.035
Deal-0.035
girls-0.032
idents-0.031
 inviting-0.030
Token but
Token ID475
Feature activation+1.89e-02

Pos logit contributions
one+0.006
 wizard+0.005
uan+0.005
lor+0.005
em+0.005
Neg logit contributions
Deal-0.006
 cartoons-0.006
girls-0.005
idents-0.005
icious-0.005
Token she
Token ID673
Feature activation+1.36e-02

Pos logit contributions
one+0.027
 wizard+0.022
uan+0.021
lor+0.020
ired+0.020
Neg logit contributions
 cartoons-0.037
Deal-0.037
girls-0.036
idents-0.034
icious-0.033
Token It
Token ID632
Feature activation-2.13e-02

Pos logit contributions
one+0.008
unk+0.007
uan+0.007
 wizard+0.006
em+0.006
Neg logit contributions
Deal-0.009
 cartoons-0.009
girls-0.008
idents-0.008
boys-0.007
Token works
Token ID2499
Feature activation-1.12e-02

Pos logit contributions
Deal+0.032
 cartoons+0.032
girls+0.030
idents+0.028
icious+0.027
Neg logit contributions
one-0.040
 wizard-0.034
uan-0.033
lor-0.033
ired-0.032
Token better
Token ID1365
Feature activation+1.17e-03

Pos logit contributions
Deal+0.020
 cartoons+0.019
girls+0.019
idents+0.018
icious+0.017
Neg logit contributions
one-0.019
 wizard-0.015
 ago-0.015
uan-0.015
lor-0.015
Token than
Token ID621
Feature activation-8.60e-03

Pos logit contributions
one+0.002
uan+0.002
 wizard+0.002
lor+0.002
 begg+0.002
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.002
 forth-0.002
Token the
Token ID262
Feature activation+2.69e-02

Pos logit contributions
 cartoons+0.014
Deal+0.012
girls+0.012
 inviting+0.011
idents+0.011
Neg logit contributions
one-0.016
lor-0.014
uan-0.014
 wizard-0.013
 robe-0.013
Token old
Token ID1468
Feature activation+7.69e-02

Pos logit contributions
one+0.041
lor+0.035
uan+0.035
orse+0.034
alks+0.033
Neg logit contributions
Deal-0.050
 cartoons-0.048
 y-0.043
 forth-0.043
idents-0.043
Token one
Token ID530
Feature activation+1.76e-02

Pos logit contributions
one+0.160
alks+0.151
uan+0.150
ann+0.149
ittle+0.148
Neg logit contributions
Deal-0.091
 cartoons-0.072
 forth-0.072
 games-0.066
idents-0.066
Token.
Token ID13
Feature activation+7.86e-03

Pos logit contributions
one+0.030
uan+0.026
lor+0.026
 wizard+0.025
 robe+0.025
Neg logit contributions
Deal-0.028
 cartoons-0.028
girls-0.026
idents-0.024
 forth-0.024
Token Have
Token ID8192
Feature activation+1.08e-02

Pos logit contributions
one+0.012
 wizard+0.011
unk+0.011
uan+0.010
 robe+0.010
Neg logit contributions
Deal-0.014
 cartoons-0.014
girls-0.013
idents-0.012
 inviting-0.012
Token a
Token ID257
Feature activation-9.24e-03

Pos logit contributions
one+0.020
 wizard+0.017
uan+0.017
lor+0.016
ired+0.016
Neg logit contributions
 cartoons-0.017
Deal-0.017
girls-0.016
idents-0.015
 inviting-0.014
Token nice
Token ID3621
Feature activation+1.36e-02

Pos logit contributions
Deal+0.013
 cartoons+0.013
girls+0.012
idents+0.011
icious+0.011
Neg logit contributions
one-0.018
 wizard-0.016
uan-0.015
lor-0.015
 robe-0.015
Token It
Token ID632
Feature activation-1.36e-02

Pos logit contributions
one+0.014
 wizard+0.011
uan+0.011
lor+0.011
 robe+0.010
Neg logit contributions
Deal-0.019
 cartoons-0.019
girls-0.018
idents-0.017
icious-0.017
Token is
Token ID318
Feature activation-9.71e-03

Pos logit contributions
Deal+0.023
 cartoons+0.023
girls+0.021
idents+0.020
icious+0.020
Neg logit contributions
one-0.023
 wizard-0.020
uan-0.019
lor-0.019
 robe-0.018
Token better
Token ID1365
Feature activation+1.50e-02

Pos logit contributions
Deal+0.016
 cartoons+0.015
girls+0.015
idents+0.014
icious+0.014
Neg logit contributions
one-0.017
 wizard-0.014
uan-0.014
 ago-0.014
em-0.013
Token than
Token ID621
Feature activation-1.07e-02

Pos logit contributions
one+0.031
uan+0.027
lor+0.027
 wizard+0.026
enna+0.026
Neg logit contributions
Deal-0.020
 cartoons-0.020
girls-0.019
idents-0.017
 inviting-0.017
Token the
Token ID262
Feature activation+2.78e-02

Pos logit contributions
 cartoons+0.017
Deal+0.016
girls+0.015
idents+0.014
 inviting+0.014
Neg logit contributions
one-0.019
lor-0.017
uan-0.017
 wizard-0.017
 robe-0.016
Token old
Token ID1468
Feature activation+7.60e-02

Pos logit contributions
one+0.041
uan+0.033
lor+0.033
 wizard+0.032
em+0.031
Neg logit contributions
 cartoons-0.053
Deal-0.053
girls-0.050
idents-0.047
 forth-0.046
Token one
Token ID530
Feature activation+1.82e-02

Pos logit contributions
one+0.122
lor+0.106
uan+0.106
em+0.105
ittle+0.101
Neg logit contributions
 cartoons-0.131
Deal-0.119
 forth-0.118
idents-0.109
girls-0.109
Token."
Token ID526
Feature activation+9.30e-03

Pos logit contributions
one+0.032
lor+0.029
uan+0.029
 wizard+0.027
 robe+0.027
Neg logit contributions
 cartoons-0.028
Deal-0.028
girls-0.025
 forth-0.023
 y-0.023
Token
Token ID198
Feature activation+5.69e-03

Pos logit contributions
one+0.013
 wizard+0.010
lor+0.010
uan+0.010
ired+0.009
Neg logit contributions
Deal-0.019
 cartoons-0.019
girls-0.018
idents-0.017
 inviting-0.017
Token
Token ID198
Feature activation+9.82e-03

Pos logit contributions
one+0.007
 wizard+0.005
uan+0.005
lor+0.005
 robe+0.005
Neg logit contributions
 cartoons-0.012
Deal-0.012
girls-0.012
idents-0.011
 inviting-0.011
TokenMom
Token ID29252
Feature activation-1.60e-02

Pos logit contributions
one+0.020
 wizard+0.017
uan+0.017
lor+0.017
 robe+0.016
Neg logit contributions
 cartoons-0.013
Deal-0.013
girls-0.012
idents-0.012
icious-0.011
Token couldn
Token ID3521
Feature activation+5.80e-03

Pos logit contributions
one+0.051
ooter+0.041
uan+0.041
alks+0.040
anger+0.040
Neg logit contributions
girls-0.036
Deal-0.035
boys-0.035
 cartoons-0.034
 inviting-0.032
Token't
Token ID470
Feature activation+3.95e-02

Pos logit contributions
one+0.010
uan+0.009
 wizard+0.009
 robe+0.009
enna+0.008
Neg logit contributions
 cartoons-0.009
Deal-0.009
girls-0.008
idents-0.008
icious-0.008
Token believe
Token ID1975
Feature activation+1.51e-02

Pos logit contributions
one+0.072
uan+0.062
lor+0.062
 wizard+0.059
em+0.059
Neg logit contributions
Deal-0.061
 cartoons-0.061
girls-0.057
idents-0.054
icious-0.052
Token what
Token ID644
Feature activation+2.29e-04

Pos logit contributions
one+0.027
 wizard+0.022
uan+0.022
lor+0.022
 robe+0.021
Neg logit contributions
Deal-0.024
 cartoons-0.024
girls-0.023
idents-0.022
icious-0.021
Token the
Token ID262
Feature activation+3.53e-02

Pos logit contributions
one+0.000
uan+0.000
lor+0.000
ooter+0.000
 wizard+0.000
Neg logit contributions
Deal-0.000
 cartoons-0.000
girls-0.000
 inviting-0.000
 y-0.000
Token old
Token ID1468
Feature activation+7.58e-02

Pos logit contributions
one+0.066
lor+0.064
enny+0.060
enna+0.059
utch+0.058
Neg logit contributions
 y-0.048
 inviting-0.048
Deal-0.048
 cartoons-0.047
 delicious-0.044
Token anchor
Token ID18021
Feature activation+3.16e-02

Pos logit contributions
one+0.155
ume+0.145
lor+0.142
reetings+0.136
enny+0.136
Neg logit contributions
Deal-0.090
 y-0.082
 forth-0.077
 inviting-0.077
idents-0.074
Token had
Token ID550
Feature activation+2.51e-02

Pos logit contributions
one+0.055
uan+0.046
lor+0.045
alks+0.044
 wizard+0.044
Neg logit contributions
Deal-0.051
 cartoons-0.049
girls-0.047
idents-0.044
boys-0.044
Token taught
Token ID7817
Feature activation+1.59e-03

Pos logit contributions
one+0.041
 wizard+0.038
alks+0.037
ooter+0.037
uan+0.037
Neg logit contributions
Deal-0.037
 together-0.036
 y-0.035
 inviting-0.034
 both-0.034
Token her
Token ID607
Feature activation+1.89e-03

Pos logit contributions
one+0.003
 wizard+0.003
uan+0.003
lor+0.002
 robe+0.002
Neg logit contributions
 cartoons-0.002
Deal-0.002
girls-0.002
idents-0.002
icious-0.002
Token.
Token ID13
Feature activation+4.13e-03

Pos logit contributions
one+0.003
uan+0.003
 wizard+0.003
lor+0.003
 robe+0.003
Neg logit contributions
 cartoons-0.003
Deal-0.003
girls-0.003
idents-0.003
 inviting-0.003
Token back
Token ID736
Feature activation-6.09e-03

Pos logit contributions
one+0.002
 wizard+0.002
uan+0.002
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.002
icious-0.002
Token on
Token ID319
Feature activation+5.58e-03

Pos logit contributions
 cartoons+0.010
Deal+0.010
girls+0.010
idents+0.009
 forth+0.009
Neg logit contributions
one-0.010
lor-0.008
uan-0.008
 wizard-0.008
 begg-0.008
Token the
Token ID262
Feature activation-1.70e-03

Pos logit contributions
one+0.008
 wizard+0.007
uan+0.006
 robe+0.006
lor+0.006
Neg logit contributions
Deal-0.011
 cartoons-0.010
girls-0.010
idents-0.010
icious-0.010
Token zip
Token ID19974
Feature activation+3.89e-02

Pos logit contributions
 cartoons+0.003
Deal+0.003
girls+0.003
idents+0.002
 inviting+0.002
Neg logit contributions
one-0.003
uan-0.002
lor-0.002
ired-0.002
 wizard-0.002
Token-
Token ID12
Feature activation-1.35e-02

Pos logit contributions
one+0.069
uan+0.058
lor+0.056
 wizard+0.056
reetings+0.055
Neg logit contributions
 cartoons-0.059
Deal-0.056
girls-0.053
 forth-0.051
boys-0.051
Tokenline
Token ID1370
Feature activation+7.58e-02

Pos logit contributions
Deal+0.027
 cartoons+0.025
girls+0.024
aghetti+0.023
icious+0.023
Neg logit contributions
one-0.015
 ago-0.014
 robe-0.014
 wizard-0.014
 begg-0.014
Token,
Token ID11
Feature activation+4.61e-03

Pos logit contributions
one+0.137
lor+0.120
uan+0.117
 begg+0.116
 wizard+0.114
Neg logit contributions
 cartoons-0.110
Deal-0.106
girls-0.097
 forth-0.095
idents-0.095
Token z
Token ID1976
Feature activation+2.33e-02

Pos logit contributions
one+0.008
lor+0.007
uan+0.007
 wizard+0.006
ired+0.006
Neg logit contributions
 cartoons-0.008
Deal-0.008
girls-0.007
idents-0.007
 inviting-0.007
Tokenipping
Token ID4501
Feature activation+1.05e-02

Pos logit contributions
one+0.040
 ago+0.034
 stub+0.033
 wizard+0.032
enna+0.032
Neg logit contributions
Deal-0.038
icious-0.032
idents-0.031
 cartoons-0.031
 forth-0.031
Token all
Token ID477
Feature activation-1.98e-03

Pos logit contributions
one+0.018
 wizard+0.015
uan+0.015
lor+0.015
 robe+0.015
Neg logit contributions
Deal-0.017
 cartoons-0.017
girls-0.016
idents-0.015
icious-0.015
Token around
Token ID1088
Feature activation+5.25e-03

Pos logit contributions
 cartoons+0.003
Deal+0.003
girls+0.003
 forth+0.003
 inviting+0.003
Neg logit contributions
one-0.004
lor-0.003
 wizard-0.003
uan-0.003
 robe-0.003
Token interesting
Token ID3499
Feature activation+2.70e-03

Pos logit contributions
Deal+0.051
girls+0.047
 cartoons+0.047
idents+0.046
icious+0.044
Neg logit contributions
one-0.054
 wizard-0.047
uan-0.044
ired-0.043
 ago-0.043
Token things
Token ID1243
Feature activation-1.37e-02

Pos logit contributions
one+0.005
uan+0.005
lor+0.005
 wizard+0.005
em+0.005
Neg logit contributions
 cartoons-0.004
Deal-0.004
girls-0.003
idents-0.003
 inviting-0.003
Token about
Token ID546
Feature activation-6.62e-03

Pos logit contributions
Deal+0.024
 cartoons+0.024
girls+0.023
idents+0.022
icious+0.021
Neg logit contributions
one-0.022
 wizard-0.018
uan-0.018
lor-0.017
 robe-0.017
Token the
Token ID262
Feature activation+8.32e-04

Pos logit contributions
Deal+0.010
 cartoons+0.010
girls+0.009
idents+0.009
icious+0.009
Neg logit contributions
one-0.012
 wizard-0.010
uan-0.010
lor-0.010
 ago-0.010
Token unknown
Token ID6439
Feature activation+3.21e-02

Pos logit contributions
one+0.001
 wizard+0.001
 robe+0.001
 ago+0.001
uan+0.001
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.001
icious-0.001
Token ear
Token ID1027
Feature activation+7.57e-02

Pos logit contributions
one+0.052
lor+0.044
uan+0.044
em+0.043
 begg+0.042
Neg logit contributions
 cartoons-0.055
Deal-0.052
girls-0.049
 inviting-0.048
idents-0.048
Token.
Token ID13
Feature activation-5.25e-03

Pos logit contributions
one+0.137
 begg+0.129
uan+0.122
 wizard+0.121
 Dale+0.121
Neg logit contributions
 cartoons-0.098
girls-0.093
boys-0.087
Deal-0.087
 together-0.086
Token He
Token ID679
Feature activation-2.41e-03

Pos logit contributions
Deal+0.008
girls+0.008
 cartoons+0.008
idents+0.008
 inviting+0.007
Neg logit contributions
one-0.009
 robe-0.008
 begg-0.008
 wizard-0.008
 stub-0.008
Token still
Token ID991
Feature activation-2.88e-03

Pos logit contributions
Deal+0.004
 cartoons+0.004
girls+0.004
 inviting+0.004
boys+0.004
Neg logit contributions
one-0.004
lor-0.003
uan-0.003
 wizard-0.003
em-0.003
Token visits
Token ID11864
Feature activation-8.74e-03

Pos logit contributions
Deal+0.005
 cartoons+0.005
girls+0.004
idents+0.004
 inviting+0.004
Neg logit contributions
one-0.005
lor-0.004
uan-0.004
em-0.004
anger-0.004
Token it
Token ID340
Feature activation-8.92e-03

Pos logit contributions
 cartoons+0.014
Deal+0.014
girls+0.014
idents+0.013
 inviting+0.012
Neg logit contributions
one-0.015
uan-0.012
 wizard-0.012
lor-0.012
ired-0.012
Token table
Token ID3084
Feature activation+7.62e-03

Pos logit contributions
one+0.045
uan+0.038
 wizard+0.038
lor+0.038
em+0.036
Neg logit contributions
 cartoons-0.039
Deal-0.039
girls-0.036
idents-0.034
icious-0.033
Token is
Token ID318
Feature activation-1.95e-02

Pos logit contributions
one+0.011
 wizard+0.008
 arrived+0.008
 ago+0.008
ired+0.008
Neg logit contributions
 cartoons-0.015
girls-0.014
Deal-0.014
icious-0.013
ksh-0.013
Token better
Token ID1365
Feature activation+1.07e-03

Pos logit contributions
Deal+0.036
girls+0.036
 cartoons+0.034
idents+0.032
icious+0.032
Neg logit contributions
one-0.030
 wizard-0.024
 ago-0.024
 arrived-0.023
em-0.023
Token than
Token ID621
Feature activation-1.18e-02

Pos logit contributions
one+0.002
 wizard+0.001
 ago+0.001
uan+0.001
ired+0.001
Neg logit contributions
 cartoons-0.002
Deal-0.002
girls-0.002
icious-0.002
idents-0.002
Token the
Token ID262
Feature activation+2.75e-02

Pos logit contributions
 cartoons+0.019
Deal+0.018
girls+0.017
idents+0.017
 inviting+0.017
Neg logit contributions
one-0.021
lor-0.018
uan-0.018
 wizard-0.017
 robe-0.017
Token old
Token ID1468
Feature activation+7.55e-02

Pos logit contributions
one+0.037
 wizard+0.034
 ago+0.031
 aid+0.030
 robe+0.030
Neg logit contributions
Deal-0.056
girls-0.053
 cartoons-0.050
icious-0.050
idents-0.049
Token one
Token ID530
Feature activation+1.40e-02

Pos logit contributions
one+0.123
lor+0.104
uan+0.100
ooter+0.098
reetings+0.094
Neg logit contributions
 cartoons-0.134
Deal-0.126
idents-0.120
girls-0.119
boys-0.114
Token,"
Token ID553
Feature activation+1.99e-03

Pos logit contributions
one+0.024
 wizard+0.020
uan+0.020
lor+0.020
 robe+0.019
Neg logit contributions
Deal-0.023
 cartoons-0.023
girls-0.022
idents-0.021
icious-0.020
Token said
Token ID531
Feature activation+2.42e-02

Pos logit contributions
one+0.003
 wizard+0.003
uan+0.002
 robe+0.002
 begg+0.002
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.003
icious-0.003
idents-0.003
Token the
Token ID262
Feature activation+1.29e-02

Pos logit contributions
one+0.041
 wizard+0.034
uan+0.034
lor+0.033
 robe+0.032
Neg logit contributions
Deal-0.041
 cartoons-0.041
girls-0.038
idents-0.036
icious-0.035
Token son
Token ID3367
Feature activation+2.12e-02

Pos logit contributions
one+0.012
 wizard+0.012
 begg+0.010
 robe+0.010
uan+0.010
Neg logit contributions
Deal-0.031
girls-0.029
 cartoons-0.028
icious-0.028
idents-0.028
Token brighter
Token ID26083
Feature activation+5.31e-03

Pos logit contributions
Deal+0.022
girls+0.021
 cartoons+0.020
idents+0.019
boys+0.019
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.015
 ago-0.015
em-0.014
Token and
Token ID290
Feature activation-2.38e-02

Pos logit contributions
one+0.010
uan+0.008
 wizard+0.008
lor+0.008
ooter+0.008
Neg logit contributions
 cartoons-0.008
Deal-0.008
girls-0.008
idents-0.007
 forth-0.007
Token better
Token ID1365
Feature activation-9.93e-04

Pos logit contributions
girls+0.039
Deal+0.037
 cartoons+0.037
idents+0.034
icious+0.033
Neg logit contributions
one-0.043
 wizard-0.037
 begg-0.034
 arrived-0.034
uan-0.033
Token than
Token ID621
Feature activation-9.84e-03

Pos logit contributions
Deal+0.002
 cartoons+0.002
girls+0.002
idents+0.001
 forth+0.001
Neg logit contributions
one-0.002
uan-0.001
 wizard-0.001
lor-0.001
em-0.001
Token the
Token ID262
Feature activation+2.34e-02

Pos logit contributions
 cartoons+0.017
Deal+0.015
girls+0.015
 inviting+0.014
idents+0.014
Neg logit contributions
one-0.016
lor-0.015
uan-0.014
unk-0.014
ooter-0.014
Token old
Token ID1468
Feature activation+7.42e-02

Pos logit contributions
one+0.037
lor+0.032
uan+0.031
orse+0.029
ired+0.028
Neg logit contributions
Deal-0.042
 cartoons-0.042
girls-0.039
idents-0.038
 forth-0.036
Token gate
Token ID8946
Feature activation+4.04e-02

Pos logit contributions
one+0.133
lor+0.124
uan+0.117
ittle+0.115
reetings+0.115
Neg logit contributions
Deal-0.107
 cartoons-0.105
idents-0.098
 forth-0.094
boys-0.090
Token.
Token ID13
Feature activation-2.24e-04

Pos logit contributions
one+0.067
 wizard+0.056
uan+0.056
lor+0.055
 robe+0.053
Neg logit contributions
Deal-0.068
 cartoons-0.068
girls-0.064
idents-0.060
icious-0.059
Token The
Token ID383
Feature activation+6.01e-03

Pos logit contributions
 cartoons+0.000
Deal+0.000
idents+0.000
girls+0.000
 inviting+0.000
Neg logit contributions
one-0.000
 robe-0.000
lor-0.000
 wizard-0.000
yl-0.000
Token old
Token ID1468
Feature activation+5.15e-02

Pos logit contributions
one+0.010
lor+0.009
uan+0.008
em+0.007
unk+0.007
Neg logit contributions
 cartoons-0.011
Deal-0.010
girls-0.010
 inviting-0.009
idents-0.009
Token man
Token ID582
Feature activation+9.92e-03

Pos logit contributions
one+0.104
lor+0.093
ume+0.086
elt+0.085
uan+0.085
Neg logit contributions
 cartoons-0.069
Deal-0.069
 forth-0.062
boys-0.060
idents-0.059
Token coming
Token ID2406
Feature activation+1.11e-02

Pos logit contributions
 cartoons+0.013
Deal+0.012
girls+0.012
 inviting+0.011
idents+0.011
Neg logit contributions
one-0.013
lor-0.011
uan-0.011
 wizard-0.011
em-0.011
Token from
Token ID422
Feature activation-3.30e-02

Pos logit contributions
one+0.019
 wizard+0.016
uan+0.015
lor+0.015
ired+0.014
Neg logit contributions
Deal-0.020
 cartoons-0.019
girls-0.018
idents-0.017
icious-0.017
Token inside
Token ID2641
Feature activation+1.52e-02

Pos logit contributions
Deal+0.058
 cartoons+0.058
girls+0.055
idents+0.052
icious+0.051
Neg logit contributions
one-0.053
 wizard-0.044
uan-0.043
lor-0.042
 robe-0.041
Token the
Token ID262
Feature activation+5.30e-03

Pos logit contributions
one+0.025
 wizard+0.021
uan+0.020
lor+0.020
 robe+0.019
Neg logit contributions
 cartoons-0.026
Deal-0.026
girls-0.025
idents-0.023
icious-0.023
Token unknown
Token ID6439
Feature activation+3.61e-02

Pos logit contributions
one+0.007
 wizard+0.006
 robe+0.005
uan+0.005
 ago+0.005
Neg logit contributions
Deal-0.011
 cartoons-0.011
girls-0.010
idents-0.010
icious-0.010
Token ear
Token ID1027
Feature activation+7.40e-02

Pos logit contributions
one+0.065
uan+0.057
lor+0.056
enna+0.054
em+0.054
Neg logit contributions
 cartoons-0.056
Deal-0.052
girls-0.049
 inviting-0.048
idents-0.046
Token.
Token ID13
Feature activation+7.00e-03

Pos logit contributions
one+0.138
 begg+0.133
 wizard+0.132
 Dale+0.129
lyss+0.129
Neg logit contributions
 cartoons-0.083
girls-0.080
 together-0.077
Deal-0.073
boys-0.072
Token It
Token ID632
Feature activation-1.25e-02

Pos logit contributions
one+0.012
lor+0.012
 robe+0.011
fer+0.011
 begg+0.011
Neg logit contributions
Deal-0.010
idents-0.009
girls-0.009
 cartoons-0.009
 inviting-0.009
Token was
Token ID373
Feature activation+3.75e-03

Pos logit contributions
Deal+0.025
 cartoons+0.024
girls+0.023
idents+0.022
icious+0.022
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.014
lor-0.014
 arrived-0.013
Token a
Token ID257
Feature activation+1.38e-03

Pos logit contributions
one+0.005
 wizard+0.004
uan+0.004
lor+0.004
 robe+0.004
Neg logit contributions
Deal-0.007
 cartoons-0.007
girls-0.007
idents-0.007
icious-0.006
Token very
Token ID845
Feature activation-2.34e-02

Pos logit contributions
one+0.002
 wizard+0.002
 robe+0.002
uan+0.002
 begg+0.002
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.002
icious-0.002
Token to
Token ID284
Feature activation+3.43e-03

Pos logit contributions
one+0.054
lor+0.049
uan+0.049
 wizard+0.048
 begg+0.046
Neg logit contributions
 cartoons-0.067
Deal-0.061
idents-0.059
girls-0.059
 forth-0.058
Token deliver
Token ID5203
Feature activation+9.98e-03

Pos logit contributions
one+0.006
uan+0.005
 wizard+0.005
lor+0.005
em+0.005
Neg logit contributions
 cartoons-0.005
Deal-0.005
girls-0.005
idents-0.005
icious-0.005
Token it
Token ID340
Feature activation-1.57e-02

Pos logit contributions
one+0.016
 wizard+0.013
uan+0.013
lor+0.013
em+0.013
Neg logit contributions
Deal-0.018
 cartoons-0.017
girls-0.017
idents-0.016
icious-0.016
Token to
Token ID284
Feature activation-1.21e-02

Pos logit contributions
Deal+0.029
 cartoons+0.029
girls+0.028
idents+0.027
icious+0.026
Neg logit contributions
one-0.023
 wizard-0.019
uan-0.019
lor-0.018
 robe-0.018
Token the
Token ID262
Feature activation-4.87e-03

Pos logit contributions
Deal+0.021
 cartoons+0.020
girls+0.020
idents+0.019
icious+0.018
Neg logit contributions
one-0.019
 wizard-0.016
uan-0.016
lor-0.015
 robe-0.015
Token kindergarten
Token ID38717
Feature activation+7.39e-02

Pos logit contributions
Deal+0.009
 cartoons+0.009
girls+0.009
idents+0.008
icious+0.008
Neg logit contributions
one-0.007
 wizard-0.006
uan-0.006
 robe-0.006
lor-0.006
Token,
Token ID11
Feature activation+5.27e-03

Pos logit contributions
one+0.114
uan+0.093
alks+0.091
lor+0.090
 tal+0.090
Neg logit contributions
 cartoons-0.139
Deal-0.133
girls-0.122
idents-0.116
 inviting-0.114
Token but
Token ID475
Feature activation-2.53e-03

Pos logit contributions
one+0.009
 wizard+0.007
uan+0.007
lor+0.007
 robe+0.007
Neg logit contributions
Deal-0.009
 cartoons-0.009
girls-0.008
idents-0.008
icious-0.008
Token it
Token ID340
Feature activation-1.90e-03

Pos logit contributions
Deal+0.005
 cartoons+0.005
girls+0.004
icious+0.004
idents+0.004
Neg logit contributions
one-0.004
 wizard-0.003
uan-0.003
 ago-0.003
lor-0.003
Token fell
Token ID3214
Feature activation+1.22e-03

Pos logit contributions
 cartoons+0.004
Deal+0.004
girls+0.003
icious+0.003
idents+0.003
Neg logit contributions
one-0.003
 wizard-0.002
 arrived-0.002
uan-0.002
lor-0.002
Token out
Token ID503
Feature activation+8.06e-04

Pos logit contributions
one+0.002
 wizard+0.002
uan+0.002
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.002
icious-0.002
Token was
Token ID373
Feature activation+6.73e-03

Pos logit contributions
one+0.001
uan+0.001
 wizard+0.001
lor+0.001
alks+0.001
Neg logit contributions
Deal-0.001
 cartoons-0.001
girls-0.001
idents-0.001
boys-0.001
Token interested
Token ID4609
Feature activation-7.15e-03

Pos logit contributions
one+0.015
uan+0.013
lor+0.013
anger+0.013
alks+0.012
Neg logit contributions
 cartoons-0.008
Deal-0.008
 inviting-0.007
girls-0.007
 y-0.007
Token in
Token ID287
Feature activation+7.56e-03

Pos logit contributions
 cartoons+0.012
Deal+0.012
girls+0.012
idents+0.012
icious+0.011
Neg logit contributions
one-0.012
 wizard-0.010
uan-0.009
ired-0.009
 ago-0.009
Token what
Token ID644
Feature activation-3.46e-03

Pos logit contributions
one+0.013
uan+0.011
lor+0.011
 wizard+0.011
ooter+0.010
Neg logit contributions
 cartoons-0.013
Deal-0.012
girls-0.011
 inviting-0.011
idents-0.011
Token the
Token ID262
Feature activation+3.19e-02

Pos logit contributions
Deal+0.007
 cartoons+0.007
girls+0.006
idents+0.006
 inviting+0.006
Neg logit contributions
one-0.005
lor-0.004
uan-0.004
 wizard-0.004
 robe-0.004
Token old
Token ID1468
Feature activation+7.32e-02

Pos logit contributions
one+0.051
lor+0.044
uan+0.043
alks+0.041
em+0.040
Neg logit contributions
 cartoons-0.059
Deal-0.057
girls-0.051
 inviting-0.050
 y-0.049
Token man
Token ID582
Feature activation+2.64e-02

Pos logit contributions
one+0.140
lor+0.120
uan+0.120
alks+0.117
enna+0.114
Neg logit contributions
 cartoons-0.111
Deal-0.108
 y-0.092
 forth-0.091
idents-0.090
Token had
Token ID550
Feature activation+2.19e-02

Pos logit contributions
one+0.041
 wizard+0.034
uan+0.034
lor+0.033
 robe+0.032
Neg logit contributions
Deal-0.047
 cartoons-0.047
girls-0.045
idents-0.042
icious-0.041
Token to
Token ID284
Feature activation+1.76e-02

Pos logit contributions
one+0.039
alks+0.034
 wizard+0.034
lor+0.033
uan+0.033
Neg logit contributions
Deal-0.033
 cartoons-0.030
 together-0.029
 y-0.029
 inviting-0.029
Token say
Token ID910
Feature activation+3.39e-02

Pos logit contributions
one+0.032
 wizard+0.028
uan+0.027
lor+0.027
 robe+0.026
Neg logit contributions
Deal-0.027
 cartoons-0.027
girls-0.025
idents-0.024
icious-0.023
Token and
Token ID290
Feature activation+1.55e-02

Pos logit contributions
one+0.055
uan+0.045
 wizard+0.045
lor+0.044
 robe+0.042
Neg logit contributions
 cartoons-0.059
Deal-0.059
girls-0.055
idents-0.052
icious-0.051
Tokenocked
Token ID3543
Feature activation+2.27e-02

Pos logit contributions
 cartoons+0.036
Deal+0.033
girls+0.031
 inviting+0.030
idents+0.030
Neg logit contributions
one-0.033
 wizard-0.029
lor-0.029
uan-0.029
 robe-0.028
Token even
Token ID772
Feature activation-6.67e-03

Pos logit contributions
one+0.035
 wizard+0.028
uan+0.028
em+0.027
lor+0.027
Neg logit contributions
Deal-0.044
girls-0.041
 cartoons-0.041
idents-0.038
icious-0.038
Token louder
Token ID27089
Feature activation+7.23e-03

Pos logit contributions
Deal+0.010
girls+0.010
idents+0.009
 cartoons+0.009
boys+0.009
Neg logit contributions
one-0.013
 wizard-0.011
 aid-0.010
ired-0.010
uan-0.010
Token than
Token ID621
Feature activation-1.04e-02

Pos logit contributions
one+0.012
 wizard+0.010
uan+0.010
lor+0.010
 robe+0.010
Neg logit contributions
 cartoons-0.012
Deal-0.012
girls-0.011
idents-0.011
icious-0.011
Token the
Token ID262
Feature activation+2.38e-02

Pos logit contributions
 cartoons+0.018
Deal+0.018
girls+0.017
idents+0.016
icious+0.015
Neg logit contributions
one-0.017
 wizard-0.014
uan-0.014
lor-0.014
 robe-0.014
Token old
Token ID1468
Feature activation+7.29e-02

Pos logit contributions
one+0.041
 wizard+0.035
uan+0.033
 robe+0.032
ired+0.032
Neg logit contributions
Deal-0.040
girls-0.039
 cartoons-0.038
idents-0.036
boys-0.035
Token one
Token ID530
Feature activation+1.61e-02

Pos logit contributions
one+0.144
uan+0.129
lor+0.129
alks+0.124
 Dale+0.124
Neg logit contributions
 cartoons-0.102
Deal-0.098
idents-0.085
 forth-0.082
girls-0.081
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
one+0.026
 wizard+0.022
uan+0.022
lor+0.022
 robe+0.021
Neg logit contributions
Deal-0.028
 cartoons-0.028
girls-0.026
idents-0.025
icious-0.024
Token Lily
Token ID20037
Feature activation+1.77e-02

Pos logit contributions
Deal+0.021
 cartoons+0.021
girls+0.020
idents+0.019
 inviting+0.018
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.014
lor-0.014
 robe-0.014
Token was
Token ID373
Feature activation+4.56e-03

Pos logit contributions
one+0.029
 wizard+0.024
uan+0.024
lor+0.023
alks+0.023
Neg logit contributions
Deal-0.031
 cartoons-0.030
girls-0.029
idents-0.028
 forth-0.027
Token so
Token ID523
Feature activation+2.80e-03

Pos logit contributions
one+0.010
uan+0.009
lor+0.009
alks+0.009
anger+0.009
Neg logit contributions
 cartoons-0.005
Deal-0.005
 inviting-0.005
 y-0.004
 forth-0.004
Token lo
Token ID2376
Feature activation+7.25e-03

Pos logit contributions
Deal+0.041
girls+0.041
 cartoons+0.040
idents+0.037
boys+0.034
Neg logit contributions
one-0.060
 wizard-0.052
uan-0.047
ired-0.047
 begg-0.047
Tokenvel
Token ID626
Feature activation+5.95e-04

Pos logit contributions
one+0.013
 wizard+0.011
uan+0.011
lor+0.011
 robe+0.010
Neg logit contributions
 cartoons-0.012
Deal-0.011
girls-0.011
icious-0.011
idents-0.010
Tokenier
Token ID959
Feature activation+1.32e-02

Pos logit contributions
one+0.001
 wizard+0.001
uan+0.001
lor+0.001
 robe+0.001
Neg logit contributions
Deal-0.001
 cartoons-0.001
girls-0.001
idents-0.001
icious-0.001
Token than
Token ID621
Feature activation-1.00e-02

Pos logit contributions
one+0.024
uan+0.021
 wizard+0.020
lor+0.020
 robe+0.020
Neg logit contributions
 cartoons-0.020
Deal-0.020
girls-0.019
idents-0.018
 forth-0.017
Token my
Token ID616
Feature activation+4.21e-02

Pos logit contributions
 cartoons+0.016
Deal+0.016
girls+0.015
idents+0.014
icious+0.014
Neg logit contributions
one-0.018
uan-0.015
lor-0.015
 wizard-0.015
 robe-0.014
Token old
Token ID1468
Feature activation+7.24e-02

Pos logit contributions
one+0.059
uan+0.047
 wizard+0.046
lor+0.045
em+0.044
Neg logit contributions
Deal-0.084
 cartoons-0.083
girls-0.079
idents-0.077
boys-0.074
Token net
Token ID2010
Feature activation-2.29e-03

Pos logit contributions
one+0.114
uan+0.095
lor+0.090
em+0.089
ooter+0.085
Neg logit contributions
Deal-0.131
 cartoons-0.128
idents-0.121
girls-0.121
 forth-0.118
Token!"
Token ID2474
Feature activation+5.31e-03

Pos logit contributions
Deal+0.004
 cartoons+0.004
girls+0.004
idents+0.003
icious+0.003
Neg logit contributions
one-0.004
 wizard-0.003
uan-0.003
lor-0.003
 robe-0.003
Token
Token ID198
Feature activation+1.07e-03

Pos logit contributions
one+0.009
uan+0.007
 begg+0.006
 wizard+0.006
em+0.006
Neg logit contributions
Deal-0.010
 cartoons-0.010
girls-0.009
idents-0.009
 inviting-0.009
Token
Token ID198
Feature activation+4.66e-03

Pos logit contributions
one+0.002
 wizard+0.001
uan+0.001
lor+0.001
em+0.001
Neg logit contributions
 cartoons-0.002
Deal-0.002
girls-0.002
 inviting-0.002
idents-0.002
TokenM
Token ID44
Feature activation-2.27e-02

Pos logit contributions
one+0.008
 wizard+0.006
lor+0.006
uan+0.006
 robe+0.006
Neg logit contributions
 cartoons-0.008
Deal-0.008
girls-0.008
idents-0.007
icious-0.007
Token saw
Token ID2497
Feature activation-2.69e-03

Pos logit contributions
one+0.012
alks+0.010
lor+0.010
 wizard+0.009
uan+0.009
Neg logit contributions
 cartoons-0.012
Deal-0.012
girls-0.011
boys-0.011
 forth-0.010
Token the
Token ID262
Feature activation+5.48e-03

Pos logit contributions
 cartoons+0.005
Deal+0.005
girls+0.005
idents+0.004
 inviting+0.004
Neg logit contributions
one-0.004
 wizard-0.003
lor-0.003
uan-0.003
em-0.003
Token great
Token ID1049
Feature activation+4.58e-03

Pos logit contributions
one+0.009
 wizard+0.008
 robe+0.007
 begg+0.007
uan+0.007
Neg logit contributions
Deal-0.010
girls-0.009
 cartoons-0.009
idents-0.009
icious-0.008
Token big
Token ID1263
Feature activation-1.16e-02

Pos logit contributions
one+0.009
uan+0.007
lor+0.007
 wizard+0.007
alks+0.007
Neg logit contributions
 cartoons-0.007
Deal-0.007
girls-0.006
idents-0.006
 inviting-0.006
Token Fer
Token ID12880
Feature activation+1.65e-03

Pos logit contributions
Deal+0.022
 cartoons+0.021
girls+0.021
idents+0.019
icious+0.019
Neg logit contributions
one-0.017
 wizard-0.015
uan-0.014
 robe-0.014
 ago-0.013
Tokenris
Token ID2442
Feature activation+7.23e-02

Pos logit contributions
one+0.002
 wizard+0.002
uan+0.002
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.003
 cartoons-0.003
girls-0.003
icious-0.003
idents-0.003
Token wheel
Token ID7825
Feature activation+1.62e-02

Pos logit contributions
enna+0.113
one+0.111
uan+0.109
unk+0.105
reetings+0.104
Neg logit contributions
Deal-0.112
 forth-0.111
 cartoons-0.107
idents-0.102
 games-0.092
Token and
Token ID290
Feature activation+5.29e-03

Pos logit contributions
one+0.029
uan+0.026
 wizard+0.025
lor+0.025
 robe+0.024
Neg logit contributions
 cartoons-0.025
Deal-0.024
girls-0.022
 forth-0.022
boys-0.021
Token all
Token ID477
Feature activation+7.55e-03

Pos logit contributions
one+0.008
lor+0.007
uan+0.007
 wizard+0.007
unk+0.006
Neg logit contributions
Deal-0.010
 cartoons-0.010
girls-0.009
idents-0.009
 inviting-0.009
Token the
Token ID262
Feature activation+7.75e-03

Pos logit contributions
one+0.014
lor+0.013
uan+0.012
 wizard+0.012
 robe+0.012
Neg logit contributions
 cartoons-0.011
Deal-0.011
 inviting-0.010
 forth-0.010
girls-0.010
Token other
Token ID584
Feature activation+2.90e-02

Pos logit contributions
one+0.015
lor+0.014
uan+0.014
 wizard+0.013
orse+0.013
Neg logit contributions
 cartoons-0.011
Deal-0.010
girls-0.009
 inviting-0.009
idents-0.009
Token becoming
Token ID5033
Feature activation+2.91e-02

Pos logit contributions
Deal+0.008
girls+0.008
 cartoons+0.008
idents+0.008
icious+0.007
Neg logit contributions
one-0.007
 wizard-0.006
 robe-0.005
 ago-0.005
uan-0.005
Token a
Token ID257
Feature activation+1.63e-02

Pos logit contributions
one+0.043
lor+0.035
uan+0.035
 wizard+0.035
ooter+0.034
Neg logit contributions
 cartoons-0.054
Deal-0.053
girls-0.051
idents-0.048
 inviting-0.047
Token lawyer
Token ID6853
Feature activation+1.07e-02

Pos logit contributions
one+0.028
uan+0.023
lor+0.023
 wizard+0.022
em+0.022
Neg logit contributions
Deal-0.027
 cartoons-0.027
girls-0.025
idents-0.024
 inviting-0.023
Token and
Token ID290
Feature activation+3.38e-02

Pos logit contributions
one+0.018
 wizard+0.015
uan+0.015
lor+0.014
 robe+0.014
Neg logit contributions
Deal-0.018
 cartoons-0.018
girls-0.017
idents-0.016
icious-0.016
Token was
Token ID373
Feature activation+2.26e-02

Pos logit contributions
one+0.056
uan+0.046
lor+0.046
 wizard+0.045
em+0.044
Neg logit contributions
 cartoons-0.059
Deal-0.058
girls-0.055
idents-0.052
 inviting-0.051
Token naturally
Token ID8752
Feature activation+7.23e-02

Pos logit contributions
one+0.044
lor+0.039
uan+0.039
anger+0.038
ooter+0.037
Neg logit contributions
 cartoons-0.031
Deal-0.030
 inviting-0.028
girls-0.027
 y-0.026
Token talented
Token ID12356
Feature activation+4.68e-02

Pos logit contributions
one+0.135
lor+0.123
uan+0.116
ooter+0.113
enna+0.113
Neg logit contributions
 cartoons-0.106
Deal-0.102
 inviting-0.094
girls-0.094
 y-0.092
Token at
Token ID379
Feature activation-1.00e-02

Pos logit contributions
one+0.079
uan+0.066
 wizard+0.065
lor+0.064
 robe+0.062
Neg logit contributions
 cartoons-0.079
Deal-0.078
girls-0.073
idents-0.069
icious-0.067
Token it
Token ID340
Feature activation+2.16e-03

Pos logit contributions
 cartoons+0.015
Deal+0.015
girls+0.014
idents+0.013
 inviting+0.013
Neg logit contributions
one-0.018
uan-0.016
 wizard-0.016
lor-0.015
 robe-0.015
Token.
Token ID13
Feature activation+1.72e-02

Pos logit contributions
one+0.003
 wizard+0.003
lor+0.003
uan+0.002
ired+0.002
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.004
idents-0.004
icious-0.004
Token
Token ID220
Feature activation+1.05e-02

Pos logit contributions
one+0.031
 wizard+0.028
uan+0.026
ont+0.026
ster+0.026
Neg logit contributions
Deal-0.027
 cartoons-0.025
 inviting-0.024
idents-0.023
icious-0.022
Token he
Token ID339
Feature activation+6.66e-03

Pos logit contributions
one+0.029
lor+0.026
uan+0.024
alks+0.024
anger+0.023
Neg logit contributions
Deal-0.036
 cartoons-0.034
 inviting-0.033
 forth-0.033
girls-0.032
Token didn
Token ID1422
Feature activation-4.66e-03

Pos logit contributions
one+0.010
 wizard+0.008
uan+0.008
lor+0.008
 robe+0.007
Neg logit contributions
Deal-0.013
 cartoons-0.013
girls-0.012
idents-0.011
icious-0.011
Token't
Token ID470
Feature activation+1.54e-02

Pos logit contributions
 cartoons+0.009
Deal+0.009
girls+0.008
idents+0.008
icious+0.008
Neg logit contributions
one-0.007
 wizard-0.006
uan-0.006
lor-0.006
 robe-0.005
Token want
Token ID765
Feature activation-9.06e-04

Pos logit contributions
lor+0.026
one+0.025
alks+0.024
unk+0.022
anger+0.022
Neg logit contributions
 cartoons-0.024
Deal-0.023
 inviting-0.021
girls-0.021
 y-0.021
Token the
Token ID262
Feature activation+2.62e-02

Pos logit contributions
 cartoons+0.002
Deal+0.002
girls+0.002
 y+0.001
 inviting+0.001
Neg logit contributions
one-0.001
lor-0.001
ane-0.001
ittle-0.001
uan-0.001
Token old
Token ID1468
Feature activation+7.19e-02

Pos logit contributions
lor+0.039
one+0.039
enna+0.035
alks+0.035
ously+0.035
Neg logit contributions
 cartoons-0.045
 y-0.043
Deal-0.042
 games-0.039
 delicious-0.038
Token man
Token ID582
Feature activation+3.04e-02

Pos logit contributions
one+0.125
lor+0.123
uster+0.119
ann+0.116
umper+0.113
Neg logit contributions
 cartoons-0.101
 y-0.095
Deal-0.094
 stories-0.093
 games-0.091
Token to
Token ID284
Feature activation-8.38e-04

Pos logit contributions
one+0.041
lor+0.035
 wizard+0.034
uan+0.034
alks+0.033
Neg logit contributions
Deal-0.059
 cartoons-0.059
girls-0.056
idents-0.053
boys-0.052
Token know
Token ID760
Feature activation+2.30e-02

Pos logit contributions
 cartoons+0.001
Deal+0.001
girls+0.001
idents+0.001
 inviting+0.001
Neg logit contributions
one-0.001
uan-0.001
lor-0.001
 wizard-0.001
unk-0.001
Token that
Token ID326
Feature activation+1.63e-03

Pos logit contributions
one+0.038
 wizard+0.031
uan+0.030
lor+0.029
em+0.029
Neg logit contributions
Deal-0.040
 cartoons-0.039
girls-0.038
idents-0.037
icious-0.036
Token.
Token ID13
Feature activation+8.75e-03

Pos logit contributions
one+0.002
 wizard+0.002
uan+0.002
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.003
 cartoons-0.003
girls-0.003
idents-0.003
icious-0.003
Token kisses
Token ID36544
Feature activation+7.53e-03

Pos logit contributions
one+0.032
 wizard+0.027
 ago+0.025
uan+0.025
em+0.025
Neg logit contributions
Deal-0.048
girls-0.043
 cartoons-0.043
idents-0.043
icious-0.043
Token,
Token ID11
Feature activation+4.90e-03

Pos logit contributions
one+0.009
 ago+0.007
 wizard+0.007
uan+0.007
ired+0.007
Neg logit contributions
Deal-0.016
girls-0.014
icious-0.014
idents-0.014
 cartoons-0.014
Token just
Token ID655
Feature activation+2.30e-02

Pos logit contributions
one+0.007
 wizard+0.006
uan+0.006
 robe+0.006
lor+0.006
Neg logit contributions
Deal-0.009
 cartoons-0.009
girls-0.008
idents-0.008
icious-0.008
Token like
Token ID588
Feature activation+1.05e-03

Pos logit contributions
one+0.044
 wizard+0.038
uan+0.038
lor+0.037
 robe+0.036
Neg logit contributions
Deal-0.033
 cartoons-0.033
girls-0.031
idents-0.029
icious-0.028
Token the
Token ID262
Feature activation+2.61e-02

Pos logit contributions
one+0.002
 wizard+0.001
uan+0.001
lor+0.001
 robe+0.001
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.002
icious-0.002
Token first
Token ID717
Feature activation+7.14e-02

Pos logit contributions
one+0.039
 wizard+0.034
 robe+0.032
uan+0.032
 aid+0.031
Neg logit contributions
Deal-0.048
girls-0.047
 cartoons-0.046
idents-0.043
icious-0.042
Token time
Token ID640
Feature activation+4.10e-02

Pos logit contributions
one+0.111
alks+0.093
uan+0.092
lor+0.090
ooter+0.089
Neg logit contributions
 cartoons-0.130
Deal-0.119
idents-0.110
 inviting-0.106
 y-0.106
Token when
Token ID618
Feature activation+1.76e-03

Pos logit contributions
one+0.068
 wizard+0.056
uan+0.055
lor+0.054
em+0.052
Neg logit contributions
Deal-0.071
 cartoons-0.070
girls-0.066
idents-0.063
icious-0.061
Token mom
Token ID1995
Feature activation+8.67e-03

Pos logit contributions
one+0.003
 wizard+0.003
uan+0.003
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.003
 cartoons-0.003
girls-0.003
idents-0.003
icious-0.003
Token received
Token ID2722
Feature activation+1.89e-02

Pos logit contributions
one+0.014
 wizard+0.011
uan+0.011
lor+0.011
 robe+0.010
Neg logit contributions
Deal-0.016
 cartoons-0.015
girls-0.015
idents-0.014
icious-0.013
Token the
Token ID262
Feature activation+6.70e-03

Pos logit contributions
one+0.031
 wizard+0.026
uan+0.026
lor+0.025
 robe+0.024
Neg logit contributions
Deal-0.033
 cartoons-0.032
girls-0.031
idents-0.029
icious-0.028
Token bigger
Token ID5749
Feature activation+2.43e-03

Pos logit contributions
Deal+0.017
 cartoons+0.016
girls+0.016
idents+0.015
icious+0.014
Neg logit contributions
one-0.018
 wizard-0.016
uan-0.015
 ago-0.015
 robe-0.015
Token and
Token ID290
Feature activation-2.90e-02

Pos logit contributions
one+0.004
uan+0.004
lor+0.004
 wizard+0.004
ooter+0.004
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.004
boys-0.003
idents-0.003
Token brighter
Token ID26083
Feature activation+7.43e-03

Pos logit contributions
 cartoons+0.054
girls+0.052
Deal+0.050
icious+0.048
idents+0.048
Neg logit contributions
one-0.046
 wizard-0.038
 begg-0.034
 arrived-0.033
 Dale-0.033
Token than
Token ID621
Feature activation-1.50e-02

Pos logit contributions
one+0.013
 wizard+0.010
uan+0.010
lor+0.010
 robe+0.010
Neg logit contributions
Deal-0.013
 cartoons-0.013
girls-0.012
idents-0.011
icious-0.011
Token the
Token ID262
Feature activation+2.36e-02

Pos logit contributions
 cartoons+0.025
Deal+0.025
girls+0.023
idents+0.022
icious+0.021
Neg logit contributions
one-0.025
 wizard-0.021
uan-0.021
lor-0.021
 robe-0.020
Token first
Token ID717
Feature activation+7.11e-02

Pos logit contributions
one+0.031
lor+0.025
uan+0.025
anging+0.023
ooter+0.023
Neg logit contributions
Deal-0.049
 cartoons-0.047
 y-0.044
 inviting-0.044
 forth-0.044
Token one
Token ID530
Feature activation+1.72e-02

Pos logit contributions
one+0.108
ooter+0.108
iers+0.103
ume+0.100
uan+0.100
Neg logit contributions
 y-0.102
Deal-0.100
 forth-0.096
 inviting-0.090
 delicious-0.089
Token.
Token ID13
Feature activation+2.02e-03

Pos logit contributions
one+0.030
lor+0.027
uan+0.027
 wizard+0.026
ooter+0.026
Neg logit contributions
Deal-0.026
 cartoons-0.025
girls-0.024
 forth-0.022
 inviting-0.022
Token She
Token ID1375
Feature activation-6.97e-03

Pos logit contributions
one+0.003
 wizard+0.003
uan+0.003
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.003
idents-0.003
 inviting-0.003
Token smiled
Token ID13541
Feature activation+1.85e-03

Pos logit contributions
Deal+0.013
 cartoons+0.012
girls+0.012
idents+0.011
boys+0.011
Neg logit contributions
one-0.011
lor-0.009
uan-0.009
 wizard-0.009
ooter-0.009
Token and
Token ID290
Feature activation-1.16e-02

Pos logit contributions
one+0.003
lor+0.003
uan+0.003
 wizard+0.003
em+0.003
Neg logit contributions
 cartoons-0.003
Deal-0.003
girls-0.003
idents-0.003
 inviting-0.002
Token blue
Token ID4171
Feature activation+3.01e-02

Pos logit contributions
one+0.031
lor+0.026
enna+0.025
uan+0.025
ooter+0.025
Neg logit contributions
 cartoons-0.023
 inviting-0.020
 games-0.019
 y-0.019
 forth-0.018
Token shells
Token ID19679
Feature activation+2.14e-02

Pos logit contributions
one+0.056
lor+0.052
enna+0.050
illian+0.050
 sorcerer+0.050
Neg logit contributions
 cartoons-0.043
 inviting-0.036
 games-0.035
 y-0.035
glers-0.034
Token.
Token ID13
Feature activation+2.03e-04

Pos logit contributions
one+0.040
uan+0.035
 wizard+0.034
lor+0.034
 aid+0.033
Neg logit contributions
 cartoons-0.030
girls-0.028
Deal-0.027
boys-0.026
 forth-0.026
Token The
Token ID383
Feature activation+1.44e-02

Pos logit contributions
one+0.000
 wizard+0.000
uan+0.000
 robe+0.000
lor+0.000
Neg logit contributions
 cartoons-0.000
Deal-0.000
girls-0.000
idents-0.000
ksh-0.000
Token her
Token ID607
Feature activation+2.51e-02

Pos logit contributions
one+0.022
lor+0.021
uan+0.019
enna+0.018
anger+0.018
Neg logit contributions
Deal-0.026
 cartoons-0.025
 forth-0.024
 y-0.024
 inviting-0.024
Tokenmit
Token ID2781
Feature activation+7.11e-02

Pos logit contributions
one+0.040
lor+0.033
uan+0.029
enna+0.028
iers+0.028
Neg logit contributions
 cartoons-0.047
Deal-0.047
 y-0.044
idents-0.043
girls-0.043
Token crab
Token ID32202
Feature activation+2.94e-03

Pos logit contributions
one+0.106
 ago+0.090
reetings+0.085
enna+0.085
 aid+0.085
Neg logit contributions
Deal-0.128
 y-0.115
 both-0.107
 together-0.106
 forth-0.105
Token was
Token ID373
Feature activation+1.37e-02

Pos logit contributions
one+0.005
uan+0.004
lor+0.004
 wizard+0.004
em+0.004
Neg logit contributions
Deal-0.005
 cartoons-0.005
girls-0.004
boys-0.004
 inviting-0.004
Token so
Token ID523
Feature activation+7.93e-03

Pos logit contributions
one+0.030
lor+0.027
uan+0.026
anger+0.026
ooter+0.026
Neg logit contributions
 cartoons-0.016
 inviting-0.016
 y-0.014
 together-0.013
girls-0.013
Token excited
Token ID6568
Feature activation-7.10e-03

Pos logit contributions
one+0.017
lor+0.014
 wizard+0.014
uan+0.014
 robe+0.014
Neg logit contributions
Deal-0.010
 cartoons-0.010
girls-0.009
 inviting-0.009
idents-0.009
Token!
Token ID0
Feature activation+3.79e-03

Pos logit contributions
 cartoons+0.011
Deal+0.011
idents+0.011
girls+0.010
 inviting+0.010
Neg logit contributions
one-0.012
uan-0.010
lor-0.010
 wizard-0.010
 robe-0.010
Token time
Token ID640
Feature activation+2.22e-02

Pos logit contributions
 cartoons+0.009
girls+0.009
Deal+0.008
idents+0.008
 forth+0.008
Neg logit contributions
one-0.005
 aid-0.004
orse-0.003
 robe-0.003
ired-0.003
Token,
Token ID11
Feature activation+6.43e-03

Pos logit contributions
one+0.038
 wizard+0.033
uan+0.033
lor+0.033
 robe+0.031
Neg logit contributions
Deal-0.036
 cartoons-0.035
girls-0.032
idents-0.032
 inviting-0.031
Token there
Token ID612
Feature activation+2.84e-03

Pos logit contributions
one+0.008
 wizard+0.006
 ago+0.005
ired+0.005
unk+0.005
Neg logit contributions
 cartoons-0.014
girls-0.014
Deal-0.014
idents-0.013
icious-0.013
Token was
Token ID373
Feature activation+2.07e-02

Pos logit contributions
one+0.004
 wizard+0.003
uan+0.003
lor+0.003
ired+0.003
Neg logit contributions
 cartoons-0.005
Deal-0.005
girls-0.005
idents-0.005
icious-0.005
Token a
Token ID257
Feature activation-2.10e-02

Pos logit contributions
one+0.023
 wizard+0.017
uan+0.016
ired+0.016
 robe+0.015
Neg logit contributions
Deal-0.047
 cartoons-0.046
girls-0.045
idents-0.044
icious-0.042
Token y
Token ID331
Feature activation-7.71e-02

Pos logit contributions
girls+0.048
Deal+0.047
 cartoons+0.045
idents+0.045
icious+0.043
Neg logit contributions
 wizard-0.021
one-0.020
 begg-0.017
 robe-0.016
 sur-0.016
Tokenummy
Token ID13513
Feature activation-3.85e-02

Pos logit contributions
Deal+0.150
girls+0.147
 cartoons+0.138
idents+0.129
boys+0.127
Neg logit contributions
one-0.106
 begg-0.092
 wizard-0.091
ired-0.089
uan-0.088
Token place
Token ID1295
Feature activation+3.11e-03

Pos logit contributions
Deal+0.072
 cartoons+0.069
girls+0.068
idents+0.065
icious+0.063
Neg logit contributions
one-0.057
 wizard-0.049
uan-0.047
 robe-0.045
lor-0.045
Token filled
Token ID5901
Feature activation-4.40e-02

Pos logit contributions
one+0.005
 wizard+0.004
uan+0.004
lor+0.004
 robe+0.004
Neg logit contributions
Deal-0.006
 cartoons-0.006
girls-0.005
idents-0.005
icious-0.005
Token with
Token ID351
Feature activation-5.94e-03

Pos logit contributions
girls+0.088
Deal+0.086
 cartoons+0.083
icious+0.082
idents+0.082
Neg logit contributions
one-0.054
 wizard-0.049
 robe-0.047
 begg-0.046
 oy-0.046
Token lots
Token ID6041
Feature activation-1.65e-02

Pos logit contributions
Deal+0.011
idents+0.010
girls+0.010
icious+0.010
 forth+0.009
Neg logit contributions
one-0.009
 oy-0.008
 begg-0.008
 robe-0.008
 wizard-0.008
Token that
Token ID326
Feature activation-7.49e-03

Pos logit contributions
 cartoons+0.005
 y+0.005
Deal+0.005
 inviting+0.005
girls+0.004
Neg logit contributions
one-0.006
lor-0.005
uan-0.005
em-0.005
 ago-0.005
Token the
Token ID262
Feature activation+7.74e-03

Pos logit contributions
Deal+0.014
 cartoons+0.014
girls+0.013
idents+0.013
icious+0.012
Neg logit contributions
one-0.011
 wizard-0.009
uan-0.009
lor-0.009
 robe-0.009
Token net
Token ID2010
Feature activation-6.79e-03

Pos logit contributions
one+0.009
 wizard+0.007
 robe+0.007
lor+0.006
uan+0.006
Neg logit contributions
 cartoons-0.017
Deal-0.017
girls-0.016
idents-0.015
icious-0.015
Token held
Token ID2714
Feature activation-4.41e-03

Pos logit contributions
Deal+0.013
 cartoons+0.013
girls+0.012
idents+0.012
icious+0.011
Neg logit contributions
one-0.010
 wizard-0.008
uan-0.008
lor-0.008
 robe-0.008
Token a
Token ID257
Feature activation-1.77e-02

Pos logit contributions
Deal+0.009
 cartoons+0.009
girls+0.008
icious+0.008
idents+0.008
Neg logit contributions
one-0.006
 wizard-0.005
 Dale-0.005
uan-0.005
 oy-0.005
Token y
Token ID331
Feature activation-7.70e-02

Pos logit contributions
Deal+0.029
 cartoons+0.029
girls+0.028
idents+0.026
icious+0.025
Neg logit contributions
one-0.030
 wizard-0.026
uan-0.025
lor-0.025
 robe-0.024
Tokenummy
Token ID13513
Feature activation-3.07e-02

Pos logit contributions
Deal+0.130
 cartoons+0.127
girls+0.122
idents+0.112
boys+0.110
Neg logit contributions
one-0.132
uan-0.109
 wizard-0.108
ired-0.107
lor-0.106
Token nut
Token ID6701
Feature activation-4.22e-02

Pos logit contributions
Deal+0.050
 cartoons+0.049
girls+0.047
idents+0.044
icious+0.042
Neg logit contributions
one-0.054
 wizard-0.046
uan-0.045
lor-0.044
 robe-0.043
Token!
Token ID0
Feature activation-1.38e-02

Pos logit contributions
Deal+0.071
 cartoons+0.071
girls+0.067
idents+0.063
icious+0.061
Neg logit contributions
one-0.071
 wizard-0.060
uan-0.059
lor-0.058
 robe-0.056
Token He
Token ID679
Feature activation-1.51e-02

Pos logit contributions
 cartoons+0.022
Deal+0.021
girls+0.020
idents+0.019
 y+0.018
Neg logit contributions
one-0.026
 wizard-0.022
uan-0.021
reetings-0.021
lor-0.021
Token grabbed
Token ID13176
Feature activation-2.47e-03

Pos logit contributions
 cartoons+0.029
Deal+0.029
girls+0.028
idents+0.027
icious+0.026
Neg logit contributions
one-0.022
 wizard-0.017
uan-0.017
lor-0.017
 robe-0.016
Token.
Token ID13
Feature activation-1.53e-02

Pos logit contributions
one+0.040
uan+0.037
lor+0.035
enna+0.035
 wizard+0.035
Neg logit contributions
Deal-0.026
 cartoons-0.024
 inviting-0.022
girls-0.022
 y-0.021
Token He
Token ID679
Feature activation-1.38e-02

Pos logit contributions
Deal+0.029
 cartoons+0.029
girls+0.028
idents+0.027
 inviting+0.026
Neg logit contributions
one-0.023
 wizard-0.019
uan-0.019
lor-0.018
enna-0.018
Token thought
Token ID1807
Feature activation-1.14e-02

Pos logit contributions
 cartoons+0.028
Deal+0.028
girls+0.027
idents+0.026
icious+0.025
Neg logit contributions
one-0.018
 wizard-0.014
uan-0.014
lor-0.013
 robe-0.013
Token it
Token ID340
Feature activation-4.08e-02

Pos logit contributions
 cartoons+0.019
Deal+0.018
girls+0.016
 inviting+0.016
idents+0.016
Neg logit contributions
one-0.020
lor-0.018
uan-0.017
 wizard-0.017
 robe-0.016
Token looked
Token ID3114
Feature activation-3.16e-02

Pos logit contributions
 cartoons+0.093
icious+0.088
girls+0.087
Deal+0.083
lights+0.078
Neg logit contributions
one-0.042
 arrived-0.039
 wizard-0.036
 stumbled-0.033
 reached-0.032
Token y
Token ID331
Feature activation-7.60e-02

Pos logit contributions
girls+0.062
 cartoons+0.057
boys+0.054
Deal+0.053
glers+0.051
Neg logit contributions
 seen-0.041
 oy-0.040
one-0.039
 shell-0.038
 reached-0.035
Tokenummy
Token ID13513
Feature activation-4.21e-02

Pos logit contributions
 cartoons+0.140
Deal+0.139
girls+0.135
boys+0.122
idents+0.120
Neg logit contributions
one-0.118
ired-0.096
uan-0.095
em-0.093
ump-0.091
Token and
Token ID290
Feature activation-1.90e-02

Pos logit contributions
 cartoons+0.092
Deal+0.091
girls+0.089
icious+0.087
idents+0.082
Neg logit contributions
one-0.051
 wizard-0.037
 oy-0.037
em-0.035
 ago-0.035
Token wanted
Token ID2227
Feature activation-2.36e-03

Pos logit contributions
girls+0.042
 cartoons+0.042
icious+0.041
Deal+0.040
ksh+0.039
Neg logit contributions
one-0.019
 wizard-0.017
orse-0.017
 seen-0.016
 oy-0.016
Token to
Token ID284
Feature activation-4.31e-03

Pos logit contributions
 cartoons+0.005
Deal+0.005
girls+0.005
idents+0.005
 inviting+0.005
Neg logit contributions
one-0.003
 wizard-0.002
uan-0.002
lor-0.002
em-0.002
Token try
Token ID1949
Feature activation+1.80e-02

Pos logit contributions
 cartoons+0.005
Deal+0.005
girls+0.004
idents+0.004
 inviting+0.004
Neg logit contributions
one-0.010
lor-0.009
uan-0.009
 wizard-0.008
em-0.008
Token bag
Token ID6131
Feature activation-9.91e-03

Pos logit contributions
one+0.016
uan+0.013
 wizard+0.013
lor+0.012
em+0.012
Neg logit contributions
Deal-0.018
 cartoons-0.018
girls-0.017
idents-0.016
boys-0.015
Token.
Token ID13
Feature activation-8.81e-03

Pos logit contributions
Deal+0.014
 cartoons+0.013
girls+0.012
 inviting+0.011
 y+0.011
Neg logit contributions
one-0.019
uan-0.017
 wizard-0.017
lor-0.016
alks-0.016
Token It
Token ID632
Feature activation-2.48e-02

Pos logit contributions
Deal+0.020
 cartoons+0.019
girls+0.018
icious+0.018
idents+0.018
Neg logit contributions
one-0.010
 wizard-0.007
uan-0.007
alks-0.007
ooter-0.007
Token was
Token ID373
Feature activation-1.18e-02

Pos logit contributions
 cartoons+0.058
Deal+0.055
girls+0.055
icious+0.054
idents+0.054
Neg logit contributions
one-0.025
 arrived-0.022
 wizard-0.019
 reached-0.018
 begg-0.018
Token a
Token ID257
Feature activation-1.51e-02

Pos logit contributions
Deal+0.027
idents+0.026
girls+0.026
boys+0.024
icious+0.024
Neg logit contributions
one-0.011
 begg-0.010
 eight-0.009
 seen-0.009
 tool-0.009
Token y
Token ID331
Feature activation-7.59e-02

Pos logit contributions
girls+0.028
 cartoons+0.027
Deal+0.027
idents+0.025
ksh+0.024
Neg logit contributions
 wizard-0.021
one-0.020
 robe-0.019
 begg-0.019
 tool-0.019
Tokenummy
Token ID13513
Feature activation-3.13e-02

Pos logit contributions
Deal+0.137
girls+0.132
 cartoons+0.130
boys+0.119
idents+0.118
Neg logit contributions
one-0.119
ired-0.098
uan-0.097
alks-0.095
em-0.095
Token cookie
Token ID19751
Feature activation-3.82e-02

Pos logit contributions
girls+0.045
Deal+0.045
 cartoons+0.043
boys+0.039
icious+0.039
Neg logit contributions
one-0.057
 wizard-0.052
 robe-0.049
ired-0.048
 begg-0.048
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
Deal+0.074
 cartoons+0.074
idents+0.071
girls+0.070
icious+0.069
Neg logit contributions
one-0.052
 wizard-0.043
 robe-0.039
unk-0.039
uan-0.039
Token Spot
Token ID15899
Feature activation-6.46e-03

Pos logit contributions
Deal+0.025
 cartoons+0.024
girls+0.023
idents+0.022
icious+0.022
Neg logit contributions
one-0.016
 wizard-0.012
uan-0.012
lor-0.012
 robe-0.011
Token wanted
Token ID2227
Feature activation-4.99e-03

Pos logit contributions
 cartoons+0.013
Deal+0.013
girls+0.012
icious+0.012
idents+0.012
Neg logit contributions
one-0.008
 wizard-0.007
 arrived-0.007
 robe-0.006
uan-0.006
Token snack
Token ID26906
Feature activation-2.49e-02

Pos logit contributions
one+0.007
 wizard+0.006
uan+0.006
 robe+0.006
lor+0.006
Neg logit contributions
Deal-0.007
 cartoons-0.007
girls-0.006
idents-0.006
icious-0.006
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
Deal+0.048
 cartoons+0.047
girls+0.046
idents+0.044
icious+0.043
Neg logit contributions
one-0.036
 wizard-0.029
uan-0.027
em-0.027
 ago-0.027
Token They
Token ID1119
Feature activation-1.87e-02

Pos logit contributions
 cartoons+0.020
Deal+0.020
girls+0.019
idents+0.018
 inviting+0.017
Neg logit contributions
one-0.023
 wizard-0.020
lor-0.019
uan-0.019
 robe-0.019
Token ate
Token ID15063
Feature activation-1.99e-02

Pos logit contributions
 cartoons+0.040
Deal+0.040
girls+0.039
idents+0.038
icious+0.038
Neg logit contributions
one-0.024
 arrived-0.019
 stepped-0.017
uan-0.017
 wizard-0.017
Token a
Token ID257
Feature activation-1.61e-02

Pos logit contributions
girls+0.048
Deal+0.046
icious+0.046
itionally+0.043
ksh+0.042
Neg logit contributions
 oy-0.017
one-0.013
 sea-0.013
 a-0.013
 one-0.013
Token y
Token ID331
Feature activation-7.58e-02

Pos logit contributions
girls+0.028
Deal+0.028
 cartoons+0.027
boys+0.025
idents+0.025
Neg logit contributions
one-0.026
 wizard-0.022
 robe-0.021
 aid-0.021
 arrived-0.021
Tokenummy
Token ID13513
Feature activation-2.82e-02

Pos logit contributions
Deal+0.140
girls+0.138
 cartoons+0.132
boys+0.123
idents+0.118
Neg logit contributions
one-0.116
ired-0.096
em-0.094
alks-0.094
uan-0.093
Token treat
Token ID2190
Feature activation-2.76e-02

Pos logit contributions
Deal+0.039
girls+0.039
 cartoons+0.037
idents+0.033
boys+0.033
Neg logit contributions
one-0.055
 wizard-0.048
 robe-0.046
uan-0.046
em-0.046
Token to
Token ID284
Feature activation-1.11e-02

Pos logit contributions
Deal+0.054
 cartoons+0.053
girls+0.052
icious+0.050
idents+0.049
Neg logit contributions
one-0.037
em-0.030
 wizard-0.030
uan-0.029
ired-0.028
Token give
Token ID1577
Feature activation-1.88e-02

Pos logit contributions
girls+0.020
Deal+0.020
idents+0.019
 cartoons+0.018
ksh+0.018
Neg logit contributions
one-0.016
 wizard-0.014
 robe-0.013
orse-0.013
em-0.013
Token them
Token ID606
Feature activation-1.88e-02

Pos logit contributions
Deal+0.037
 cartoons+0.035
girls+0.034
icious+0.034
idents+0.032
Neg logit contributions
one-0.027
em-0.022
uan-0.022
 wizard-0.021
ired-0.020
Token.
Token ID13
Feature activation-1.99e-02

Pos logit contributions
one+0.009
 wizard+0.007
uan+0.007
lor+0.007
 robe+0.007
Neg logit contributions
Deal-0.009
 cartoons-0.009
girls-0.009
idents-0.008
icious-0.008
Token He
Token ID679
Feature activation-1.26e-02

Pos logit contributions
 cartoons+0.038
Deal+0.037
idents+0.035
girls+0.035
 inviting+0.033
Neg logit contributions
one-0.030
 wizard-0.025
lor-0.025
uan-0.024
 robe-0.023
Token thought
Token ID1807
Feature activation-1.01e-02

Pos logit contributions
Deal+0.026
 cartoons+0.026
girls+0.025
idents+0.023
icious+0.023
Neg logit contributions
one-0.017
 wizard-0.013
uan-0.013
lor-0.013
 robe-0.012
Token it
Token ID340
Feature activation-3.69e-02

Pos logit contributions
 cartoons+0.017
Deal+0.017
girls+0.016
idents+0.015
 inviting+0.015
Neg logit contributions
one-0.017
lor-0.014
 wizard-0.014
uan-0.014
 robe-0.013
Token looked
Token ID3114
Feature activation-3.05e-02

Pos logit contributions
 cartoons+0.088
icious+0.087
girls+0.086
Deal+0.085
ksh+0.076
Neg logit contributions
one-0.033
 arrived-0.031
 wizard-0.026
 stumbled-0.025
 stepped-0.023
Token y
Token ID331
Feature activation-7.55e-02

Pos logit contributions
girls+0.063
Deal+0.060
 cartoons+0.057
boys+0.054
icious+0.053
Neg logit contributions
 seen-0.038
one-0.036
 oy-0.035
 shell-0.033
 wizard-0.032
Tokenummy
Token ID13513
Feature activation-4.21e-02

Pos logit contributions
Deal+0.139
 cartoons+0.138
girls+0.134
boys+0.120
idents+0.118
Neg logit contributions
one-0.119
ired-0.096
uan-0.096
em-0.094
alks-0.092
Token,
Token ID11
Feature activation-9.52e-03

Pos logit contributions
Deal+0.091
 cartoons+0.090
girls+0.089
icious+0.086
idents+0.081
Neg logit contributions
one-0.051
 wizard-0.039
 ago-0.036
 oy-0.036
uan-0.036
Token so
Token ID523
Feature activation-2.29e-02

Pos logit contributions
Deal+0.017
 cartoons+0.017
girls+0.017
icious+0.015
idents+0.015
Neg logit contributions
one-0.015
 wizard-0.012
uan-0.012
 robe-0.011
 begg-0.011
Token he
Token ID339
Feature activation-1.02e-02

Pos logit contributions
girls+0.067
Deal+0.065
 cartoons+0.064
idents+0.064
ksh+0.064
Neg logit contributions
one-0.011
orse-0.005
 wizard-0.005
 stub-0.003
 Dale-0.002
Token tried
Token ID3088
Feature activation+1.16e-02

Pos logit contributions
 cartoons+0.020
Deal+0.020
girls+0.019
idents+0.019
icious+0.018
Neg logit contributions
one-0.014
 wizard-0.011
uan-0.011
lor-0.011
 robe-0.010
Token smelled
Token ID37609
Feature activation-3.50e-02

Pos logit contributions
Deal+0.046
 cartoons+0.045
girls+0.044
icious+0.043
idents+0.040
Neg logit contributions
one-0.021
 arrived-0.018
 stub-0.017
 wizard-0.017
 stepped-0.016
Token funny
Token ID8258
Feature activation-2.04e-02

Pos logit contributions
girls+0.080
Deal+0.074
boys+0.068
ksh+0.063
 cartoons+0.063
Neg logit contributions
one-0.039
 oy-0.039
 grown-0.038
 eye-0.034
 shell-0.033
Token and
Token ID290
Feature activation-1.85e-02

Pos logit contributions
Deal+0.049
girls+0.044
icious+0.042
 forth+0.041
 cartoons+0.041
Neg logit contributions
one-0.021
 oy-0.017
unk-0.017
ired-0.017
em-0.016
Token turned
Token ID2900
Feature activation+6.17e-03

Pos logit contributions
girls+0.036
Deal+0.036
 cartoons+0.034
icious+0.034
boys+0.032
Neg logit contributions
one-0.023
 arrived-0.021
 wizard-0.021
 stepped-0.020
 stub-0.020
Token a
Token ID257
Feature activation-1.73e-02

Pos logit contributions
one+0.009
alks+0.007
 wizard+0.007
 tal+0.007
uan+0.007
Neg logit contributions
Deal-0.014
girls-0.012
icious-0.011
 cartoons-0.011
boys-0.011
Token y
Token ID331
Feature activation-7.54e-02

Pos logit contributions
Deal+0.033
girls+0.032
 cartoons+0.031
idents+0.029
boys+0.029
Neg logit contributions
one-0.026
 wizard-0.023
 robe-0.020
uan-0.020
 begg-0.020
Tokenucky
Token ID5309
Feature activation-2.40e-02

Pos logit contributions
Deal+0.142
girls+0.140
 cartoons+0.134
boys+0.125
idents+0.118
Neg logit contributions
one-0.113
ired-0.094
alks-0.091
 wizard-0.090
uan-0.090
Token colour
Token ID9568
Feature activation+3.68e-03

Pos logit contributions
Deal+0.043
girls+0.041
 cartoons+0.041
icious+0.038
idents+0.037
Neg logit contributions
one-0.038
 wizard-0.033
 robe-0.030
uan-0.030
lor-0.030
Token.
Token ID13
Feature activation-1.18e-02

Pos logit contributions
one+0.006
 wizard+0.005
uan+0.005
lor+0.005
em+0.005
Neg logit contributions
Deal-0.007
 cartoons-0.006
girls-0.006
idents-0.006
icious-0.006
Token
Token ID198
Feature activation+1.46e-03

Pos logit contributions
 cartoons+0.022
Deal+0.021
girls+0.020
idents+0.020
 inviting+0.019
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.015
lor-0.014
ittle-0.014
Token
Token ID198
Feature activation+1.52e-03

Pos logit contributions
one+0.002
 wizard+0.002
uan+0.002
 robe+0.002
lor+0.002
Neg logit contributions
Deal-0.003
 cartoons-0.003
girls-0.003
 inviting-0.003
idents-0.002
Token Tweet
Token ID18752
Feature activation-1.00e-02

Pos logit contributions
Deal+0.040
 cartoons+0.039
girls+0.038
idents+0.037
 inviting+0.035
Neg logit contributions
one-0.036
uan-0.030
 wizard-0.029
lor-0.028
em-0.028
Tokenie
Token ID494
Feature activation+9.79e-03

Pos logit contributions
Deal+0.011
 cartoons+0.011
girls+0.010
idents+0.009
icious+0.009
Neg logit contributions
one-0.023
 wizard-0.020
uan-0.020
lor-0.020
ired-0.019
Token thought
Token ID1807
Feature activation-1.05e-02

Pos logit contributions
one+0.013
 wizard+0.011
uan+0.010
lor+0.010
ired+0.010
Neg logit contributions
 cartoons-0.020
Deal-0.020
girls-0.019
idents-0.018
icious-0.018
Token it
Token ID340
Feature activation-4.11e-02

Pos logit contributions
 cartoons+0.018
Deal+0.017
girls+0.016
idents+0.015
 inviting+0.015
Neg logit contributions
one-0.018
lor-0.015
uan-0.015
 wizard-0.015
 robe-0.014
Token looked
Token ID3114
Feature activation-2.74e-02

Pos logit contributions
 cartoons+0.092
girls+0.087
icious+0.085
Deal+0.083
glers+0.077
Neg logit contributions
one-0.048
 arrived-0.042
 wizard-0.039
 stumbled-0.036
 reached-0.035
Token y
Token ID331
Feature activation-7.52e-02

Pos logit contributions
girls+0.055
 cartoons+0.050
Deal+0.047
boys+0.046
glers+0.046
Neg logit contributions
 seen-0.036
one-0.036
 oy-0.033
 shell-0.032
 reached-0.031
Tokenummy
Token ID13513
Feature activation-4.00e-02

Pos logit contributions
 cartoons+0.135
Deal+0.134
girls+0.130
boys+0.116
idents+0.116
Neg logit contributions
one-0.121
ired-0.098
uan-0.098
em-0.096
lor-0.093
Token,
Token ID11
Feature activation-1.18e-02

Pos logit contributions
 cartoons+0.090
Deal+0.089
girls+0.088
icious+0.085
idents+0.080
Neg logit contributions
one-0.046
 oy-0.033
 wizard-0.033
em-0.032
ired-0.030
Token but
Token ID475
Feature activation-6.45e-03

Pos logit contributions
Deal+0.021
 cartoons+0.020
girls+0.020
idents+0.018
icious+0.018
Neg logit contributions
one-0.019
 wizard-0.016
uan-0.015
lor-0.015
 robe-0.015
Token it
Token ID340
Feature activation-1.49e-02

Pos logit contributions
 cartoons+0.014
Deal+0.013
girls+0.013
icious+0.012
idents+0.012
Neg logit contributions
one-0.009
 wizard-0.007
uan-0.006
lor-0.006
 robe-0.006
Token was
Token ID373
Feature activation-9.07e-03

Pos logit contributions
 cartoons+0.037
girls+0.035
Deal+0.032
icious+0.032
ksh+0.030
Neg logit contributions
one-0.016
 stub-0.013
 reached-0.013
 stumbled-0.012
 arrived-0.012
Token boy
Token ID2933
Feature activation-5.95e-03

Pos logit contributions
Deal+0.027
 cartoons+0.027
girls+0.026
idents+0.025
icious+0.024
Neg logit contributions
one-0.021
 wizard-0.017
uan-0.016
lor-0.016
 robe-0.015
Token.
Token ID13
Feature activation-6.71e-03

Pos logit contributions
 cartoons+0.009
Deal+0.009
girls+0.009
boys+0.008
 inviting+0.008
Neg logit contributions
one-0.011
lor-0.010
uan-0.009
 wizard-0.009
anger-0.009
Token He
Token ID679
Feature activation-9.13e-03

Pos logit contributions
 cartoons+0.015
Deal+0.015
girls+0.014
idents+0.013
 inviting+0.013
Neg logit contributions
one-0.008
 wizard-0.006
lor-0.006
uan-0.006
ired-0.006
Token saw
Token ID2497
Feature activation-1.08e-03

Pos logit contributions
 cartoons+0.017
Deal+0.016
girls+0.016
idents+0.015
icious+0.015
Neg logit contributions
one-0.014
 wizard-0.012
uan-0.011
 robe-0.011
lor-0.011
Token a
Token ID257
Feature activation-1.58e-02

Pos logit contributions
 cartoons+0.002
Deal+0.002
girls+0.002
 y+0.002
 inviting+0.002
Neg logit contributions
one-0.002
lor-0.001
uan-0.001
 wizard-0.001
em-0.001
Token y
Token ID331
Feature activation-7.51e-02

Pos logit contributions
Deal+0.032
girls+0.031
 cartoons+0.030
idents+0.028
icious+0.028
Neg logit contributions
one-0.020
 wizard-0.020
 robe-0.018
 begg-0.018
uan-0.017
Tokenummy
Token ID13513
Feature activation-3.27e-02

Pos logit contributions
Deal+0.138
girls+0.132
 cartoons+0.129
idents+0.116
boys+0.116
Neg logit contributions
one-0.114
 wizard-0.099
 begg-0.096
uan-0.096
ired-0.095
Token cel
Token ID18725
Feature activation-3.83e-02

Pos logit contributions
Deal+0.055
girls+0.053
 cartoons+0.051
idents+0.047
icious+0.047
Neg logit contributions
one-0.054
 wizard-0.050
 robe-0.047
 begg-0.046
uan-0.045
Tokenery
Token ID1924
Feature activation-3.32e-02

Pos logit contributions
 cartoons+0.063
Deal+0.061
girls+0.059
idents+0.056
 forth+0.053
Neg logit contributions
one-0.067
 wizard-0.058
lor-0.058
uan-0.056
unk-0.055
Token on
Token ID319
Feature activation-4.54e-03

Pos logit contributions
Deal+0.058
 cartoons+0.058
girls+0.055
idents+0.052
icious+0.051
Neg logit contributions
one-0.054
 wizard-0.045
uan-0.044
lor-0.044
 robe-0.042
Token the
Token ID262
Feature activation-7.06e-03

Pos logit contributions
Deal+0.010
girls+0.009
 cartoons+0.009
icious+0.009
idents+0.009
Neg logit contributions
one-0.006
 wizard-0.005
growth-0.004
 robe-0.004
uan-0.004
Token Inside
Token ID14384
Feature activation+9.14e-04

Pos logit contributions
 cartoons+0.002
Deal+0.002
girls+0.002
idents+0.002
 inviting+0.002
Neg logit contributions
one-0.002
 wizard-0.002
uan-0.002
unk-0.002
reetings-0.002
Token the
Token ID262
Feature activation+3.53e-03

Pos logit contributions
one+0.002
lor+0.001
uan+0.001
 wizard+0.001
ooter+0.001
Neg logit contributions
Deal-0.001
 cartoons-0.001
girls-0.001
idents-0.001
 forth-0.001
Token bone
Token ID9970
Feature activation-1.20e-02

Pos logit contributions
one+0.005
 wizard+0.005
 robe+0.005
 begg+0.004
ired+0.004
Neg logit contributions
Deal-0.006
 cartoons-0.006
girls-0.006
idents-0.006
icious-0.005
Token was
Token ID373
Feature activation-1.16e-03

Pos logit contributions
Deal+0.019
 cartoons+0.018
girls+0.017
idents+0.017
boys+0.017
Neg logit contributions
one-0.021
uan-0.018
alks-0.017
lor-0.017
em-0.017
Token a
Token ID257
Feature activation-1.59e-02

Pos logit contributions
Deal+0.003
 cartoons+0.002
girls+0.002
idents+0.002
icious+0.002
Neg logit contributions
one-0.001
 wizard-0.001
uan-0.001
lor-0.001
 robe-0.001
Token y
Token ID331
Feature activation-7.51e-02

Pos logit contributions
Deal+0.029
girls+0.028
 cartoons+0.028
idents+0.026
icious+0.025
Neg logit contributions
one-0.024
 wizard-0.022
 robe-0.020
 begg-0.020
uan-0.020
Tokenummy
Token ID13513
Feature activation-3.74e-02

Pos logit contributions
Deal+0.127
 cartoons+0.122
girls+0.121
idents+0.109
boys+0.107
Neg logit contributions
one-0.127
 wizard-0.107
uan-0.106
ired-0.104
lor-0.103
Token sausage
Token ID31889
Feature activation-3.65e-02

Pos logit contributions
Deal+0.058
 cartoons+0.055
girls+0.054
idents+0.050
icious+0.048
Neg logit contributions
one-0.068
 wizard-0.060
uan-0.057
 robe-0.057
lor-0.056
Token.
Token ID13
Feature activation-2.29e-03

Pos logit contributions
 cartoons+0.059
Deal+0.059
girls+0.055
idents+0.052
boys+0.051
Neg logit contributions
one-0.064
uan-0.054
lor-0.053
 wizard-0.053
 robe-0.050
Token
Token ID220
Feature activation-1.01e-02

Pos logit contributions
 cartoons+0.004
Deal+0.004
girls+0.004
idents+0.004
 inviting+0.004
Neg logit contributions
one-0.004
 wizard-0.003
uan-0.003
lor-0.003
unk-0.003
Token
Token ID198
Feature activation+1.43e-05

Pos logit contributions
Deal+0.019
 cartoons+0.019
girls+0.019
idents+0.018
icious+0.017
Neg logit contributions
one-0.014
 wizard-0.013
uan-0.012
 robe-0.012
 begg-0.011
Token time
Token ID640
Feature activation+1.98e-02

Pos logit contributions
girls+0.004
 cartoons+0.004
Deal+0.004
idents+0.004
 forth+0.003
Neg logit contributions
one-0.002
 aid-0.001
ired-0.001
 robe-0.001
orse-0.001
Token,
Token ID11
Feature activation+8.33e-03

Pos logit contributions
one+0.034
 wizard+0.029
uan+0.029
lor+0.029
 robe+0.027
Neg logit contributions
 cartoons-0.032
Deal-0.032
girls-0.029
idents-0.029
 inviting-0.028
Token there
Token ID612
Feature activation+7.51e-03

Pos logit contributions
one+0.011
 wizard+0.008
 ago+0.008
uan+0.008
ired+0.008
Neg logit contributions
 cartoons-0.018
Deal-0.018
girls-0.017
idents-0.016
icious-0.016
Token was
Token ID373
Feature activation+2.47e-02

Pos logit contributions
one+0.012
 wizard+0.010
uan+0.010
lor+0.009
 robe+0.009
Neg logit contributions
Deal-0.014
 cartoons-0.013
girls-0.013
idents-0.012
icious-0.012
Token a
Token ID257
Feature activation-1.71e-02

Pos logit contributions
one+0.028
 wizard+0.020
uan+0.020
 robe+0.019
ired+0.019
Neg logit contributions
Deal-0.056
 cartoons-0.054
girls-0.054
idents-0.052
icious-0.050
Token y
Token ID331
Feature activation-7.50e-02

Pos logit contributions
girls+0.040
Deal+0.039
idents+0.038
 cartoons+0.038
icious+0.037
Neg logit contributions
 wizard-0.015
one-0.015
 begg-0.013
 robe-0.012
orse-0.011
Tokenummy
Token ID13513
Feature activation-3.60e-02

Pos logit contributions
Deal+0.150
girls+0.145
 cartoons+0.134
idents+0.128
boys+0.125
Neg logit contributions
one-0.100
 begg-0.087
 wizard-0.086
 oy-0.084
ired-0.084
Token cake
Token ID12187
Feature activation-2.23e-02

Pos logit contributions
Deal+0.068
 cartoons+0.066
girls+0.065
idents+0.062
icious+0.060
Neg logit contributions
one-0.053
 wizard-0.045
uan-0.043
 robe-0.041
lor-0.041
Token.
Token ID13
Feature activation-6.98e-03

Pos logit contributions
 cartoons+0.036
Deal+0.036
girls+0.033
idents+0.031
 inviting+0.031
Neg logit contributions
one-0.040
uan-0.033
 wizard-0.033
lor-0.032
em-0.031
Token It
Token ID632
Feature activation-2.06e-02

Pos logit contributions
 cartoons+0.015
Deal+0.014
girls+0.013
idents+0.013
 inviting+0.013
Neg logit contributions
one-0.009
lor-0.007
 wizard-0.007
uan-0.007
ooter-0.007
Token was
Token ID373
Feature activation-4.62e-03

Pos logit contributions
Deal+0.040
 cartoons+0.039
girls+0.038
idents+0.036
icious+0.036
Neg logit contributions
one-0.029
 wizard-0.024
uan-0.023
lor-0.023
 robe-0.022
Token cone
Token ID27763
Feature activation-1.96e-02

Pos logit contributions
 cartoons+0.002
Deal+0.002
girls+0.002
 forth+0.002
idents+0.002
Neg logit contributions
one-0.002
uan-0.002
lor-0.002
enna-0.002
 wizard-0.001
Token.
Token ID13
Feature activation-1.67e-02

Pos logit contributions
 cartoons+0.027
Deal+0.027
girls+0.025
 forth+0.024
boys+0.023
Neg logit contributions
one-0.038
uan-0.033
 wizard-0.033
lor-0.032
enna-0.031
Token It
Token ID632
Feature activation-2.52e-02

Pos logit contributions
 cartoons+0.031
Deal+0.031
girls+0.029
idents+0.028
 inviting+0.027
Neg logit contributions
one-0.026
lor-0.021
 wizard-0.021
uan-0.021
unk-0.020
Token looked
Token ID3114
Feature activation-3.56e-02

Pos logit contributions
Deal+0.057
 cartoons+0.055
girls+0.053
idents+0.052
icious+0.052
Neg logit contributions
one-0.029
 arrived-0.024
 wizard-0.023
 stub-0.021
uan-0.021
Token so
Token ID523
Feature activation-4.02e-02

Pos logit contributions
girls+0.073
Deal+0.069
boys+0.062
icious+0.061
aghetti+0.060
Neg logit contributions
one-0.043
 oy-0.043
 seen-0.043
 wizard-0.040
 begg-0.039
Token y
Token ID331
Feature activation-7.50e-02

Pos logit contributions
girls+0.064
 cartoons+0.056
boys+0.056
idents+0.053
Deal+0.053
Neg logit contributions
one-0.071
 oy-0.065
 begg-0.063
 arrived-0.061
 sur-0.060
Tokenummy
Token ID13513
Feature activation-3.76e-02

Pos logit contributions
 cartoons+0.132
Deal+0.131
girls+0.128
boys+0.115
idents+0.113
Neg logit contributions
one-0.122
uan-0.099
em-0.098
ired-0.098
alks-0.096
Token that
Token ID326
Feature activation-2.12e-02

Pos logit contributions
Deal+0.060
 cartoons+0.060
girls+0.055
idents+0.054
 inviting+0.052
Neg logit contributions
one-0.066
uan-0.056
 wizard-0.055
lor-0.055
 robe-0.053
Token she
Token ID673
Feature activation-2.11e-03

Pos logit contributions
Deal+0.050
girls+0.048
icious+0.047
idents+0.046
ksh+0.045
Neg logit contributions
one-0.023
 wizard-0.019
 arrived-0.017
 begg-0.016
 stub-0.015
Token asked
Token ID1965
Feature activation-1.31e-03

Pos logit contributions
Deal+0.004
 cartoons+0.004
girls+0.004
idents+0.004
icious+0.004
Neg logit contributions
one-0.003
 wizard-0.002
 arrived-0.002
 stub-0.002
uan-0.002
Token if
Token ID611
Feature activation-2.65e-02

Pos logit contributions
Deal+0.003
girls+0.002
 cartoons+0.002
icious+0.002
idents+0.002
Neg logit contributions
one-0.002
 wizard-0.002
uan-0.001
em-0.001
 arrived-0.001
Token ball
Token ID2613
Feature activation-3.48e-02

Pos logit contributions
 cartoons+0.029
Deal+0.029
girls+0.027
idents+0.026
icious+0.025
Neg logit contributions
one-0.026
uan-0.022
 wizard-0.021
lor-0.021
em-0.020
Token.
Token ID13
Feature activation-8.47e-03

Pos logit contributions
 cartoons+0.053
Deal+0.053
girls+0.047
 inviting+0.045
boys+0.044
Neg logit contributions
one-0.065
uan-0.057
lor-0.055
em-0.054
enna-0.054
Token It
Token ID632
Feature activation-2.08e-02

Pos logit contributions
 cartoons+0.019
Deal+0.018
girls+0.017
idents+0.017
 inviting+0.016
Neg logit contributions
one-0.010
lor-0.008
 wizard-0.008
uan-0.008
 robe-0.007
Token was
Token ID373
Feature activation-3.30e-03

Pos logit contributions
Deal+0.030
 cartoons+0.028
girls+0.026
 inviting+0.025
 y+0.024
Neg logit contributions
one-0.042
uan-0.036
lor-0.036
em-0.036
 wizard-0.035
Token so
Token ID523
Feature activation-4.49e-03

Pos logit contributions
Deal+0.005
 cartoons+0.005
girls+0.005
idents+0.005
icious+0.005
Neg logit contributions
one-0.006
 wizard-0.005
uan-0.005
lor-0.005
 robe-0.005
Token boun
Token ID31283
Feature activation-7.50e-02

Pos logit contributions
Deal+0.007
 cartoons+0.007
girls+0.006
idents+0.006
icious+0.006
Neg logit contributions
one-0.008
 wizard-0.007
uan-0.007
lor-0.007
 robe-0.007
Tokency
Token ID948
Feature activation-1.86e-02

Pos logit contributions
 cartoons+0.125
girls+0.119
Deal+0.113
icious+0.111
idents+0.105
Neg logit contributions
one-0.133
ane-0.112
uan-0.111
ired-0.109
 stub-0.107
Token and
Token ID290
Feature activation-1.09e-02

Pos logit contributions
Deal+0.030
 cartoons+0.029
girls+0.028
idents+0.026
 inviting+0.025
Neg logit contributions
one-0.033
uan-0.028
 wizard-0.028
lor-0.027
 robe-0.026
Token fun
Token ID1257
Feature activation-5.11e-03

Pos logit contributions
 cartoons+0.019
Deal+0.019
girls+0.018
idents+0.017
icious+0.017
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.014
 robe-0.014
orse-0.014
Token to
Token ID284
Feature activation-1.43e-02

Pos logit contributions
Deal+0.009
 cartoons+0.009
girls+0.008
idents+0.008
icious+0.008
Neg logit contributions
one-0.008
 wizard-0.007
uan-0.007
lor-0.007
 robe-0.007
Token play
Token ID711
Feature activation-2.72e-02

Pos logit contributions
Deal+0.017
 cartoons+0.016
girls+0.015
idents+0.014
icious+0.013
Neg logit contributions
one-0.032
 wizard-0.028
uan-0.027
lor-0.027
 robe-0.026
Token time
Token ID640
Feature activation+2.02e-02

Pos logit contributions
 cartoons+0.006
girls+0.006
Deal+0.006
idents+0.005
 forth+0.005
Neg logit contributions
one-0.003
 aid-0.003
 robe-0.002
ired-0.002
lor-0.002
Token,
Token ID11
Feature activation+8.19e-03

Pos logit contributions
one+0.035
 wizard+0.030
uan+0.030
lor+0.030
 robe+0.029
Neg logit contributions
Deal-0.032
 cartoons-0.032
girls-0.029
idents-0.029
 inviting-0.028
Token there
Token ID612
Feature activation+6.32e-03

Pos logit contributions
one+0.010
 wizard+0.007
 ago+0.007
ired+0.007
uan+0.006
Neg logit contributions
Deal-0.018
 cartoons-0.018
girls-0.018
idents-0.017
icious-0.017
Token was
Token ID373
Feature activation+2.45e-02

Pos logit contributions
one+0.010
 wizard+0.008
uan+0.008
lor+0.008
ired+0.007
Neg logit contributions
Deal-0.012
 cartoons-0.012
girls-0.011
idents-0.010
icious-0.010
Token a
Token ID257
Feature activation-1.72e-02

Pos logit contributions
one+0.027
 wizard+0.020
uan+0.019
ired+0.018
 ago+0.018
Neg logit contributions
Deal-0.056
 cartoons-0.054
girls-0.054
idents-0.052
icious-0.050
Token y
Token ID331
Feature activation-7.49e-02

Pos logit contributions
girls+0.040
Deal+0.039
 cartoons+0.038
idents+0.037
icious+0.036
Neg logit contributions
 wizard-0.016
one-0.016
 begg-0.013
 robe-0.013
orse-0.012
Tokenummy
Token ID13513
Feature activation-3.65e-02

Pos logit contributions
Deal+0.146
girls+0.140
 cartoons+0.133
idents+0.124
boys+0.122
Neg logit contributions
one-0.104
 wizard-0.091
 begg-0.090
uan-0.087
 oy-0.087
Token treat
Token ID2190
Feature activation-1.47e-02

Pos logit contributions
Deal+0.068
 cartoons+0.066
girls+0.064
idents+0.061
icious+0.060
Neg logit contributions
one-0.055
 wizard-0.046
uan-0.044
lor-0.043
 robe-0.043
Token.
Token ID13
Feature activation-4.37e-03

Pos logit contributions
 cartoons+0.024
Deal+0.024
girls+0.022
idents+0.021
boys+0.021
Neg logit contributions
one-0.025
uan-0.021
 wizard-0.021
lor-0.021
 robe-0.020
Token It
Token ID632
Feature activation-1.77e-02

Pos logit contributions
 cartoons+0.009
Deal+0.009
girls+0.009
idents+0.008
 inviting+0.008
Neg logit contributions
one-0.006
 wizard-0.004
lor-0.004
uan-0.004
ooter-0.004
Token was
Token ID373
Feature activation-4.02e-03

Pos logit contributions
 cartoons+0.035
Deal+0.035
girls+0.035
idents+0.033
icious+0.033
Neg logit contributions
one-0.022
 wizard-0.019
uan-0.018
 arrived-0.018
 robe-0.018
Token day
Token ID1110
Feature activation-2.85e-04

Pos logit contributions
Deal+0.018
 cartoons+0.018
girls+0.018
idents+0.016
icious+0.016
Neg logit contributions
one-0.015
 wizard-0.013
uan-0.012
ired-0.012
 robe-0.012
Token,
Token ID11
Feature activation-6.35e-03

Pos logit contributions
 cartoons+0.000
Deal+0.000
idents+0.000
 y+0.000
 forth+0.000
Neg logit contributions
one-0.001
lor-0.001
uan-0.001
 wizard-0.001
enna-0.000
Token she
Token ID673
Feature activation+2.19e-03

Pos logit contributions
girls+0.013
Deal+0.013
 cartoons+0.013
icious+0.012
boys+0.012
Neg logit contributions
one-0.008
 wizard-0.006
 robe-0.006
uan-0.006
 stub-0.006
Token smelled
Token ID37609
Feature activation-1.64e-02

Pos logit contributions
one+0.003
 wizard+0.002
uan+0.002
lor+0.002
 robe+0.002
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.004
idents-0.004
icious-0.004
Token something
Token ID1223
Feature activation-3.54e-02

Pos logit contributions
Deal+0.035
girls+0.034
 cartoons+0.031
boys+0.030
idents+0.030
Neg logit contributions
one-0.022
 wizard-0.017
 oy-0.016
uan-0.016
em-0.016
Token y
Token ID331
Feature activation-7.46e-02

Pos logit contributions
girls+0.055
Deal+0.051
 cartoons+0.045
boys+0.044
 forth+0.043
Neg logit contributions
one-0.066
 wizard-0.059
 oy-0.057
em-0.056
 arrived-0.056
Tokenummy
Token ID13513
Feature activation-3.77e-02

Pos logit contributions
Deal+0.138
 cartoons+0.137
girls+0.136
boys+0.122
 inviting+0.117
Neg logit contributions
one-0.114
ired-0.093
em-0.093
uan-0.091
ump-0.090
Token coming
Token ID2406
Feature activation-2.47e-04

Pos logit contributions
Deal+0.069
 cartoons+0.068
girls+0.065
idents+0.061
icious+0.061
Neg logit contributions
one-0.059
 wizard-0.048
uan-0.047
em-0.046
lor-0.046
Token from
Token ID422
Feature activation-5.10e-02

Pos logit contributions
Deal+0.001
girls+0.000
 cartoons+0.000
icious+0.000
idents+0.000
Neg logit contributions
one-0.000
em-0.000
uan-0.000
 wizard-0.000
alks-0.000
Token the
Token ID262
Feature activation-1.11e-02

Pos logit contributions
Deal+0.092
 cartoons+0.087
girls+0.085
icious+0.081
idents+0.080
Neg logit contributions
one-0.080
 wizard-0.070
uan-0.065
 robe-0.065
 ago-0.065
Token kitchen
Token ID9592
Feature activation+9.29e-04

Pos logit contributions
Deal+0.021
 cartoons+0.020
girls+0.020
idents+0.019
icious+0.018
Neg logit contributions
one-0.016
 wizard-0.014
 robe-0.013
lor-0.013
uan-0.013
Token treat
Token ID2190
Feature activation-2.16e-02

Pos logit contributions
Deal+0.063
 cartoons+0.063
girls+0.060
idents+0.057
icious+0.055
Neg logit contributions
one-0.058
 wizard-0.049
uan-0.048
lor-0.047
 robe-0.046
Token.
Token ID13
Feature activation-2.45e-02

Pos logit contributions
Deal+0.034
 cartoons+0.034
girls+0.031
idents+0.030
boys+0.029
Neg logit contributions
one-0.039
 wizard-0.032
uan-0.032
lor-0.032
 robe-0.031
Token It
Token ID632
Feature activation-3.46e-02

Pos logit contributions
Deal+0.042
 cartoons+0.041
girls+0.040
idents+0.037
icious+0.037
Neg logit contributions
one-0.040
 wizard-0.033
uan-0.033
lor-0.032
 robe-0.032
Token was
Token ID373
Feature activation-1.02e-02

Pos logit contributions
Deal+0.075
girls+0.074
 cartoons+0.073
icious+0.069
idents+0.066
Neg logit contributions
one-0.041
 arrived-0.033
 wizard-0.033
uan-0.031
lor-0.029
Token a
Token ID257
Feature activation-1.46e-02

Pos logit contributions
Deal+0.024
girls+0.023
idents+0.021
 cartoons+0.020
boys+0.020
Neg logit contributions
one-0.011
 wizard-0.009
 begg-0.009
 ago-0.009
em-0.008
Token y
Token ID331
Feature activation-7.46e-02

Pos logit contributions
girls+0.027
Deal+0.026
 cartoons+0.024
boys+0.023
idents+0.023
Neg logit contributions
 wizard-0.021
one-0.020
 robe-0.019
 begg-0.019
 tool-0.019
Tokenummy
Token ID13513
Feature activation-3.31e-02

Pos logit contributions
Deal+0.138
girls+0.137
 cartoons+0.132
boys+0.123
idents+0.118
Neg logit contributions
one-0.111
ired-0.092
uan-0.090
em-0.089
alks-0.089
Token cookie
Token ID19751
Feature activation-3.75e-02

Pos logit contributions
Deal+0.048
girls+0.047
 cartoons+0.046
idents+0.041
boys+0.041
Neg logit contributions
one-0.062
 wizard-0.055
uan-0.052
 robe-0.052
lor-0.052
Token,
Token ID11
Feature activation-8.46e-03

Pos logit contributions
Deal+0.070
 cartoons+0.069
girls+0.067
idents+0.064
icious+0.062
Neg logit contributions
one-0.055
 wizard-0.046
uan-0.043
lor-0.043
 robe-0.042
Token all
Token ID477
Feature activation+1.14e-03

Pos logit contributions
girls+0.016
Deal+0.016
 cartoons+0.015
idents+0.014
icious+0.014
Neg logit contributions
one-0.012
 wizard-0.010
 robe-0.010
 begg-0.009
 ago-0.009
Token soft
Token ID2705
Feature activation-1.75e-02

Pos logit contributions
one+0.002
 wizard+0.001
uan+0.001
em+0.001
 arrived+0.001
Neg logit contributions
girls-0.002
Deal-0.002
 cartoons-0.002
idents-0.002
icious-0.002
Token Her
Token ID2332
Feature activation-6.88e-04

Pos logit contributions
 cartoons+0.020
Deal+0.018
idents+0.017
girls+0.017
 inviting+0.017
Neg logit contributions
one-0.017
 wizard-0.014
lor-0.014
uan-0.014
unk-0.013
Token grandma
Token ID49890
Feature activation-9.19e-03

Pos logit contributions
Deal+0.001
 cartoons+0.001
girls+0.001
icious+0.001
idents+0.001
Neg logit contributions
one-0.001
 wizard-0.001
uan-0.001
lor-0.001
ired-0.001
Token made
Token ID925
Feature activation-1.24e-02

Pos logit contributions
 cartoons+0.018
Deal+0.018
girls+0.018
idents+0.017
icious+0.017
Neg logit contributions
one-0.013
 wizard-0.010
uan-0.010
 arrived-0.009
ired-0.009
Token her
Token ID607
Feature activation+1.21e-02

Pos logit contributions
Deal+0.026
girls+0.024
 cartoons+0.022
idents+0.022
 forth+0.022
Neg logit contributions
one-0.018
em-0.014
 wizard-0.014
uan-0.014
 begg-0.014
Token a
Token ID257
Feature activation-1.90e-02

Pos logit contributions
one+0.013
 aid+0.012
 begg+0.011
 robe+0.011
 wizard+0.011
Neg logit contributions
Deal-0.026
girls-0.025
icious-0.024
 cartoons-0.024
 forth-0.022
Token y
Token ID331
Feature activation-7.44e-02

Pos logit contributions
girls+0.041
Deal+0.039
ksh+0.034
 forth+0.033
icious+0.033
Neg logit contributions
 wizard-0.023
 begg-0.022
 robe-0.022
 tool-0.022
 aid-0.021
Tokenummy
Token ID13513
Feature activation-2.81e-02

Pos logit contributions
Deal+0.144
girls+0.143
 cartoons+0.132
boys+0.125
idents+0.121
Neg logit contributions
one-0.104
ired-0.089
lor-0.085
ump-0.084
 begg-0.084
Token cake
Token ID12187
Feature activation-3.14e-02

Pos logit contributions
girls+0.049
Deal+0.048
boys+0.041
icious+0.040
 cartoons+0.040
Neg logit contributions
one-0.042
 wizard-0.041
 robe-0.040
 begg-0.038
 eye-0.038
Token.
Token ID13
Feature activation-1.87e-02

Pos logit contributions
girls+0.062
Deal+0.062
 cartoons+0.057
icious+0.054
idents+0.054
Neg logit contributions
one-0.039
 wizard-0.034
em-0.033
 eye-0.032
 begg-0.031
Token Lily
Token ID20037
Feature activation+8.49e-03

Pos logit contributions
Deal+0.034
 cartoons+0.034
girls+0.032
idents+0.031
icious+0.030
Neg logit contributions
one-0.029
 wizard-0.024
uan-0.023
lor-0.023
 robe-0.022
Token loved
Token ID6151
Feature activation-2.44e-02

Pos logit contributions
one+0.012
 wizard+0.010
 arrived+0.009
uan+0.009
 robe+0.009
Neg logit contributions
 cartoons-0.017
Deal-0.016
girls-0.016
icious-0.015
idents-0.015
Token Tim
Token ID5045
Feature activation-7.69e-03

Pos logit contributions
icious+0.013
girls+0.013
Deal+0.013
ksh+0.012
boys+0.012
Neg logit contributions
one-0.010
 arrived-0.008
 eight-0.008
 tool-0.007
 There-0.007
Token's
Token ID338
Feature activation-1.43e-02

Pos logit contributions
Deal+0.011
boys+0.011
 cartoons+0.011
girls+0.011
 forth+0.011
Neg logit contributions
one-0.014
lor-0.013
alks-0.012
 wizard-0.012
uan-0.012
Token mom
Token ID1995
Feature activation-2.50e-02

Pos logit contributions
Deal+0.032
 cartoons+0.031
girls+0.030
icious+0.029
idents+0.029
Neg logit contributions
one-0.016
 wizard-0.012
 aid-0.012
ired-0.012
 robe-0.012
Token made
Token ID925
Feature activation-1.73e-02

Pos logit contributions
 cartoons+0.044
Deal+0.044
girls+0.041
boys+0.040
idents+0.039
Neg logit contributions
one-0.040
lor-0.034
 wizard-0.033
uan-0.033
alks-0.032
Token a
Token ID257
Feature activation-1.99e-02

Pos logit contributions
Deal+0.036
girls+0.032
icious+0.030
 cartoons+0.030
idents+0.030
Neg logit contributions
one-0.024
ired-0.019
unk-0.019
uan-0.018
 wizard-0.018
Token y
Token ID331
Feature activation-7.41e-02

Pos logit contributions
girls+0.040
Deal+0.038
 cartoons+0.035
ksh+0.034
icious+0.034
Neg logit contributions
 wizard-0.025
 tool-0.025
 begg-0.023
 aid-0.023
one-0.023
Tokenummy
Token ID13513
Feature activation-2.88e-02

Pos logit contributions
Deal+0.138
girls+0.135
 cartoons+0.129
boys+0.119
idents+0.117
Neg logit contributions
one-0.109
ired-0.093
em-0.089
 begg-0.089
alks-0.089
Token steak
Token ID26320
Feature activation-3.48e-02

Pos logit contributions
Deal+0.047
girls+0.046
 cartoons+0.042
icious+0.040
boys+0.039
Neg logit contributions
one-0.046
 wizard-0.045
 robe-0.042
 begg-0.041
 tool-0.041
Token for
Token ID329
Feature activation-2.72e-02

Pos logit contributions
Deal+0.059
 cartoons+0.057
girls+0.055
icious+0.052
idents+0.052
Neg logit contributions
one-0.056
 wizard-0.051
uan-0.046
 ago-0.046
 robe-0.045
Token dinner
Token ID8073
Feature activation-1.36e-02

Pos logit contributions
Deal+0.050
girls+0.041
idents+0.041
ksh+0.040
icious+0.039
Neg logit contributions
one-0.042
orse-0.036
alks-0.036
 robe-0.036
 wizard-0.036
Token.
Token ID13
Feature activation-2.00e-02

Pos logit contributions
Deal+0.026
 cartoons+0.026
girls+0.026
idents+0.025
icious+0.024
Neg logit contributions
one-0.019
 wizard-0.015
lor-0.014
em-0.014
 ago-0.014
TokenOnce
Token ID7454
Feature activation-1.19e-02

Pos logit contributions
 cartoons+0.022
Deal+0.022
girls+0.021
 inviting+0.019
idents+0.019
Neg logit contributions
one-0.015
 wizard-0.012
uan-0.012
ooter-0.012
lor-0.011
Token,
Token ID11
Feature activation+4.48e-04

Pos logit contributions
 cartoons+0.018
Deal+0.017
idents+0.016
girls+0.016
 inviting+0.016
Neg logit contributions
one-0.021
lor-0.019
 wizard-0.018
 robe-0.018
 begg-0.018
Token there
Token ID612
Feature activation+4.23e-03

Pos logit contributions
one+0.001
 ago+0.000
 wizard+0.000
ired+0.000
 arrived+0.000
Neg logit contributions
girls-0.001
 cartoons-0.001
Deal-0.001
icious-0.001
idents-0.001
Token was
Token ID373
Feature activation+2.44e-02

Pos logit contributions
one+0.007
 wizard+0.006
uan+0.006
lor+0.006
alks+0.006
Neg logit contributions
Deal-0.007
 cartoons-0.007
girls-0.006
idents-0.006
 inviting-0.006
Token a
Token ID257
Feature activation-1.51e-02

Pos logit contributions
one+0.027
 wizard+0.019
uan+0.019
 robe+0.018
ired+0.018
Neg logit contributions
Deal-0.056
 cartoons-0.054
girls-0.054
idents-0.052
 forth-0.051
Token y
Token ID331
Feature activation-7.40e-02

Pos logit contributions
Deal+0.033
girls+0.032
 cartoons+0.032
idents+0.031
icious+0.030
Neg logit contributions
one-0.017
 wizard-0.014
uan-0.013
 robe-0.012
 begg-0.012
Tokenummy
Token ID13513
Feature activation-3.76e-02

Pos logit contributions
Deal+0.144
girls+0.139
 cartoons+0.131
idents+0.125
boys+0.122
Neg logit contributions
one-0.103
 wizard-0.089
 begg-0.089
ired-0.086
uan-0.085
Token books
Token ID3835
Feature activation-1.51e-02

Pos logit contributions
Deal+0.069
 cartoons+0.069
girls+0.066
idents+0.062
icious+0.061
Neg logit contributions
one-0.057
 wizard-0.047
uan-0.046
lor-0.045
 robe-0.044
Tokenhe
Token ID258
Feature activation-4.53e-03

Pos logit contributions
Deal+0.025
 cartoons+0.024
girls+0.023
idents+0.022
icious+0.021
Neg logit contributions
one-0.026
 wizard-0.022
uan-0.021
lor-0.021
 robe-0.021
Tokenlf
Token ID1652
Feature activation-1.36e-02

Pos logit contributions
Deal+0.007
girls+0.007
idents+0.007
 cartoons+0.006
icious+0.006
Neg logit contributions
one-0.008
 wizard-0.007
 robe-0.007
unk-0.007
lor-0.007
Token in
Token ID287
Feature activation+6.86e-03

Pos logit contributions
Deal+0.023
 cartoons+0.023
girls+0.022
idents+0.021
icious+0.021
Neg logit contributions
one-0.023
 wizard-0.019
uan-0.018
lor-0.018
ired-0.018
Token.
Token ID13
Feature activation-7.13e-03

Pos logit contributions
Deal+0.046
girls+0.045
 cartoons+0.044
icious+0.040
idents+0.040
Neg logit contributions
one-0.028
ired-0.020
 wizard-0.020
 aid-0.020
 ago-0.019
Token He
Token ID679
Feature activation-1.22e-02

Pos logit contributions
 cartoons+0.015
Deal+0.015
girls+0.014
idents+0.014
 inviting+0.014
Neg logit contributions
one-0.009
lor-0.007
uan-0.007
 wizard-0.007
em-0.006
Token thought
Token ID1807
Feature activation-6.28e-03

Pos logit contributions
 cartoons+0.027
Deal+0.027
girls+0.026
idents+0.025
icious+0.025
Neg logit contributions
one-0.014
 wizard-0.011
uan-0.011
orse-0.010
 robe-0.010
Token it
Token ID340
Feature activation-3.79e-02

Pos logit contributions
Deal+0.012
 cartoons+0.012
girls+0.011
idents+0.011
icious+0.010
Neg logit contributions
one-0.010
 wizard-0.008
uan-0.008
lor-0.007
 robe-0.007
Token looked
Token ID3114
Feature activation-2.86e-02

Pos logit contributions
 cartoons+0.089
girls+0.086
icious+0.085
Deal+0.082
 forth+0.076
Neg logit contributions
one-0.036
 arrived-0.033
 wizard-0.028
 stumbled-0.027
 stepped-0.025
Token y
Token ID331
Feature activation-7.38e-02

Pos logit contributions
girls+0.057
Deal+0.050
 cartoons+0.050
boys+0.049
glers+0.047
Neg logit contributions
 seen-0.037
one-0.036
 oy-0.035
 shell-0.032
 points-0.031
Tokenummy
Token ID13513
Feature activation-4.27e-02

Pos logit contributions
Deal+0.132
 cartoons+0.131
girls+0.127
boys+0.114
idents+0.113
Neg logit contributions
one-0.120
uan-0.097
ired-0.096
em-0.096
alks-0.092
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
Deal+0.092
 cartoons+0.092
girls+0.090
icious+0.087
idents+0.084
Neg logit contributions
one-0.052
 wizard-0.038
 oy-0.037
 ago-0.037
em-0.037
Token He
Token ID679
Feature activation-1.50e-02

Pos logit contributions
Deal+0.022
 cartoons+0.021
girls+0.020
idents+0.020
icious+0.019
Neg logit contributions
one-0.013
 wizard-0.010
uan-0.010
lor-0.009
em-0.009
Token smiled
Token ID13541
Feature activation-3.55e-03

Pos logit contributions
 cartoons+0.032
Deal+0.032
girls+0.031
idents+0.030
icious+0.029
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.014
 robe-0.014
 arrived-0.014
Token and
Token ID290
Feature activation-1.81e-02

Pos logit contributions
Deal+0.007
 cartoons+0.006
girls+0.006
idents+0.006
icious+0.006
Neg logit contributions
one-0.005
 wizard-0.005
uan-0.004
ired-0.004
lor-0.004
Token
Token ID198
Feature activation+4.09e-03

Pos logit contributions
one+0.012
 wizard+0.010
uan+0.010
 robe+0.009
alks+0.009
Neg logit contributions
Deal-0.016
 cartoons-0.016
girls-0.015
 inviting-0.015
icious-0.014
TokenOne
Token ID3198
Feature activation-2.02e-03

Pos logit contributions
one+0.008
 wizard+0.007
uan+0.007
lor+0.006
 robe+0.006
Neg logit contributions
Deal-0.006
 cartoons-0.006
girls-0.006
idents-0.005
icious-0.005
Token day
Token ID1110
Feature activation+1.02e-02

Pos logit contributions
 cartoons+0.003
Deal+0.003
girls+0.003
idents+0.003
 inviting+0.003
Neg logit contributions
one-0.004
lor-0.003
uan-0.003
 wizard-0.003
 robe-0.003
Token,
Token ID11
Feature activation+4.92e-03

Pos logit contributions
one+0.019
lor+0.018
ooter+0.017
uan+0.017
enna+0.017
Neg logit contributions
 cartoons-0.016
Deal-0.014
girls-0.013
 y-0.013
 inviting-0.013
Token the
Token ID262
Feature activation+2.85e-02

Pos logit contributions
one+0.007
 wizard+0.005
uan+0.005
 robe+0.005
 begg+0.005
Neg logit contributions
Deal-0.010
 cartoons-0.010
girls-0.009
icious-0.009
idents-0.009
Token bald
Token ID28273
Feature activation+6.00e-02

Pos logit contributions
one+0.047
lor+0.040
uan+0.038
alks+0.037
ously+0.037
Neg logit contributions
 cartoons-0.052
Deal-0.050
 y-0.045
girls-0.045
idents-0.044
Token man
Token ID582
Feature activation+1.44e-02

Pos logit contributions
one+0.118
lor+0.104
uan+0.101
reetings+0.100
enna+0.099
Neg logit contributions
 cartoons-0.084
Deal-0.082
idents-0.072
 y-0.066
 forth-0.066
Token was
Token ID373
Feature activation+3.93e-03

Pos logit contributions
one+0.023
lor+0.020
alks+0.019
uan+0.019
 wizard+0.019
Neg logit contributions
 cartoons-0.024
Deal-0.024
girls-0.023
boys-0.023
 forth-0.022
Token walking
Token ID6155
Feature activation+2.24e-03

Pos logit contributions
one+0.007
uan+0.006
lor+0.006
 wizard+0.006
alks+0.006
Neg logit contributions
 cartoons-0.006
Deal-0.006
girls-0.005
 inviting-0.005
boys-0.005
Token down
Token ID866
Feature activation+1.74e-02

Pos logit contributions
one+0.004
 wizard+0.003
uan+0.003
lor+0.003
 robe+0.003
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.003
idents-0.003
icious-0.003
Token the
Token ID262
Feature activation-2.11e-03

Pos logit contributions
one+0.039
lor+0.037
ooter+0.035
uan+0.034
orse+0.034
Neg logit contributions
 cartoons-0.020
 inviting-0.018
 together-0.017
Deal-0.017
girls-0.017
Token He
Token ID679
Feature activation-6.31e-03

Pos logit contributions
one+0.020
 wizard+0.017
lor+0.016
uan+0.016
enna+0.016
Neg logit contributions
 cartoons-0.022
Deal-0.022
girls-0.022
idents-0.020
boys-0.019
Token's
Token ID338
Feature activation-1.11e-02

Pos logit contributions
Deal+0.010
 cartoons+0.010
girls+0.010
idents+0.009
boys+0.009
Neg logit contributions
one-0.011
 wizard-0.009
uan-0.009
lor-0.009
 robe-0.009
Token better
Token ID1365
Feature activation+7.87e-03

Pos logit contributions
Deal+0.015
 cartoons+0.015
girls+0.014
idents+0.013
icious+0.012
Neg logit contributions
one-0.023
 wizard-0.020
uan-0.019
lor-0.019
 robe-0.019
Token than
Token ID621
Feature activation-1.08e-02

Pos logit contributions
one+0.014
uan+0.012
lor+0.011
 wizard+0.011
enna+0.011
Neg logit contributions
Deal-0.013
 cartoons-0.013
girls-0.012
 forth-0.012
idents-0.012
Token your
Token ID534
Feature activation+3.09e-02

Pos logit contributions
 cartoons+0.015
Deal+0.013
girls+0.013
 inviting+0.012
idents+0.012
Neg logit contributions
one-0.022
lor-0.020
uan-0.020
 wizard-0.019
ired-0.019
Token old
Token ID1468
Feature activation+5.67e-02

Pos logit contributions
one+0.044
 wizard+0.035
uan+0.035
lor+0.034
em+0.032
Neg logit contributions
Deal-0.061
 cartoons-0.061
girls-0.058
idents-0.055
icious-0.053
Token toy
Token ID13373
Feature activation+2.65e-02

Pos logit contributions
one+0.083
lor+0.067
uan+0.067
em+0.063
 wizard+0.061
Neg logit contributions
 cartoons-0.109
Deal-0.109
girls-0.104
idents-0.100
boys-0.097
Token.
Token ID13
Feature activation+4.35e-03

Pos logit contributions
one+0.042
 wizard+0.035
uan+0.034
lor+0.033
 robe+0.032
Neg logit contributions
Deal-0.047
 cartoons-0.047
girls-0.044
idents-0.043
icious-0.042
Token You
Token ID921
Feature activation+6.61e-03

Pos logit contributions
one+0.006
 wizard+0.005
uan+0.005
lor+0.005
ired+0.005
Neg logit contributions
 cartoons-0.008
Deal-0.008
girls-0.008
idents-0.007
 inviting-0.007
Token don
Token ID836
Feature activation-1.67e-02

Pos logit contributions
one+0.012
 wizard+0.010
uan+0.010
lor+0.010
ired+0.010
Neg logit contributions
 cartoons-0.010
Deal-0.010
girls-0.010
idents-0.009
icious-0.009
Token't
Token ID470
Feature activation+1.88e-02

Pos logit contributions
Deal+0.036
 cartoons+0.034
girls+0.033
idents+0.032
 forth+0.031
Neg logit contributions
one-0.022
lor-0.016
 wizard-0.016
uan-0.016
ired-0.015
Token and
Token ID290
Feature activation-7.28e-03

Pos logit contributions
one+0.051
 wizard+0.042
uan+0.041
lor+0.041
 robe+0.039
Neg logit contributions
Deal-0.058
 cartoons-0.058
girls-0.055
idents-0.052
icious-0.050
Token most
Token ID749
Feature activation+1.44e-02

Pos logit contributions
 cartoons+0.011
Deal+0.010
girls+0.010
idents+0.010
icious+0.009
Neg logit contributions
one-0.014
 wizard-0.012
 begg-0.012
uan-0.012
em-0.011
Token beautiful
Token ID4950
Feature activation+2.11e-02

Pos logit contributions
one+0.030
 wizard+0.026
uan+0.025
 begg+0.025
ired+0.025
Neg logit contributions
Deal-0.019
 cartoons-0.018
girls-0.018
idents-0.017
icious-0.016
Token tree
Token ID5509
Feature activation-4.10e-03

Pos logit contributions
one+0.033
 wizard+0.027
uan+0.026
lor+0.026
 robe+0.025
Neg logit contributions
Deal-0.038
 cartoons-0.038
girls-0.037
idents-0.035
icious-0.034
Token Lily
Token ID20037
Feature activation+2.21e-02

Pos logit contributions
Deal+0.008
 cartoons+0.008
girls+0.007
idents+0.007
icious+0.007
Neg logit contributions
one-0.006
 wizard-0.005
uan-0.005
lor-0.005
 ago-0.005
Token had
Token ID550
Feature activation+4.86e-02

Pos logit contributions
one+0.035
 wizard+0.029
uan+0.028
lor+0.028
 robe+0.027
Neg logit contributions
Deal-0.039
 cartoons-0.038
girls-0.037
idents-0.035
boys-0.034
Token ever
Token ID1683
Feature activation+1.03e-02

Pos logit contributions
one+0.090
 wizard+0.083
ooter+0.082
uan+0.082
alks+0.080
Neg logit contributions
Deal-0.066
girls-0.059
 together-0.059
boys-0.057
 y-0.056
Token seen
Token ID1775
Feature activation+2.08e-02

Pos logit contributions
one+0.010
anger+0.009
lor+0.009
ooter+0.009
ane+0.008
Neg logit contributions
Deal-0.022
 y-0.022
girls-0.022
 cartoons-0.022
 inviting-0.021
Token.
Token ID13
Feature activation-3.64e-03

Pos logit contributions
one+0.032
 wizard+0.026
lor+0.026
uan+0.025
 ago+0.024
Neg logit contributions
Deal-0.039
 cartoons-0.038
girls-0.036
idents-0.035
icious-0.034
Token She
Token ID1375
Feature activation-4.93e-03

Pos logit contributions
 cartoons+0.006
Deal+0.006
girls+0.006
idents+0.005
 inviting+0.005
Neg logit contributions
one-0.006
 wizard-0.005
 robe-0.005
lor-0.005
uan-0.005
Token was
Token ID373
Feature activation+5.45e-03

Pos logit contributions
Deal+0.009
 cartoons+0.008
girls+0.008
idents+0.008
boys+0.007
Neg logit contributions
one-0.008
 wizard-0.007
uan-0.007
lor-0.006
em-0.006
Token was
Token ID373
Feature activation+1.75e-02

Pos logit contributions
one+0.013
 wizard+0.011
uan+0.010
 robe+0.010
 arrived+0.010
Neg logit contributions
 cartoons-0.014
girls-0.013
Deal-0.013
icious-0.013
idents-0.013
Token very
Token ID845
Feature activation+1.60e-03

Pos logit contributions
one+0.043
lor+0.038
uan+0.038
 wizard+0.037
em+0.036
Neg logit contributions
 cartoons-0.017
Deal-0.016
girls-0.015
 inviting-0.014
boys-0.014
Token curious
Token ID11040
Feature activation+5.31e-03

Pos logit contributions
one+0.003
lor+0.003
uan+0.003
 wizard+0.003
em+0.003
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
idents-0.002
 inviting-0.002
Token.
Token ID13
Feature activation-1.69e-02

Pos logit contributions
one+0.008
 wizard+0.007
uan+0.007
lor+0.007
ired+0.007
Neg logit contributions
Deal-0.010
 cartoons-0.009
girls-0.009
idents-0.009
icious-0.008
Token He
Token ID679
Feature activation-7.60e-03

Pos logit contributions
Deal+0.039
 cartoons+0.038
girls+0.037
idents+0.035
icious+0.035
Neg logit contributions
one-0.019
 wizard-0.013
uan-0.013
ooter-0.013
 ago-0.013
Token had
Token ID550
Feature activation+4.32e-02

Pos logit contributions
Deal+0.012
 cartoons+0.012
girls+0.011
idents+0.011
boys+0.010
Neg logit contributions
one-0.014
 wizard-0.012
uan-0.011
lor-0.011
em-0.011
Token bright
Token ID6016
Feature activation+5.16e-04

Pos logit contributions
anger+0.090
one+0.090
reetings+0.083
ane+0.082
fer+0.082
Neg logit contributions
 y-0.052
 inviting-0.052
 both-0.049
 cartoons-0.049
 fun-0.047
Token eyes
Token ID2951
Feature activation+6.05e-04

Pos logit contributions
one+0.001
lor+0.001
 wizard+0.001
uan+0.001
em+0.001
Neg logit contributions
 cartoons-0.001
Deal-0.001
girls-0.001
 inviting-0.001
 forth-0.001
Token with
Token ID351
Feature activation+1.92e-02

Pos logit contributions
one+0.001
 wizard+0.001
uan+0.001
lor+0.001
em+0.001
Neg logit contributions
 cartoons-0.001
Deal-0.001
girls-0.001
 inviting-0.001
boys-0.001
Token sharp
Token ID7786
Feature activation+7.40e-03

Pos logit contributions
one+0.039
lor+0.035
 wizard+0.033
em+0.032
 aid+0.032
Neg logit contributions
 cartoons-0.027
 inviting-0.024
 y-0.023
Deal-0.023
girls-0.023
Token pupils
Token ID25613
Feature activation+4.12e-02

Pos logit contributions
one+0.015
lor+0.014
 wizard+0.014
 begg+0.013
fer+0.013
Neg logit contributions
 cartoons-0.009
 y-0.008
girls-0.008
idents-0.008
 forth-0.008
Token.
Token ID13
Feature activation+1.09e-03

Pos logit contributions
Deal+0.017
 cartoons+0.017
girls+0.016
idents+0.015
icious+0.015
Neg logit contributions
one-0.015
 wizard-0.013
uan-0.012
lor-0.012
 robe-0.012
Token
Token ID198
Feature activation+1.79e-02

Pos logit contributions
one+0.002
 wizard+0.001
 robe+0.001
uan+0.001
lor+0.001
Neg logit contributions
Deal-0.002
 cartoons-0.002
girls-0.002
 inviting-0.002
idents-0.002
Token
Token ID198
Feature activation+1.58e-02

Pos logit contributions
one+0.025
 wizard+0.020
uan+0.020
lor+0.019
 robe+0.019
Neg logit contributions
Deal-0.035
 cartoons-0.035
girls-0.033
 inviting-0.032
icious-0.031
TokenCh
Token ID1925
Feature activation-7.39e-03

Pos logit contributions
one+0.027
 wizard+0.023
uan+0.022
lor+0.022
 robe+0.021
Neg logit contributions
 cartoons-0.026
Deal-0.026
girls-0.025
idents-0.024
icious-0.022
Tokenant
Token ID415
Feature activation+1.54e-02

Pos logit contributions
 cartoons+0.011
Deal+0.011
girls+0.010
icious+0.010
idents+0.010
Neg logit contributions
one-0.013
 wizard-0.012
 begg-0.011
 robe-0.011
uan-0.011
Tokenelle
Token ID13485
Feature activation+4.95e-02

Pos logit contributions
one+0.024
lor+0.021
 wizard+0.021
uan+0.021
alks+0.020
Neg logit contributions
Deal-0.027
 cartoons-0.026
girls-0.025
 forth-0.023
idents-0.023
Token smiled
Token ID13541
Feature activation+5.14e-03

Pos logit contributions
one+0.084
lor+0.072
uan+0.071
 wizard+0.069
alks+0.069
Neg logit contributions
Deal-0.080
 cartoons-0.077
girls-0.074
boys-0.072
 forth-0.069
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
one+0.008
 wizard+0.007
uan+0.007
lor+0.007
 robe+0.007
Neg logit contributions
Deal-0.009
 cartoons-0.009
girls-0.008
idents-0.008
icious-0.008
Token said
Token ID531
Feature activation+2.79e-02

Pos logit contributions
Deal+0.017
 cartoons+0.016
 inviting+0.015
 forth+0.015
 y+0.015
Neg logit contributions
one-0.021
lor-0.018
uan-0.018
 aid-0.017
ooter-0.017
Token,
Token ID11
Feature activation-6.67e-03

Pos logit contributions
one+0.049
uan+0.042
lor+0.041
 aid+0.040
em+0.040
Neg logit contributions
Deal-0.044
 cartoons-0.043
 y-0.039
idents-0.038
 inviting-0.038
Token "
Token ID366
Feature activation-1.67e-02

Pos logit contributions
 cartoons+0.012
Deal+0.011
 inviting+0.011
girls+0.010
idents+0.010
Neg logit contributions
one-0.011
lor-0.009
uan-0.009
ired-0.009
em-0.008
Token watched
Token ID7342
Feature activation-8.79e-03

Pos logit contributions
one+0.011
 wizard+0.009
uan+0.009
lor+0.008
 robe+0.008
Neg logit contributions
 cartoons-0.014
Deal-0.014
girls-0.013
idents-0.013
icious-0.012
Token.
Token ID13
Feature activation-5.74e-03

Pos logit contributions
Deal+0.019
girls+0.016
icious+0.015
idents+0.015
aghetti+0.014
Neg logit contributions
one-0.012
 wizard-0.011
em-0.010
 aid-0.010
alks-0.009
Token Soon
Token ID15894
Feature activation+5.48e-03

Pos logit contributions
 cartoons+0.009
Deal+0.009
girls+0.008
idents+0.008
 inviting+0.008
Neg logit contributions
one-0.011
 wizard-0.009
uan-0.009
lor-0.009
 robe-0.009
Token,
Token ID11
Feature activation+7.73e-04

Pos logit contributions
one+0.009
 wizard+0.007
uan+0.007
lor+0.007
 robe+0.007
Neg logit contributions
 cartoons-0.010
Deal-0.010
girls-0.009
idents-0.009
 inviting-0.009
Token she
Token ID673
Feature activation+7.84e-03

Pos logit contributions
one+0.001
 wizard+0.001
 Dale+0.001
 arrived+0.001
uan+0.001
Neg logit contributions
Deal-0.001
girls-0.001
 cartoons-0.001
icious-0.001
idents-0.001
Token had
Token ID550
Feature activation+2.71e-02

Pos logit contributions
one+0.013
 wizard+0.010
uan+0.010
lor+0.010
ooter+0.010
Neg logit contributions
 cartoons-0.014
Deal-0.014
girls-0.013
idents-0.012
boys-0.012
Token gathered
Token ID9272
Feature activation-2.28e-03

Pos logit contributions
one+0.045
 wizard+0.041
ooter+0.039
anger+0.039
lor+0.038
Neg logit contributions
 cartoons-0.041
 y-0.041
Deal-0.040
girls-0.039
 inviting-0.038
Token a
Token ID257
Feature activation-7.76e-03

Pos logit contributions
Deal+0.004
girls+0.004
 cartoons+0.004
icious+0.004
idents+0.004
Neg logit contributions
one-0.004
 wizard-0.003
uan-0.003
em-0.003
 Dale-0.003
Token whole
Token ID2187
Feature activation-2.34e-02

Pos logit contributions
Deal+0.013
girls+0.012
 cartoons+0.012
idents+0.011
boys+0.011
Neg logit contributions
one-0.013
 wizard-0.012
uan-0.011
 robe-0.011
 arrived-0.011
Token bag
Token ID6131
Feature activation-7.58e-03

Pos logit contributions
Deal+0.040
 cartoons+0.039
girls+0.039
idents+0.036
boys+0.034
Neg logit contributions
one-0.038
 wizard-0.033
uan-0.032
 robe-0.031
lor-0.031
Token full
Token ID1336
Feature activation+2.03e-04

Pos logit contributions
 cartoons+0.015
Deal+0.015
girls+0.014
idents+0.014
 inviting+0.014
Neg logit contributions
one-0.010
 wizard-0.008
uan-0.008
lor-0.007
 robe-0.007
Token he
Token ID339
Feature activation+7.10e-03

Pos logit contributions
Deal+0.011
 cartoons+0.011
girls+0.010
 inviting+0.010
 forth+0.010
Neg logit contributions
one-0.008
lor-0.006
uan-0.006
alks-0.006
unk-0.006
Token loved
Token ID6151
Feature activation-1.90e-02

Pos logit contributions
one+0.013
uan+0.011
 wizard+0.011
lor+0.011
alks+0.010
Neg logit contributions
Deal-0.011
 cartoons-0.011
girls-0.010
idents-0.009
 inviting-0.009
Token to
Token ID284
Feature activation+8.91e-03

Pos logit contributions
Deal+0.041
 cartoons+0.041
girls+0.039
idents+0.038
icious+0.037
Neg logit contributions
one-0.023
 wizard-0.018
uan-0.017
lor-0.016
 robe-0.016
Token play
Token ID711
Feature activation-1.08e-02

Pos logit contributions
one+0.017
lor+0.015
uan+0.015
 wizard+0.015
ired+0.014
Neg logit contributions
 cartoons-0.013
Deal-0.012
girls-0.011
 inviting-0.011
 forth-0.011
Token on
Token ID319
Feature activation+5.89e-03

Pos logit contributions
Deal+0.020
idents+0.020
girls+0.020
icious+0.019
ksh+0.019
Neg logit contributions
one-0.015
 wizard-0.013
 robe-0.013
lor-0.012
anger-0.012
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
one+0.008
 wizard+0.007
 robe+0.007
 ago+0.006
uan+0.006
Neg logit contributions
Deal-0.012
girls-0.011
 cartoons-0.011
idents-0.011
icious-0.010
Token One
Token ID1881
Feature activation+2.08e-03

Pos logit contributions
one+0.020
ster+0.020
lor+0.020
unk+0.020
 wizard+0.020
Neg logit contributions
 cartoons-0.015
Deal-0.014
 inviting-0.012
girls-0.012
ksh-0.012
Token day
Token ID1110
Feature activation+2.12e-02

Pos logit contributions
one+0.004
lor+0.004
uan+0.004
alks+0.004
 wizard+0.004
Neg logit contributions
 cartoons-0.003
Deal-0.003
 forth-0.002
 inviting-0.002
 y-0.002
Token J
Token ID449
Feature activation+4.46e-02

Pos logit contributions
lor+0.050
inger+0.049
 tal+0.047
one+0.045
age+0.045
Neg logit contributions
 together-0.019
 cartoons-0.019
 y-0.018
 both-0.017
 inviting-0.016
Tokenax
Token ID897
Feature activation+3.36e-02

Pos logit contributions
 doorway+0.074
 tal+0.073
 wizard+0.073
 stub+0.070
 wing+0.069
Neg logit contributions
Deal-0.054
aghetti-0.051
 cartoons-0.050
icious-0.046
 y-0.046
Token had
Token ID550
Feature activation+3.78e-02

Pos logit contributions
one+0.057
lor+0.052
alks+0.052
 wizard+0.050
uan+0.048
Neg logit contributions
 cartoons-0.048
boys-0.047
Deal-0.046
girls-0.046
 forth-0.046
Token of
Token ID286
Feature activation-2.35e-03

Pos logit contributions
one+0.021
lor+0.017
uan+0.017
 wizard+0.017
 robe+0.016
Neg logit contributions
 cartoons-0.037
Deal-0.035
girls-0.033
 inviting-0.033
idents-0.031
Token you
Token ID345
Feature activation+1.34e-03

Pos logit contributions
Deal+0.003
 cartoons+0.003
girls+0.003
idents+0.003
icious+0.003
Neg logit contributions
one-0.005
 wizard-0.004
uan-0.004
lor-0.004
em-0.004
Token,"
Token ID553
Feature activation-3.39e-03

Pos logit contributions
one+0.002
 ago+0.001
 wizard+0.001
em+0.001
ired+0.001
Neg logit contributions
Deal-0.003
 cartoons-0.003
girls-0.003
idents-0.003
icious-0.003
Token Mom
Token ID11254
Feature activation-7.83e-03

Pos logit contributions
girls+0.006
Deal+0.006
 cartoons+0.006
icious+0.006
idents+0.006
Neg logit contributions
one-0.005
 wizard-0.004
em-0.004
uan-0.004
 robe-0.004
Token said
Token ID531
Feature activation+2.84e-02

Pos logit contributions
 cartoons+0.012
Deal+0.012
girls+0.011
idents+0.010
 inviting+0.010
Neg logit contributions
one-0.014
lor-0.012
 wizard-0.012
uan-0.012
alks-0.012
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
one+0.048
 wizard+0.040
uan+0.039
lor+0.039
 robe+0.037
Neg logit contributions
 cartoons-0.048
Deal-0.048
girls-0.045
idents-0.043
icious-0.041
Token
Token ID198
Feature activation+4.03e-03

Pos logit contributions
one+0.017
lor+0.015
uan+0.014
 wizard+0.014
ooter+0.014
Neg logit contributions
 cartoons-0.018
Deal-0.017
girls-0.016
 inviting-0.015
idents-0.015
Token
Token ID198
Feature activation+5.77e-03

Pos logit contributions
one+0.004
 wizard+0.003
uan+0.003
lor+0.003
 robe+0.003
Neg logit contributions
Deal-0.009
 cartoons-0.009
girls-0.009
idents-0.008
icious-0.008
Token"
Token ID1
Feature activation-1.64e-02

Pos logit contributions
one+0.007
 wizard+0.005
em+0.005
lor+0.004
 aid+0.004
Neg logit contributions
 cartoons-0.013
girls-0.013
idents-0.012
Deal-0.012
boys-0.012
TokenThank
Token ID10449
Feature activation-2.17e-02

Pos logit contributions
 cartoons+0.023
Deal+0.023
girls+0.022
idents+0.020
icious+0.019
Neg logit contributions
one-0.033
 wizard-0.028
uan-0.028
lor-0.027
 robe-0.027
Token you
Token ID345
Feature activation-1.09e-02

Pos logit contributions
 cartoons+0.032
Deal+0.031
girls+0.030
idents+0.029
icious+0.027
Neg logit contributions
one-0.041
 wizard-0.035
uan-0.034
lor-0.034
em-0.033
Token.
Token ID13
Feature activation-5.51e-03

Pos logit contributions
 cartoons+0.030
Deal+0.030
girls+0.028
idents+0.027
boys+0.026
Neg logit contributions
one-0.030
uan-0.025
 wizard-0.025
lor-0.024
 robe-0.023
Token But
Token ID887
Feature activation+3.38e-03

Pos logit contributions
Deal+0.011
 cartoons+0.011
girls+0.010
idents+0.010
icious+0.009
Neg logit contributions
one-0.008
 wizard-0.007
uan-0.006
lor-0.006
 robe-0.006
Token on
Token ID319
Feature activation+9.98e-03

Pos logit contributions
one+0.005
 wizard+0.004
 ago+0.004
ired+0.004
 arrived+0.004
Neg logit contributions
girls-0.006
Deal-0.006
 cartoons-0.006
icious-0.006
ksh-0.006
Token their
Token ID511
Feature activation-6.71e-03

Pos logit contributions
one+0.012
 wizard+0.010
 ago+0.009
em+0.009
 tool+0.009
Neg logit contributions
Deal-0.022
girls-0.022
ksh-0.021
icious-0.020
 cartoons-0.019
Token way
Token ID835
Feature activation+8.29e-03

Pos logit contributions
Deal+0.014
girls+0.013
 cartoons+0.013
icious+0.012
idents+0.012
Neg logit contributions
one-0.009
 aid-0.007
 begg-0.007
 wizard-0.007
 robe-0.007
Token home
Token ID1363
Feature activation+1.59e-02

Pos logit contributions
one+0.015
lor+0.014
uan+0.013
alks+0.013
 wizard+0.013
Neg logit contributions
 cartoons-0.012
 forth-0.012
Deal-0.011
idents-0.011
 together-0.011
Token,
Token ID11
Feature activation+2.46e-03

Pos logit contributions
one+0.025
uan+0.021
 wizard+0.021
lor+0.020
 robe+0.019
Neg logit contributions
Deal-0.028
 cartoons-0.028
idents-0.026
girls-0.026
 forth-0.025
Token they
Token ID484
Feature activation-7.35e-03

Pos logit contributions
one+0.003
 wizard+0.003
 ago+0.003
 arrived+0.003
em+0.003
Neg logit contributions
girls-0.005
Deal-0.005
 cartoons-0.005
ksh-0.005
icious-0.004
Token got
Token ID1392
Feature activation+1.61e-02

Pos logit contributions
 cartoons+0.016
Deal+0.016
girls+0.015
icious+0.015
idents+0.014
Neg logit contributions
one-0.009
 arrived-0.008
 wizard-0.007
 stub-0.007
 stumbled-0.007
Token into
Token ID656
Feature activation-5.27e-03

Pos logit contributions
one+0.026
 wizard+0.021
uan+0.020
 begg+0.020
ired+0.020
Neg logit contributions
Deal-0.030
 cartoons-0.028
girls-0.027
icious-0.026
idents-0.025
Token a
Token ID257
Feature activation-4.54e-03

Pos logit contributions
Deal+0.012
girls+0.011
icious+0.011
 cartoons+0.010
ksh+0.010
Neg logit contributions
one-0.006
 wizard-0.005
 aid-0.005
 robe-0.005
 ago-0.005
Token and
Token ID290
Feature activation+8.09e-03

Pos logit contributions
 cartoons+0.024
Deal+0.024
girls+0.023
idents+0.022
icious+0.021
Neg logit contributions
one-0.024
 wizard-0.020
uan-0.020
lor-0.020
 robe-0.019
Token was
Token ID373
Feature activation+3.18e-04

Pos logit contributions
one+0.013
 wizard+0.011
uan+0.010
 robe+0.010
 ago+0.010
Neg logit contributions
Deal-0.015
 cartoons-0.014
girls-0.014
icious-0.013
idents-0.013
Token now
Token ID783
Feature activation+2.56e-02

Pos logit contributions
one+0.001
 wizard+0.000
uan+0.000
lor+0.000
 robe+0.000
Neg logit contributions
Deal-0.001
 cartoons-0.001
girls-0.001
idents-0.001
icious-0.001
Token running
Token ID2491
Feature activation+2.88e-03

Pos logit contributions
one+0.041
 wizard+0.035
uan+0.033
 ago+0.032
 aid+0.032
Neg logit contributions
Deal-0.046
 cartoons-0.044
girls-0.043
idents-0.040
icious-0.040
Token towards
Token ID3371
Feature activation-1.62e-02

Pos logit contributions
one+0.005
 wizard+0.004
 ago+0.004
uan+0.004
ired+0.004
Neg logit contributions
Deal-0.005
 cartoons-0.005
icious-0.005
girls-0.005
idents-0.004
Token them
Token ID606
Feature activation+8.79e-03

Pos logit contributions
Deal+0.024
 cartoons+0.022
girls+0.021
idents+0.020
icious+0.020
Neg logit contributions
one-0.032
 wizard-0.027
uan-0.027
em-0.026
lor-0.026
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
one+0.012
ired+0.009
 wizard+0.009
 aid+0.009
 ago+0.009
Neg logit contributions
Deal-0.019
 cartoons-0.018
girls-0.017
icious-0.016
idents-0.016
Token
Token ID220
Feature activation-4.74e-03

Pos logit contributions
Deal+0.028
 cartoons+0.028
girls+0.027
idents+0.025
icious+0.025
Neg logit contributions
one-0.021
 wizard-0.017
uan-0.017
lor-0.016
em-0.016
Token
Token ID198
Feature activation-9.17e-03

Pos logit contributions
Deal+0.009
 cartoons+0.009
girls+0.008
idents+0.008
icious+0.008
Neg logit contributions
one-0.007
 wizard-0.006
 robe-0.006
uan-0.006
 begg-0.006
Token
Token ID198
Feature activation-6.00e-03

Pos logit contributions
 cartoons+0.019
Deal+0.019
girls+0.018
 inviting+0.018
idents+0.017
Neg logit contributions
one-0.012
 wizard-0.009
uan-0.009
lor-0.009
 robe-0.008
TokenL
Token ID43
Feature activation-5.37e-03

Pos logit contributions
 cartoons+0.011
Deal+0.011
girls+0.011
idents+0.010
boys+0.009
Neg logit contributions
one-0.009
 wizard-0.007
lor-0.007
em-0.007
uan-0.007
Token climb
Token ID12080
Feature activation+6.82e-03

Pos logit contributions
 cartoons+0.012
Deal+0.012
girls+0.011
idents+0.011
 forth+0.010
Neg logit contributions
one-0.013
lor-0.011
uan-0.011
 wizard-0.011
em-0.010
Token on
Token ID319
Feature activation+3.28e-03

Pos logit contributions
one+0.013
lor+0.012
uan+0.011
 wizard+0.011
ired+0.011
Neg logit contributions
 cartoons-0.010
Deal-0.009
girls-0.009
 forth-0.008
idents-0.008
Token top
Token ID1353
Feature activation+9.53e-03

Pos logit contributions
one+0.005
 wizard+0.004
uan+0.004
lor+0.004
 robe+0.004
Neg logit contributions
Deal-0.006
 cartoons-0.006
girls-0.006
idents-0.005
icious-0.005
Token of
Token ID286
Feature activation-1.17e-02

Pos logit contributions
one+0.013
lor+0.013
 robe+0.012
 wizard+0.012
uan+0.012
Neg logit contributions
 cartoons-0.017
girls-0.015
 forth-0.015
glers-0.015
Deal-0.015
Token it
Token ID340
Feature activation-1.59e-02

Pos logit contributions
 cartoons+0.019
Deal+0.019
girls+0.018
idents+0.017
 inviting+0.017
Neg logit contributions
one-0.020
lor-0.017
uan-0.017
 wizard-0.017
ooter-0.016
Token.
Token ID13
Feature activation-1.84e-03

Pos logit contributions
Deal+0.027
 cartoons+0.027
girls+0.026
idents+0.024
icious+0.024
Neg logit contributions
one-0.026
 wizard-0.022
uan-0.022
lor-0.021
 robe-0.021
Token
Token ID198
Feature activation+3.70e-03

Pos logit contributions
 cartoons+0.003
idents+0.003
girls+0.003
Deal+0.003
 together+0.003
Neg logit contributions
one-0.003
unk-0.003
lor-0.003
ila-0.003
em-0.003
Token
Token ID198
Feature activation+4.33e-03

Pos logit contributions
one+0.006
 wizard+0.005
ooter+0.005
 begg+0.005
alks+0.005
Neg logit contributions
 cartoons-0.006
Deal-0.006
girls-0.006
 inviting-0.006
 together-0.005
TokenBut
Token ID1537
Feature activation+7.90e-03

Pos logit contributions
one+0.007
 wizard+0.006
uan+0.006
lor+0.006
unk+0.006
Neg logit contributions
Deal-0.007
 cartoons-0.007
girls-0.007
 inviting-0.006
idents-0.006
Token when
Token ID618
Feature activation-9.84e-03

Pos logit contributions
one+0.015
 wizard+0.012
uan+0.012
lor+0.012
 robe+0.012
Neg logit contributions
Deal-0.012
 cartoons-0.012
girls-0.011
idents-0.011
icious-0.010
Token he
Token ID339
Feature activation-2.79e-03

Pos logit contributions
Deal+0.024
 cartoons+0.023
girls+0.022
icious+0.022
idents+0.021
Neg logit contributions
one-0.010
 wizard-0.008
uan-0.007
lor-0.006
 robe-0.006
Token decided
Token ID3066
Feature activation+9.37e-03

Pos logit contributions
Deal+0.007
 cartoons+0.007
girls+0.007
icious+0.006
idents+0.006
Neg logit contributions
one-0.007
uan-0.006
 wizard-0.006
 arrived-0.005
em-0.005
Token to
Token ID284
Feature activation-8.72e-04

Pos logit contributions
one+0.014
unk+0.012
uan+0.012
alks+0.012
 wizard+0.012
Neg logit contributions
 cartoons-0.017
Deal-0.016
idents-0.016
 inviting-0.016
girls-0.015
Token take
Token ID1011
Feature activation-6.25e-03

Pos logit contributions
Deal+0.001
 cartoons+0.001
girls+0.001
idents+0.001
icious+0.001
Neg logit contributions
one-0.002
 wizard-0.001
uan-0.001
lor-0.001
 robe-0.001
Token a
Token ID257
Feature activation-4.57e-03

Pos logit contributions
 cartoons+0.011
Deal+0.011
girls+0.010
idents+0.010
icious+0.009
Neg logit contributions
one-0.010
 wizard-0.008
uan-0.008
lor-0.008
em-0.008
Token walk
Token ID2513
Feature activation-6.61e-03

Pos logit contributions
 cartoons+0.008
Deal+0.008
girls+0.007
idents+0.007
icious+0.007
Neg logit contributions
one-0.008
 wizard-0.006
uan-0.006
lor-0.006
em-0.006
Token around
Token ID1088
Feature activation-6.44e-03

Pos logit contributions
Deal+0.011
 cartoons+0.011
girls+0.011
icious+0.010
idents+0.010
Neg logit contributions
one-0.011
 wizard-0.009
uan-0.009
lor-0.009
 robe-0.009
Token the
Token ID262
Feature activation-3.10e-03

Pos logit contributions
Deal+0.011
 cartoons+0.011
girls+0.011
idents+0.010
icious+0.010
Neg logit contributions
one-0.011
 wizard-0.009
uan-0.009
lor-0.008
 robe-0.008
Token park
Token ID3952
Feature activation+1.76e-02

Pos logit contributions
Deal+0.006
 cartoons+0.006
girls+0.006
idents+0.006
icious+0.005
Neg logit contributions
one-0.004
 wizard-0.004
uan-0.003
lor-0.003
 robe-0.003
Token.
Token ID13
Feature activation+1.46e-02

Pos logit contributions
one+0.030
 wizard+0.026
uan+0.026
lor+0.025
 robe+0.024
Neg logit contributions
Deal-0.029
 cartoons-0.029
girls-0.027
idents-0.025
boys-0.025
Token Joey
Token ID26154
Feature activation+6.82e-03

Pos logit contributions
one+0.030
 crow+0.026
lor+0.025
 wizard+0.025
unk+0.025
Neg logit contributions
 cartoons-0.020
idents-0.019
 together-0.018
 inviting-0.018
ksh-0.017
Token looked
Token ID3114
Feature activation-1.55e-02

Pos logit contributions
one+0.012
lor+0.010
alks+0.010
 wizard+0.010
uan+0.010
Neg logit contributions
 cartoons-0.011
Deal-0.011
girls-0.010
boys-0.010
 forth-0.010
Token the
Token ID262
Feature activation-6.83e-03

Pos logit contributions
Deal+0.028
girls+0.025
 cartoons+0.024
icious+0.024
idents+0.024
Neg logit contributions
one-0.022
 wizard-0.018
uan-0.017
 Dale-0.017
 robe-0.017
Token rain
Token ID6290
Feature activation-1.27e-02

Pos logit contributions
Deal+0.009
 cartoons+0.009
girls+0.009
idents+0.008
icious+0.008
Neg logit contributions
one-0.014
 wizard-0.012
uan-0.012
lor-0.012
 robe-0.011
Tokendrops
Token ID49253
Feature activation-7.02e-03

Pos logit contributions
Deal+0.025
 cartoons+0.024
girls+0.023
icious+0.023
idents+0.022
Neg logit contributions
one-0.018
ooter-0.014
 wizard-0.014
 arrived-0.013
anger-0.013
Token with
Token ID351
Feature activation-1.34e-02

Pos logit contributions
Deal+0.013
 cartoons+0.013
girls+0.013
idents+0.012
icious+0.012
Neg logit contributions
one-0.011
 wizard-0.008
ooter-0.008
 arrived-0.008
uan-0.008
Token his
Token ID465
Feature activation-7.48e-04

Pos logit contributions
Deal+0.028
 cartoons+0.027
girls+0.026
idents+0.025
icious+0.025
Neg logit contributions
one-0.018
 wizard-0.014
uan-0.014
 robe-0.013
ired-0.013
Token tongue
Token ID11880
Feature activation-6.47e-03

Pos logit contributions
Deal+0.001
 cartoons+0.001
girls+0.001
icious+0.001
idents+0.001
Neg logit contributions
one-0.001
 wizard-0.001
uan-0.001
 robe-0.001
ooter-0.001
Token and
Token ID290
Feature activation+7.44e-03

Pos logit contributions
Deal+0.012
 cartoons+0.012
girls+0.012
idents+0.011
icious+0.011
Neg logit contributions
one-0.009
 wizard-0.008
uan-0.007
lor-0.007
 robe-0.007
Token jumped
Token ID11687
Feature activation-5.97e-03

Pos logit contributions
one+0.011
 wizard+0.009
uan+0.009
 robe+0.009
orse+0.009
Neg logit contributions
Deal-0.014
 cartoons-0.013
girls-0.013
icious-0.012
idents-0.012
Token in
Token ID287
Feature activation-1.79e-02

Pos logit contributions
Deal+0.012
girls+0.011
 cartoons+0.011
icious+0.010
idents+0.010
Neg logit contributions
one-0.009
 wizard-0.007
 robe-0.007
anger-0.007
unk-0.007
Token all
Token ID477
Feature activation+2.04e-03

Pos logit contributions
Deal+0.036
girls+0.034
 cartoons+0.033
idents+0.032
icious+0.032
Neg logit contributions
one-0.025
 wizard-0.021
 robe-0.020
 aid-0.020
 ago-0.020
Token the
Token ID262
Feature activation-7.31e-03

Pos logit contributions
one+0.004
lor+0.003
 wizard+0.003
uan+0.003
 robe+0.003
Neg logit contributions
 cartoons-0.003
Deal-0.003
girls-0.003
 forth-0.003
 inviting-0.003
TokenOne
Token ID3198
Feature activation-5.37e-03

Pos logit contributions
idents+0.005
Deal+0.005
girls+0.005
 cartoons+0.005
 forth+0.005
Neg logit contributions
one-0.005
 wizard-0.004
uan-0.003
 aid-0.003
lor-0.003
Token day
Token ID1110
Feature activation+7.57e-03

Pos logit contributions
Deal+0.009
 cartoons+0.009
girls+0.008
idents+0.008
icious+0.008
Neg logit contributions
one-0.009
 wizard-0.008
uan-0.008
lor-0.007
 robe-0.007
Token,
Token ID11
Feature activation+1.61e-03

Pos logit contributions
one+0.013
lor+0.012
uan+0.011
ooter+0.011
enna+0.011
Neg logit contributions
 cartoons-0.013
Deal-0.012
girls-0.011
 inviting-0.011
 y-0.011
Token the
Token ID262
Feature activation+2.15e-02

Pos logit contributions
one+0.002
 wizard+0.002
uan+0.002
 arrived+0.001
 robe+0.001
Neg logit contributions
Deal-0.003
girls-0.003
 cartoons-0.003
icious-0.003
idents-0.003
Token farmer
Token ID18739
Feature activation+1.36e-02

Pos logit contributions
one+0.026
 wizard+0.020
uan+0.019
lor+0.019
 robe+0.018
Neg logit contributions
Deal-0.047
 cartoons-0.047
girls-0.045
idents-0.043
icious-0.042
Token was
Token ID373
Feature activation-6.79e-04

Pos logit contributions
one+0.021
lor+0.018
alks+0.018
uan+0.017
ooter+0.017
Neg logit contributions
Deal-0.023
 cartoons-0.023
girls-0.022
boys-0.022
 forth-0.021
Token too
Token ID1165
Feature activation-1.99e-03

Pos logit contributions
 cartoons+0.001
Deal+0.001
girls+0.001
 inviting+0.001
boys+0.001
Neg logit contributions
one-0.001
uan-0.001
lor-0.001
enna-0.001
 wizard-0.001
Token busy
Token ID8179
Feature activation+2.44e-03

Pos logit contributions
 cartoons+0.002
Deal+0.002
girls+0.002
 inviting+0.002
idents+0.002
Neg logit contributions
one-0.004
lor-0.004
uan-0.004
 wizard-0.004
 robe-0.004
Token to
Token ID284
Feature activation-5.14e-03

Pos logit contributions
one+0.004
uan+0.004
lor+0.004
 wizard+0.004
enna+0.004
Neg logit contributions
 cartoons-0.004
Deal-0.003
 inviting-0.003
girls-0.003
 forth-0.003
Token take
Token ID1011
Feature activation-8.74e-03

Pos logit contributions
Deal+0.010
 cartoons+0.009
girls+0.009
idents+0.009
ksh+0.008
Neg logit contributions
one-0.008
 wizard-0.007
 robe-0.006
 aid-0.006
uan-0.006
Token the
Token ID262
Feature activation+4.01e-03

Pos logit contributions
 cartoons+0.015
Deal+0.015
girls+0.014
idents+0.013
boys+0.013
Neg logit contributions
one-0.015
 wizard-0.012
uan-0.012
lor-0.012
 robe-0.011
Token sees
Token ID7224
Feature activation-3.64e-03

Pos logit contributions
one+0.026
 wizard+0.021
uan+0.021
lor+0.021
 robe+0.020
Neg logit contributions
Deal-0.030
 cartoons-0.030
girls-0.028
idents-0.027
icious-0.026
Token her
Token ID607
Feature activation+1.44e-02

Pos logit contributions
 cartoons+0.006
Deal+0.005
girls+0.005
 inviting+0.005
idents+0.005
Neg logit contributions
one-0.007
lor-0.006
uan-0.006
 wizard-0.006
ooter-0.005
Token fall
Token ID2121
Feature activation+1.51e-03

Pos logit contributions
one+0.024
 wizard+0.020
uan+0.019
lor+0.019
 robe+0.018
Neg logit contributions
Deal-0.025
 cartoons-0.025
girls-0.024
idents-0.023
icious-0.022
Token and
Token ID290
Feature activation+6.22e-03

Pos logit contributions
one+0.003
 wizard+0.002
uan+0.002
lor+0.002
 robe+0.002
Neg logit contributions
 cartoons-0.003
Deal-0.003
girls-0.002
idents-0.002
icious-0.002
Token runs
Token ID4539
Feature activation+5.63e-03

Pos logit contributions
one+0.011
lor+0.009
uan+0.009
em+0.009
 wizard+0.009
Neg logit contributions
 cartoons-0.010
Deal-0.010
girls-0.009
idents-0.009
 forth-0.009
Token after
Token ID706
Feature activation-1.49e-02

Pos logit contributions
one+0.008
 wizard+0.006
uan+0.006
lor+0.006
 robe+0.005
Neg logit contributions
Deal-0.011
 cartoons-0.011
girls-0.011
idents-0.010
icious-0.010
Token her
Token ID607
Feature activation+3.79e-03

Pos logit contributions
 cartoons+0.023
Deal+0.023
girls+0.022
idents+0.020
 inviting+0.020
Neg logit contributions
one-0.027
uan-0.023
 wizard-0.023
lor-0.023
em-0.022
Token.
Token ID13
Feature activation+6.25e-03

Pos logit contributions
one+0.007
uan+0.006
lor+0.006
 wizard+0.006
em+0.005
Neg logit contributions
 cartoons-0.006
Deal-0.006
girls-0.006
idents-0.006
 forth-0.005
Token He
Token ID679
Feature activation-6.11e-03

Pos logit contributions
one+0.011
enna+0.010
uan+0.009
 wizard+0.009
lor+0.009
Neg logit contributions
 cartoons-0.010
Deal-0.010
girls-0.009
 inviting-0.009
idents-0.009
Token is
Token ID318
Feature activation-4.74e-03

Pos logit contributions
Deal+0.011
 cartoons+0.011
girls+0.011
idents+0.010
icious+0.010
Neg logit contributions
one-0.009
 wizard-0.008
uan-0.007
lor-0.007
 robe-0.007
Token scared
Token ID12008
Feature activation+1.08e-02

Pos logit contributions
Deal+0.007
 cartoons+0.007
girls+0.007
idents+0.006
icious+0.006
Neg logit contributions
one-0.009
 wizard-0.008
uan-0.007
lor-0.007
 robe-0.007
Tokenmy
Token ID1820
Feature activation+2.95e-03

Pos logit contributions
one+0.005
 wizard+0.004
uan+0.004
lor+0.004
alks+0.004
Neg logit contributions
 cartoons-0.004
Deal-0.004
girls-0.004
idents-0.004
boys-0.004
Token and
Token ID290
Feature activation+7.68e-03

Pos logit contributions
one+0.005
 wizard+0.004
uan+0.004
lor+0.004
 robe+0.004
Neg logit contributions
 cartoons-0.005
Deal-0.005
girls-0.005
idents-0.005
icious-0.004
Token took
Token ID1718
Feature activation-2.75e-03

Pos logit contributions
one+0.015
alks+0.013
lor+0.013
uan+0.012
ane+0.012
Neg logit contributions
 cartoons-0.011
Deal-0.011
girls-0.010
 inviting-0.010
 forth-0.010
Token the
Token ID262
Feature activation-8.58e-03

Pos logit contributions
Deal+0.004
 cartoons+0.004
girls+0.004
icious+0.004
idents+0.004
Neg logit contributions
one-0.005
 wizard-0.004
uan-0.004
lor-0.004
 robe-0.004
Token car
Token ID1097
Feature activation-1.67e-02

Pos logit contributions
 cartoons+0.015
Deal+0.014
girls+0.013
idents+0.013
 y+0.012
Neg logit contributions
one-0.014
uan-0.013
lor-0.013
enna-0.012
alks-0.012
Token from
Token ID422
Feature activation-4.23e-02

Pos logit contributions
Deal+0.029
 cartoons+0.028
girls+0.027
idents+0.026
icious+0.025
Neg logit contributions
one-0.028
 wizard-0.023
uan-0.023
lor-0.022
em-0.022
Token him
Token ID683
Feature activation-9.37e-03

Pos logit contributions
Deal+0.071
 cartoons+0.064
girls+0.064
icious+0.063
idents+0.063
Neg logit contributions
one-0.072
 wizard-0.066
 robe-0.060
uan-0.060
 ago-0.059
Token.
Token ID13
Feature activation-8.86e-05

Pos logit contributions
Deal+0.018
 cartoons+0.018
girls+0.017
icious+0.016
idents+0.016
Neg logit contributions
one-0.014
 wizard-0.011
uan-0.011
 ago-0.011
lor-0.011
Token She
Token ID1375
Feature activation-8.97e-03

Pos logit contributions
Deal+0.000
 cartoons+0.000
girls+0.000
idents+0.000
 inviting+0.000
Neg logit contributions
one-0.000
lor-0.000
 wizard-0.000
uan-0.000
em-0.000
Token sc
Token ID629
Feature activation-2.67e-03

Pos logit contributions
 cartoons+0.018
Deal+0.018
girls+0.017
idents+0.016
icious+0.016
Neg logit contributions
one-0.012
 wizard-0.010
uan-0.010
 robe-0.010
lor-0.009
Tokenolded
Token ID48959
Feature activation-1.76e-02

Pos logit contributions
Deal+0.005
girls+0.004
idents+0.004
 cartoons+0.004
boys+0.004
Neg logit contributions
one-0.004
 wizard-0.004
lor-0.004
 robe-0.004
uan-0.004
Token together
Token ID1978
Feature activation-2.76e-02

Pos logit contributions
ksh+0.052
glers+0.047
idents+0.046
icious+0.044
 cartoons+0.043
Neg logit contributions
 wizard-0.043
one-0.041
unk-0.040
anging-0.039
ously-0.039
Token every
Token ID790
Feature activation-3.09e-02

Pos logit contributions
 cartoons+0.048
idents+0.048
girls+0.047
Deal+0.047
icious+0.047
Neg logit contributions
one-0.043
 wizard-0.037
 eight-0.033
ired-0.033
 aid-0.032
Token day
Token ID1110
Feature activation-3.61e-03

Pos logit contributions
Deal+0.061
girls+0.060
 cartoons+0.059
idents+0.057
icious+0.055
Neg logit contributions
one-0.045
 wizard-0.036
 aid-0.033
ired-0.033
 robe-0.032
Token and
Token ID290
Feature activation-6.33e-03

Pos logit contributions
Deal+0.007
 cartoons+0.007
girls+0.007
idents+0.007
icious+0.006
Neg logit contributions
one-0.005
 wizard-0.004
 ago-0.004
uan-0.004
ired-0.004
Token always
Token ID1464
Feature activation-1.32e-02

Pos logit contributions
 cartoons+0.013
icious+0.013
Deal+0.013
idents+0.012
ksh+0.012
Neg logit contributions
one-0.007
 arrived-0.006
 wizard-0.006
 known-0.005
orse-0.005
Token helped
Token ID4193
Feature activation-4.22e-02

Pos logit contributions
Deal+0.025
 cartoons+0.024
girls+0.023
idents+0.022
 forth+0.021
Neg logit contributions
one-0.020
 wizard-0.016
uan-0.016
lor-0.016
 robe-0.015
Token each
Token ID1123
Feature activation-3.31e-02

Pos logit contributions
Deal+0.060
 cartoons+0.057
icious+0.056
idents+0.054
girls+0.054
Neg logit contributions
one-0.082
 aid-0.067
em-0.066
 wizard-0.066
uan-0.065
Token other
Token ID584
Feature activation-2.06e-02

Pos logit contributions
Deal+0.075
girls+0.073
idents+0.073
 cartoons+0.071
ksh+0.069
Neg logit contributions
one-0.040
 wizard-0.029
ired-0.028
 aid-0.026
uan-0.024
Token when
Token ID618
Feature activation-1.80e-02

Pos logit contributions
Deal+0.044
icious+0.041
girls+0.040
 cartoons+0.038
idents+0.038
Neg logit contributions
one-0.027
 wizard-0.022
 aid-0.022
ired-0.020
ooter-0.018
Token they
Token ID484
Feature activation-1.76e-02

Pos logit contributions
Deal+0.030
 cartoons+0.028
girls+0.027
icious+0.027
idents+0.026
Neg logit contributions
one-0.032
 wizard-0.027
 ago-0.026
uan-0.025
orse-0.025
Token needed
Token ID2622
Feature activation-1.05e-02

Pos logit contributions
 cartoons+0.035
Deal+0.034
girls+0.033
idents+0.032
icious+0.032
Neg logit contributions
one-0.024
 wizard-0.020
 arrived-0.019
uan-0.019
 robe-0.019
Token big
Token ID1263
Feature activation-2.94e-02

Pos logit contributions
one+0.000
uan+0.000
lor+0.000
 wizard+0.000
em+0.000
Neg logit contributions
 cartoons-0.000
Deal-0.000
girls-0.000
idents-0.000
 inviting-0.000
Token missile
Token ID10105
Feature activation-2.59e-02

Pos logit contributions
Deal+0.053
 cartoons+0.052
girls+0.050
idents+0.047
icious+0.047
Neg logit contributions
one-0.046
 wizard-0.039
uan-0.037
 robe-0.036
lor-0.036
Token that
Token ID326
Feature activation-7.87e-03

Pos logit contributions
 cartoons+0.043
Deal+0.042
girls+0.040
idents+0.037
boys+0.037
Neg logit contributions
one-0.045
uan-0.038
lor-0.037
 wizard-0.037
em-0.036
Token can
Token ID460
Feature activation-1.25e-02

Pos logit contributions
Deal+0.014
 cartoons+0.013
icious+0.013
girls+0.012
idents+0.012
Neg logit contributions
one-0.013
 wizard-0.011
uan-0.011
ooter-0.010
 ago-0.010
Token shoot
Token ID2686
Feature activation+1.82e-03

Pos logit contributions
Deal+0.023
 cartoons+0.022
girls+0.021
idents+0.020
icious+0.020
Neg logit contributions
one-0.020
 wizard-0.016
uan-0.016
lor-0.015
 robe-0.015
Token from
Token ID422
Feature activation-4.36e-02

Pos logit contributions
one+0.003
 wizard+0.002
uan+0.002
ired+0.002
 ago+0.002
Neg logit contributions
Deal-0.004
icious-0.003
 cartoons-0.003
idents-0.003
girls-0.003
Token a
Token ID257
Feature activation-5.38e-03

Pos logit contributions
Deal+0.089
icious+0.084
 cartoons+0.079
idents+0.079
girls+0.078
Neg logit contributions
one-0.059
 wizard-0.049
 Dale-0.045
 ago-0.045
uan-0.045
Token launcher
Token ID24008
Feature activation-9.46e-03

Pos logit contributions
Deal+0.011
 cartoons+0.010
idents+0.010
girls+0.010
icious+0.010
Neg logit contributions
one-0.008
 wizard-0.007
 robe-0.006
 aid-0.006
uan-0.006
Token.
Token ID13
Feature activation-4.25e-03

Pos logit contributions
Deal+0.016
 cartoons+0.016
girls+0.015
idents+0.015
icious+0.014
Neg logit contributions
one-0.015
 wizard-0.013
uan-0.013
lor-0.012
 robe-0.012
Token
Token ID198
Feature activation+1.25e-02

Pos logit contributions
Deal+0.008
 cartoons+0.008
girls+0.007
idents+0.007
icious+0.007
Neg logit contributions
one-0.007
 wizard-0.005
uan-0.005
lor-0.005
 robe-0.005
Token
Token ID198
Feature activation+1.16e-02

Pos logit contributions
one+0.016
 wizard+0.013
uan+0.012
lor+0.012
 robe+0.012
Neg logit contributions
Deal-0.026
 cartoons-0.026
girls-0.025
 inviting-0.023
idents-0.023
Token Tim
Token ID5045
Feature activation+2.27e-03

Pos logit contributions
girls+0.029
Deal+0.027
 cartoons+0.025
icious+0.025
boys+0.024
Neg logit contributions
one-0.025
 Dale-0.020
 arrived-0.020
 wizard-0.020
 tool-0.020
Tokenmy
Token ID1820
Feature activation+7.05e-03

Pos logit contributions
one+0.005
alks+0.005
lor+0.005
 wizard+0.005
anger+0.005
Neg logit contributions
 cartoons-0.002
Deal-0.002
 forth-0.002
girls-0.002
boys-0.002
Token poured
Token ID19036
Feature activation+1.86e-03

Pos logit contributions
one+0.013
alks+0.012
anger+0.011
lor+0.011
uan+0.011
Neg logit contributions
 cartoons-0.011
 forth-0.010
boys-0.009
Deal-0.009
 y-0.009
Token himself
Token ID2241
Feature activation-2.17e-03

Pos logit contributions
one+0.003
 wizard+0.002
uan+0.002
em+0.002
 robe+0.002
Neg logit contributions
Deal-0.004
 cartoons-0.004
girls-0.004
icious-0.003
idents-0.003
Token a
Token ID257
Feature activation-1.96e-02

Pos logit contributions
 cartoons+0.003
Deal+0.003
girls+0.003
idents+0.003
 forth+0.003
Neg logit contributions
one-0.004
 wizard-0.004
uan-0.004
lor-0.004
 ago-0.003
Token bowl
Token ID9396
Feature activation-4.78e-02

Pos logit contributions
Deal+0.033
 cartoons+0.033
girls+0.031
idents+0.029
icious+0.029
Neg logit contributions
one-0.033
 wizard-0.028
uan-0.027
lor-0.027
 robe-0.026
Token of
Token ID286
Feature activation-2.30e-02

Pos logit contributions
Deal+0.089
 cartoons+0.088
girls+0.084
idents+0.080
icious+0.078
Neg logit contributions
one-0.072
 wizard-0.059
uan-0.058
lor-0.057
 robe-0.055
Token cereal
Token ID33158
Feature activation-4.78e-02

Pos logit contributions
Deal+0.038
girls+0.036
boys+0.033
idents+0.032
icious+0.032
Neg logit contributions
one-0.039
 wizard-0.035
 oy-0.034
 robe-0.034
uan-0.032
Token and
Token ID290
Feature activation+3.36e-03

Pos logit contributions
Deal+0.087
 cartoons+0.085
girls+0.083
icious+0.078
idents+0.076
Neg logit contributions
one-0.075
 wizard-0.063
uan-0.059
lor-0.059
em-0.058
Token sat
Token ID3332
Feature activation-7.95e-03

Pos logit contributions
one+0.005
 wizard+0.004
uan+0.004
lor+0.004
 robe+0.004
Neg logit contributions
Deal-0.006
 cartoons-0.006
girls-0.006
idents-0.005
icious-0.005
Token down
Token ID866
Feature activation+1.53e-02

Pos logit contributions
girls+0.014
Deal+0.014
 cartoons+0.014
icious+0.013
idents+0.012
Neg logit contributions
one-0.012
 wizard-0.011
 robe-0.010
lor-0.010
uan-0.010
Token They
Token ID1119
Feature activation-7.14e-03

Pos logit contributions
Deal+0.002
 cartoons+0.002
girls+0.002
idents+0.002
icious+0.002
Neg logit contributions
one-0.002
 wizard-0.001
uan-0.001
lor-0.001
 robe-0.001
Token laughed
Token ID13818
Feature activation-1.34e-02

Pos logit contributions
 cartoons+0.015
Deal+0.015
girls+0.014
idents+0.014
icious+0.014
Neg logit contributions
one-0.009
 wizard-0.007
uan-0.007
 arrived-0.007
 robe-0.007
Token and
Token ID290
Feature activation-1.28e-02

Pos logit contributions
Deal+0.034
girls+0.033
icious+0.031
idents+0.031
 cartoons+0.030
Neg logit contributions
one-0.010
 wizard-0.007
ired-0.007
 robe-0.006
ously-0.006
Token cl
Token ID537
Feature activation+6.21e-04

Pos logit contributions
Deal+0.024
 cartoons+0.024
girls+0.022
icious+0.022
idents+0.022
Neg logit contributions
one-0.018
 wizard-0.015
uan-0.015
 robe-0.015
orse-0.015
Tokenapped
Token ID6320
Feature activation-9.91e-03

Pos logit contributions
one+0.001
 wizard+0.001
uan+0.001
lor+0.001
 robe+0.001
Neg logit contributions
Deal-0.001
 cartoons-0.001
girls-0.001
idents-0.001
icious-0.001
Token their
Token ID511
Feature activation-4.09e-02

Pos logit contributions
Deal+0.022
girls+0.020
icious+0.020
idents+0.020
 cartoons+0.019
Neg logit contributions
one-0.011
 wizard-0.009
 mate-0.009
 aid-0.009
ously-0.009
Token hands
Token ID2832
Feature activation-2.02e-02

Pos logit contributions
Deal+0.083
 cartoons+0.082
girls+0.078
idents+0.075
icious+0.074
Neg logit contributions
one-0.056
 wizard-0.044
uan-0.043
lor-0.041
 robe-0.041
Token when
Token ID618
Feature activation-1.26e-02

Pos logit contributions
Deal+0.046
 cartoons+0.042
girls+0.042
idents+0.041
icious+0.040
Neg logit contributions
one-0.024
ired-0.018
 wizard-0.017
 ago-0.017
em-0.016
Token they
Token ID484
Feature activation-1.93e-03

Pos logit contributions
Deal+0.021
 cartoons+0.019
girls+0.019
icious+0.018
idents+0.018
Neg logit contributions
one-0.022
 wizard-0.019
uan-0.018
 ago-0.018
 robe-0.018
Token finished
Token ID5201
Feature activation+1.03e-03

Pos logit contributions
 cartoons+0.004
Deal+0.004
girls+0.004
idents+0.004
icious+0.004
Neg logit contributions
one-0.002
uan-0.002
 wizard-0.002
 robe-0.002
 arrived-0.002
Token their
Token ID511
Feature activation-2.14e-02

Pos logit contributions
one+0.001
alks+0.001
 ago+0.001
em+0.001
 wizard+0.001
Neg logit contributions
Deal-0.002
girls-0.002
icious-0.002
 cartoons-0.002
idents-0.002