TOP ACTIVATIONS
MAX = 4.468

and then Jack pressed the ' start ' button . All
mom . Everyone started singing ' Happy Birthday ' to John
and heard the man repeating " Ban ana , banana ,
of Jean . They counted " one , two , three
. Alexa loved the word " cup cake ". It sounded
with pasta . She wrote " past a " on a
Jack smiled and said he liked the way the problems made
. They laughed and shouted ' fore ' a lot .
, squares , and triangles all over the porch . When
. She tries to make one like his . She puts
the candles and everyone sang " Happy Birthday " to her
chalk board . Words like " hello " and " I
so happy that he yelled " Y ay !" Tim my
. She chooses the word " cat " and the number
race . Billy started counting " one , two , three
twist and turn the toy all day long .
said yes , and they all got to work ! All
had to use the words ' Please ' and ' Thank
, he wrote the letter ' M ' with his special
. Tim would spin the top every day and watch it

MIN ACTIVATIONS
MIN = -5.269

One day , the b unn ies happened across an elderly
with ." The kind sheep said , " I
. The b unn ies showed the elderly rabbit
lonely . The kind sheep asked , " Can
toast ? The c rows happily ate the toast
all knew that the b unn ies were having a very
please !" The kind sheep said , " I
seemed lonely . The b unn ies invited him to join
so happy and hugged the kind sheep tightly . The sheep
, leaving it to its former state .
. But the b unn ies didn 't wake up
. They learned that some chambers were not for them .
the harbor . The harbor has many boats . Some boats
unn ies . The b unn ies lived in a cozy
bed , knowing the b unn ies couldn 't get in
. The sw an on the right flew
in some weeds . The sw an paused again and decided
you !" The c rows were relieved , and
an . The sw an stops at the trash
. But the persistent sheep refused to give up

INTERVAL 2.034 - 4.468
CONTAINS 0.732%

heart . Tom and Anna look at each other
sweet and soft , but it was salty and crunch y
Do you know how dangerous that is ? You could have
friends . They danced together and had lots of fun .
counted to ten all of the children cheered , they had

INTERVAL -0.400 - 2.034
CONTAINS 68.306%

. <|endoftext|> Once upon a time , there was a little
. <|endoftext|> Once upon a time , there was an old
moral of the story is that we should always forgive .
He looked everywhere but could not find it . Tom felt
wanted to try something new . <|endoftext|> Once upon a time

INTERVAL -2.835 - -0.400
CONTAINS 30.854%

. When he got there , the grown - ups asked
. They hugged and smiled . They went to
was a little girl named Lily . She was playing in
mom my gave him some medicine and he felt better .
glove back on . He remembered just as he was about

INTERVAL -5.269 - -2.835
CONTAINS 0.108%

. And so , the sw an continued to live in
again . They learned that digging a tunnel was
. He gave him his own bag of food and said
time , in a big forest , there lived a squirrel
shelter . But , the shelter was always a little bit
Token and
Token ID290
Feature activation+2.87e-01

Pos logit contributions
 Jack+0.017
 Luke+0.017
 gigg+0.017
 subtract+0.016
 subt+0.016
Neg logit contributions
 vet-0.020
 hawk-0.019
oster-0.019
 pilot-0.019
 mir-0.018
Token then
Token ID788
Feature activation+9.80e-01

Pos logit contributions
igsaw+0.006
 subtract+0.006
 subt+0.006
 Luke+0.006
 Jack+0.006
Neg logit contributions
 vet-0.008
 pilot-0.008
 hawk-0.008
 wing-0.007
 mir-0.007
Token Jack
Token ID3619
Feature activation+1.13e+00

Pos logit contributions
 Luke+0.021
 subtract+0.021
 Jack+0.021
 subt+0.020
igsaw+0.020
Neg logit contributions
 vet-0.027
 hawk-0.026
 pilot-0.025
 mir-0.025
oster-0.025
Token pressed
Token ID12070
Feature activation+1.89e+00

Pos logit contributions
 Luke+0.025
 Jack+0.025
 subtract+0.024
 gigg+0.024
 subt+0.024
Neg logit contributions
 vet-0.031
 hawk-0.030
 pilot-0.029
 mir-0.029
oster-0.029
Token the
Token ID262
Feature activation+1.46e+00

Pos logit contributions
 subtract+0.046
 subt+0.045
igsaw+0.045
 Luke+0.044
 hips+0.044
Neg logit contributions
 vet-0.045
 hawk-0.042
 pilot-0.042
 wing-0.042
oster-0.040
Token '
Token ID705
Feature activation+4.47e+00

Pos logit contributions
 Luke+0.037
 subtract+0.037
 Jack+0.036
 subt+0.036
 gigg+0.036
Neg logit contributions
 vet-0.035
 hawk-0.033
 mir-0.032
oster-0.032
 pilot-0.032
Tokenstart
Token ID9688
Feature activation+6.26e-02

Pos logit contributions
 Luke+0.103
 Jack+0.102
 subtract+0.101
 gigg+0.100
 subt+0.099
Neg logit contributions
 vet-0.116
 hawk-0.109
 pilot-0.108
oster-0.108
 mir-0.106
Token'
Token ID6
Feature activation+2.15e+00

Pos logit contributions
 Luke+0.001
 Jack+0.001
 subtract+0.001
 subt+0.001
igsaw+0.001
Neg logit contributions
 vet-0.002
 hawk-0.002
 mir-0.002
 pilot-0.002
 wing-0.002
Token button
Token ID4936
Feature activation+1.41e+00

Pos logit contributions
 subtract+0.047
 Jack+0.046
 subt+0.045
 Luke+0.045
 gigg+0.043
Neg logit contributions
 vet-0.060
 hawk-0.058
 mir-0.058
oster-0.057
 pilot-0.057
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
 Jack+0.026
 Luke+0.026
 subtract+0.026
 subt+0.025
 gigg+0.025
Neg logit contributions
 vet-0.044
 hawk-0.042
 pilot-0.041
 mir-0.041
oster-0.040
Token All
Token ID1439
Feature activation+3.08e+00

Pos logit contributions
 Jack+0.026
 Luke+0.026
 subtract+0.025
 subt+0.024
igsaw+0.024
Neg logit contributions
 vet-0.046
 hawk-0.046
 mir-0.045
 pilot-0.045
oster-0.044
Token mom
Token ID1995
Feature activation+9.31e-01

Pos logit contributions
 subtract+0.016
 Luke+0.016
 subt+0.016
 Jack+0.015
igsaw+0.015
Neg logit contributions
 vet-0.021
 hawk-0.020
 wing-0.020
 pilot-0.020
 mir-0.019
Token.
Token ID13
Feature activation+1.00e+00

Pos logit contributions
 subtract+0.019
 subt+0.019
igsaw+0.019
 Luke+0.018
 Jack+0.018
Neg logit contributions
 vet-0.026
 pilot-0.025
 wing-0.025
 hawk-0.024
oster-0.024
Token Everyone
Token ID11075
Feature activation+2.71e+00

Pos logit contributions
 Jack+0.019
 Luke+0.018
 subtract+0.018
 subt+0.018
 gigg+0.018
Neg logit contributions
 vet-0.031
 hawk-0.030
 pilot-0.029
oster-0.029
 mir-0.029
Token started
Token ID2067
Feature activation-1.10e-01

Pos logit contributions
 subtract+0.064
 Luke+0.064
 Jack+0.064
 subt+0.063
igsaw+0.063
Neg logit contributions
 vet-0.069
 hawk-0.065
 pilot-0.065
oster-0.063
 mir-0.063
Token singing
Token ID13777
Feature activation+8.93e-02

Pos logit contributions
 vet+0.003
 hawk+0.003
 pilot+0.003
 mir+0.003
oster+0.003
Neg logit contributions
 Luke-0.003
 subtract-0.003
 Jack-0.003
 subt-0.002
 gigg-0.002
Token '
Token ID705
Feature activation+4.41e+00

Pos logit contributions
 Luke+0.002
 subtract+0.002
 Jack+0.002
 subt+0.002
 gigg+0.002
Neg logit contributions
 vet-0.002
 hawk-0.002
 pilot-0.002
 mir-0.002
oster-0.002
TokenHappy
Token ID25082
Feature activation-2.18e-02

Pos logit contributions
 Luke+0.097
 Jack+0.095
 hips+0.093
 subtract+0.092
 gigg+0.092
Neg logit contributions
 vet-0.119
oster-0.113
 pilot-0.113
 hawk-0.112
 wing-0.109
Token Birthday
Token ID33511
Feature activation+5.70e-01

Pos logit contributions
 vet+0.001
 pilot+0.001
 hawk+0.001
 wing+0.001
oster+0.001
Neg logit contributions
 subtract-0.000
 Luke-0.000
 Jack-0.000
 subt-0.000
 gigg-0.000
Token'
Token ID6
Feature activation+1.39e+00

Pos logit contributions
 subtract+0.011
 subt+0.011
 gigg+0.011
 Luke+0.010
igsaw+0.010
Neg logit contributions
 vet-0.017
 pilot-0.016
 wing-0.016
oster-0.016
 hawk-0.016
Token to
Token ID284
Feature activation+1.45e+00

Pos logit contributions
 Luke+0.028
 Jack+0.028
 subtract+0.027
 subt+0.027
 gigg+0.026
Neg logit contributions
 vet-0.041
 hawk-0.039
 pilot-0.038
 mir-0.038
oster-0.038
Token John
Token ID1757
Feature activation+1.17e+00

Pos logit contributions
 subtract+0.031
 subt+0.031
igsaw+0.031
 Luke+0.030
 gigg+0.030
Neg logit contributions
 vet-0.040
 pilot-0.038
 hawk-0.037
 wing-0.036
oster-0.036
Token and
Token ID290
Feature activation+2.07e+00

Pos logit contributions
 Jack+0.025
 gigg+0.024
 Luke+0.024
 subtract+0.024
 subt+0.023
Neg logit contributions
 vet-0.026
 hawk-0.025
oster-0.025
 pilot-0.025
 mir-0.024
Token heard
Token ID2982
Feature activation+4.14e-01

Pos logit contributions
 subtract+0.044
 Luke+0.044
igsaw+0.044
 Jack+0.044
 subt+0.043
Neg logit contributions
 vet-0.058
 hawk-0.055
 pilot-0.054
 mir-0.053
oster-0.053
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
 Luke+0.009
 Jack+0.009
 subtract+0.009
 subt+0.009
 gigg+0.009
Neg logit contributions
 vet-0.011
 hawk-0.011
 pilot-0.010
oster-0.010
 mir-0.010
Token man
Token ID582
Feature activation+1.87e+00

Pos logit contributions
igsaw+0.042
 Jack+0.041
 subt+0.040
 Luke+0.040
 wrists+0.039
Neg logit contributions
 vet-0.030
 pilot-0.027
 hawk-0.026
oster-0.025
 crow-0.025
Token repeating
Token ID20394
Feature activation+7.91e-01

Pos logit contributions
igsaw+0.037
 Luke+0.037
 subt+0.037
 Jack+0.036
 subtract+0.036
Neg logit contributions
 vet-0.055
 pilot-0.052
 wing-0.051
 hawk-0.051
 mir-0.050
Token "
Token ID366
Feature activation+4.36e+00

Pos logit contributions
 subtract+0.019
igsaw+0.019
 subt+0.019
 Luke+0.018
 Jack+0.018
Neg logit contributions
 vet-0.020
 pilot-0.018
 hawk-0.018
 wing-0.018
 mir-0.018
TokenBan
Token ID30457
Feature activation+8.84e-01

Pos logit contributions
 subtract+0.099
 Luke+0.097
 Jack+0.097
 subt+0.096
 gigg+0.096
Neg logit contributions
 vet-0.118
 hawk-0.112
 mir-0.109
 pilot-0.109
 wing-0.108
Tokenana
Token ID2271
Feature activation+3.78e-01

Pos logit contributions
 Jack+0.022
 Luke+0.021
 subt+0.021
igsaw+0.021
 subtract+0.020
Neg logit contributions
oster-0.022
 vet-0.022
 mir-0.020
 pilot-0.020
 wing-0.019
Token,
Token ID11
Feature activation-9.44e-02

Pos logit contributions
 Jack+0.007
 Luke+0.007
 subtract+0.007
 gigg+0.007
 subt+0.007
Neg logit contributions
 vet-0.011
 hawk-0.011
 mir-0.011
 pilot-0.011
oster-0.010
Token banana
Token ID25996
Feature activation-4.03e-01

Pos logit contributions
 vet+0.003
 hawk+0.002
 pilot+0.002
oster+0.002
 mir+0.002
Neg logit contributions
 Luke-0.002
 Jack-0.002
 subtract-0.002
 gigg-0.002
 subt-0.002
Token,
Token ID11
Feature activation+6.25e-01

Pos logit contributions
 vet+0.013
 hawk+0.012
 pilot+0.012
 mir+0.012
oster+0.012
Neg logit contributions
 Luke-0.007
 Jack-0.007
 subtract-0.007
 gigg-0.007
 subt-0.007
Token of
Token ID286
Feature activation+1.88e+00

Pos logit contributions
 subtract+0.054
 Luke+0.054
igsaw+0.054
 subt+0.054
 Jack+0.053
Neg logit contributions
 vet-0.068
 pilot-0.064
 hawk-0.064
 wing-0.063
 mir-0.062
Token Jean
Token ID11320
Feature activation+2.00e+00

Pos logit contributions
ksh+0.044
igsaw+0.043
idents+0.041
 wrists+0.041
irms+0.040
Neg logit contributions
 vet-0.047
 pilot-0.045
 hawk-0.044
 adult-0.043
 mir-0.042
Token.
Token ID13
Feature activation+6.95e-01

Pos logit contributions
igsaw+0.044
 subt+0.043
 subtract+0.042
 Luke+0.042
irms+0.041
Neg logit contributions
 vet-0.054
 pilot-0.052
 wing-0.050
 hawk-0.050
oster-0.048
Token They
Token ID1119
Feature activation+1.82e+00

Pos logit contributions
 subtract+0.014
 Luke+0.014
igsaw+0.014
 Jack+0.013
 gigg+0.013
Neg logit contributions
 vet-0.020
 hawk-0.019
 pilot-0.019
oster-0.019
 mir-0.019
Token counted
Token ID14789
Feature activation+1.74e+00

Pos logit contributions
igsaw+0.047
 subt+0.041
irms+0.041
 subtract+0.040
idents+0.040
Neg logit contributions
 pilot-0.047
 vet-0.045
 hawk-0.043
oster-0.042
 captain-0.041
Token "
Token ID366
Feature activation+4.36e+00

Pos logit contributions
igsaw+0.043
 subt+0.042
 Luke+0.042
 subtract+0.042
 Jack+0.041
Neg logit contributions
 vet-0.042
 pilot-0.040
 hawk-0.039
 wing-0.038
 mir-0.036
Tokenone
Token ID505
Feature activation+1.66e+00

Pos logit contributions
 Luke+0.095
 subtract+0.095
 Jack+0.094
 subt+0.093
 gigg+0.092
Neg logit contributions
 vet-0.119
 hawk-0.113
 pilot-0.112
 mir-0.110
oster-0.110
Token,
Token ID11
Feature activation+6.74e-01

Pos logit contributions
 Luke+0.035
 Jack+0.035
 subtract+0.035
 subt+0.034
 gigg+0.034
Neg logit contributions
 vet-0.047
 hawk-0.044
 pilot-0.044
oster-0.043
 mir-0.043
Token two
Token ID734
Feature activation-8.83e-02

Pos logit contributions
 Luke+0.015
 Jack+0.015
 subtract+0.015
 subt+0.015
 gigg+0.015
Neg logit contributions
 vet-0.018
 hawk-0.017
 pilot-0.017
 mir-0.016
oster-0.016
Token,
Token ID11
Feature activation+5.09e-01

Pos logit contributions
 vet+0.002
 pilot+0.002
 hawk+0.002
 wing+0.002
 mir+0.002
Neg logit contributions
 Luke-0.002
igsaw-0.002
 subt-0.002
 Jack-0.002
 subtract-0.002
Token three
Token ID1115
Feature activation-9.48e-01

Pos logit contributions
 subtract+0.012
 Jack+0.012
 Luke+0.012
 subt+0.011
 gigg+0.011
Neg logit contributions
 vet-0.013
 hawk-0.013
 mir-0.013
oster-0.012
 pilot-0.012
Token.
Token ID13
Feature activation+9.33e-01

Pos logit contributions
 Jack+0.039
 Luke+0.039
 subtract+0.037
 James+0.036
 subt+0.036
Neg logit contributions
 vet-0.055
 mir-0.055
oster-0.055
 hawk-0.054
 pilot-0.052
Token Alexa
Token ID34630
Feature activation-2.76e-01

Pos logit contributions
 subtract+0.020
igsaw+0.020
 Jack+0.020
 subt+0.020
 gigg+0.020
Neg logit contributions
 vet-0.026
 pilot-0.023
 wing-0.023
 hawk-0.023
oster-0.022
Token loved
Token ID6151
Feature activation+2.37e+00

Pos logit contributions
 vet+0.009
 mir+0.008
 hawk+0.008
oster+0.008
 wing+0.008
Neg logit contributions
 gigg-0.005
 Jack-0.005
 Luke-0.005
 subt-0.005
 subtract-0.005
Token the
Token ID262
Feature activation+2.09e+00

Pos logit contributions
igsaw+0.058
 hips+0.055
 Luke+0.055
 subtract+0.055
 subt+0.054
Neg logit contributions
 vet-0.059
 hawk-0.055
 pilot-0.054
 mir-0.053
 wing-0.053
Token word
Token ID1573
Feature activation+2.62e+00

Pos logit contributions
 wrists+0.069
igsaw+0.068
 hips+0.067
ksh+0.067
 subt+0.067
Neg logit contributions
 vet-0.036
 hawk-0.031
 pilot-0.030
 crow-0.028
 wing-0.028
Token "
Token ID366
Feature activation+4.23e+00

Pos logit contributions
 Luke+0.057
 Jack+0.057
 subtract+0.056
 subt+0.055
 gigg+0.055
Neg logit contributions
 vet-0.072
 hawk-0.069
 mir-0.068
oster-0.068
 pilot-0.068
Tokencup
Token ID25244
Feature activation-3.49e-01

Pos logit contributions
 subtract+0.098
 subt+0.091
 Jack+0.091
 gigg+0.090
 Luke+0.090
Neg logit contributions
 vet-0.115
 mir-0.113
 hawk-0.113
 pilot-0.105
 wing-0.105
Tokencake
Token ID30560
Feature activation+1.01e+00

Pos logit contributions
 vet+0.009
 hawk+0.008
 mir+0.008
 pilot+0.008
oster+0.008
Neg logit contributions
 Luke-0.009
 Jack-0.009
 subtract-0.008
igsaw-0.008
 subt-0.008
Token".
Token ID1911
Feature activation+1.22e+00

Pos logit contributions
 Jack+0.026
 Luke+0.026
 subtract+0.025
 subt+0.025
 gigg+0.024
Neg logit contributions
 vet-0.024
 hawk-0.023
 pilot-0.023
 mir-0.023
 wing-0.022
Token It
Token ID632
Feature activation+2.46e+00

Pos logit contributions
igsaw+0.029
ci+0.028
 subtract+0.028
 subt+0.028
 Jack+0.027
Neg logit contributions
 vet-0.031
 pilot-0.027
 wing-0.027
 doctor-0.027
 veterinarian-0.026
Token sounded
Token ID14846
Feature activation+5.95e-01

Pos logit contributions
 Luke+0.053
 Jack+0.053
 subtract+0.053
 subt+0.052
 gigg+0.052
Neg logit contributions
 vet-0.068
 hawk-0.065
 pilot-0.064
 mir-0.063
oster-0.063
Token with
Token ID351
Feature activation+1.52e+00

Pos logit contributions
 subt+0.035
 subtract+0.034
 Luke+0.034
igsaw+0.034
 Jack+0.033
Neg logit contributions
 vet-0.030
 pilot-0.028
 wing-0.028
 mir-0.027
 hawk-0.027
Token pasta
Token ID26296
Feature activation+1.38e+00

Pos logit contributions
 subt+0.037
 subtract+0.036
igsaw+0.036
 Luke+0.036
 hips+0.035
Neg logit contributions
 vet-0.037
 wing-0.035
 pilot-0.034
 hawk-0.034
 mir-0.034
Token.
Token ID13
Feature activation+7.65e-01

Pos logit contributions
 subtract+0.030
 subt+0.029
 Luke+0.029
igsaw+0.029
 Jack+0.029
Neg logit contributions
 vet-0.038
 pilot-0.035
oster-0.035
 mir-0.035
 wing-0.035
Token She
Token ID1375
Feature activation+1.57e+00

Pos logit contributions
 Luke+0.020
igsaw+0.019
 subt+0.019
 hips+0.019
 gigg+0.019
Neg logit contributions
 vet-0.019
 doctor-0.015
 wing-0.015
 veterinarian-0.015
 pilot-0.015
Token wrote
Token ID2630
Feature activation-6.38e-02

Pos logit contributions
 Jack+0.031
 gigg+0.031
 Luke+0.031
 subtract+0.030
 subt+0.030
Neg logit contributions
 vet-0.047
 hawk-0.047
 mir-0.045
oster-0.044
 wing-0.044
Token "
Token ID366
Feature activation+4.21e+00

Pos logit contributions
 vet+0.002
 hawk+0.002
 mir+0.002
oster+0.002
 pilot+0.002
Neg logit contributions
 Luke-0.001
 Jack-0.001
 subtract-0.001
 gigg-0.001
 subt-0.001
Tokenpast
Token ID30119
Feature activation+7.08e-01

Pos logit contributions
 subtract+0.099
 subt+0.094
 Jack+0.094
 Luke+0.093
 gigg+0.090
Neg logit contributions
 vet-0.114
 hawk-0.113
 mir-0.108
 pilot-0.105
 wing-0.104
Tokena
Token ID64
Feature activation+6.41e-01

Pos logit contributions
 Luke+0.016
 Jack+0.016
 subtract+0.016
 subt+0.015
igsaw+0.015
Neg logit contributions
 vet-0.019
 hawk-0.018
 pilot-0.018
 mir-0.018
 wing-0.017
Token"
Token ID1
Feature activation+1.56e+00

Pos logit contributions
 Luke+0.015
 Jack+0.015
 subtract+0.014
 gigg+0.014
 subt+0.014
Neg logit contributions
 vet-0.017
 hawk-0.017
 pilot-0.016
 mir-0.016
 wing-0.015
Token on
Token ID319
Feature activation+3.41e-01

Pos logit contributions
 Jack+0.035
 subtract+0.035
 Luke+0.034
 gigg+0.034
 subt+0.033
Neg logit contributions
 hawk-0.043
 vet-0.043
 mir-0.042
oster-0.040
 pilot-0.040
Token a
Token ID257
Feature activation+2.62e+00

Pos logit contributions
 Jack+0.007
 Luke+0.007
 subtract+0.006
igsaw+0.006
 subt+0.006
Neg logit contributions
 vet-0.011
 hawk-0.011
 pilot-0.010
 mir-0.010
oster-0.010
Token Jack
Token ID3619
Feature activation+3.56e-01

Pos logit contributions
 gigg+0.009
ci+0.009
 wrists+0.008
rob+0.008
hetically+0.008
Neg logit contributions
 vet-0.036
 doctor-0.032
 or-0.032
 veterinarian-0.032
 pilot-0.032
Token smiled
Token ID13541
Feature activation+4.32e-01

Pos logit contributions
 subtract+0.007
igsaw+0.007
 subt+0.006
 Luke+0.006
 Jack+0.006
Neg logit contributions
 vet-0.011
 hawk-0.010
 pilot-0.010
oster-0.010
 wing-0.010
Token and
Token ID290
Feature activation+1.45e+00

Pos logit contributions
 Jack+0.011
 Luke+0.011
 gigg+0.011
 subtract+0.010
 hips+0.010
Neg logit contributions
 vet-0.011
 hawk-0.011
oster-0.011
 mir-0.010
 pilot-0.010
Token said
Token ID531
Feature activation+3.50e-01

Pos logit contributions
igsaw+0.034
 hips+0.030
ksh+0.029
irms+0.029
 subt+0.028
Neg logit contributions
 vet-0.041
 pilot-0.037
 hawk-0.036
 wing-0.035
 doctor-0.035
Token he
Token ID339
Feature activation+1.30e+00

Pos logit contributions
 Jack+0.007
 Luke+0.007
 subtract+0.007
 subt+0.007
 gigg+0.007
Neg logit contributions
 vet-0.010
 hawk-0.009
 pilot-0.009
oster-0.009
 mir-0.009
Token liked
Token ID8288
Feature activation+4.20e+00

Pos logit contributions
igsaw+0.038
 subt+0.035
 hips+0.035
 subtract+0.035
 wrists+0.035
Neg logit contributions
 vet-0.028
 pilot-0.026
 wing-0.024
oster-0.024
 hawk-0.023
Token the
Token ID262
Feature activation+3.78e+00

Pos logit contributions
ksh+0.107
ci+0.103
irms+0.101
 hips+0.099
hetically+0.099
Neg logit contributions
 vet-0.099
 doctor-0.091
 pilot-0.088
 or-0.088
 adult-0.086
Token way
Token ID835
Feature activation+2.61e+00

Pos logit contributions
 wrists+0.102
ksh+0.099
ci+0.097
 gigg+0.093
 hips+0.092
Neg logit contributions
 vet-0.090
 doctor-0.087
 pilot-0.080
 moral-0.078
 veterinarian-0.077
Token the
Token ID262
Feature activation+3.59e+00

Pos logit contributions
 subt+0.061
 gigg+0.061
 subtract+0.060
 wrists+0.060
igsaw+0.059
Neg logit contributions
 vet-0.065
 pilot-0.063
 hawk-0.061
 wing-0.060
 mir-0.058
Token problems
Token ID2761
Feature activation+1.80e+00

Pos logit contributions
 wrists+0.092
ksh+0.092
ci+0.089
 gigg+0.088
 hips+0.085
Neg logit contributions
 vet-0.087
 doctor-0.081
 pilot-0.078
 moral-0.075
 veterinarian-0.074
Token made
Token ID925
Feature activation+2.49e+00

Pos logit contributions
 Luke+0.038
 subtract+0.037
 subt+0.037
 Jack+0.037
igsaw+0.037
Neg logit contributions
 vet-0.050
 pilot-0.047
 hawk-0.047
oster-0.046
 wing-0.046
Token.
Token ID13
Feature activation+2.71e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
oster+0.002
 mir+0.001
 pilot+0.001
Neg logit contributions
 Jack-0.001
 Luke-0.001
 subtract-0.001
 gigg-0.001
 hands-0.001
Token They
Token ID1119
Feature activation+8.67e-01

Pos logit contributions
 Jack+0.005
 Luke+0.005
 subtract+0.005
 +0.004
 subt+0.004
Neg logit contributions
 hawk-0.009
 pilot-0.009
 mir-0.009
oster-0.009
 wing-0.009
Token laughed
Token ID13818
Feature activation+5.49e-01

Pos logit contributions
 Luke+0.019
 Jack+0.019
 subtract+0.019
 gigg+0.019
 subt+0.019
Neg logit contributions
 vet-0.024
 hawk-0.022
 mir-0.022
 pilot-0.022
oster-0.022
Token and
Token ID290
Feature activation+1.45e+00

Pos logit contributions
 Jack+0.014
 gigg+0.014
 Luke+0.014
 subtract+0.013
 subt+0.013
Neg logit contributions
 vet-0.013
 mir-0.013
oster-0.013
 hawk-0.013
 pilot-0.012
Token shouted
Token ID17293
Feature activation+7.98e-01

Pos logit contributions
igsaw+0.044
ello+0.033
 sauces+0.032
idents+0.032
 batch+0.032
Neg logit contributions
 vet-0.037
 hawk-0.036
 wing-0.035
 pilot-0.034
 tou-0.033
Token '
Token ID705
Feature activation+4.17e+00

Pos logit contributions
 Luke+0.015
 Jack+0.015
 subtract+0.015
 subt+0.015
 gigg+0.015
Neg logit contributions
 vet-0.024
 hawk-0.023
 pilot-0.023
 mir-0.022
oster-0.022
Tokenfore
Token ID754
Feature activation+9.11e-01

Pos logit contributions
 Luke+0.108
 Jack+0.106
igsaw+0.104
 hips+0.104
 shoulders+0.101
Neg logit contributions
 vet-0.098
 hawk-0.095
oster-0.093
 pilot-0.090
 mir-0.086
Token'
Token ID6
Feature activation+1.65e+00

Pos logit contributions
 Jack+0.023
 Luke+0.023
 subtract+0.023
igsaw+0.023
 subt+0.023
Neg logit contributions
 vet-0.021
 pilot-0.020
oster-0.020
 hawk-0.020
 wing-0.019
Token a
Token ID257
Feature activation+7.62e-01

Pos logit contributions
 subtract+0.036
 Jack+0.036
 Luke+0.036
 subt+0.035
 gigg+0.035
Neg logit contributions
 vet-0.045
 hawk-0.043
 mir-0.043
 pilot-0.042
oster-0.042
Token lot
Token ID1256
Feature activation-4.40e-01

Pos logit contributions
 Luke+0.018
 Jack+0.018
 subtract+0.018
igsaw+0.017
 gigg+0.017
Neg logit contributions
 vet-0.019
 hawk-0.018
oster-0.018
 pilot-0.018
 mir-0.018
Token.
Token ID13
Feature activation+9.07e-01

Pos logit contributions
 vet+0.014
 hawk+0.014
 pilot+0.014
 mir+0.014
oster+0.014
Neg logit contributions
 Jack-0.008
igsaw-0.007
 Luke-0.007
 subtract-0.007
 subt-0.007
Token,
Token ID11
Feature activation+9.33e-01

Pos logit contributions
 Luke+0.042
 subtract+0.042
 subt+0.042
igsaw+0.041
 Jack+0.041
Neg logit contributions
 vet-0.052
 pilot-0.050
 hawk-0.049
 wing-0.049
oster-0.048
Token squares
Token ID24438
Feature activation+2.29e-01

Pos logit contributions
 subtract+0.017
 Luke+0.017
 Jack+0.017
 subt+0.017
 gigg+0.017
Neg logit contributions
 vet-0.029
 hawk-0.028
 pilot-0.027
oster-0.027
 mir-0.027
Token,
Token ID11
Feature activation+7.58e-01

Pos logit contributions
 Jack+0.005
 subtract+0.005
 Luke+0.005
 gigg+0.005
 subt+0.005
Neg logit contributions
 vet-0.006
 hawk-0.006
 pilot-0.006
 mir-0.006
oster-0.006
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
 subtract+0.017
 Jack+0.017
 Luke+0.017
 gigg+0.017
 subt+0.016
Neg logit contributions
 vet-0.021
 hawk-0.020
oster-0.020
 mir-0.020
 pilot-0.019
Token triangles
Token ID44360
Feature activation+9.69e-01

Pos logit contributions
igsaw+0.025
 Luke+0.023
 hips+0.023
 Jack+0.023
 subtract+0.023
Neg logit contributions
 vet-0.037
 pilot-0.035
 wing-0.034
 hawk-0.034
 mir-0.033
Token all
Token ID477
Feature activation+4.16e+00

Pos logit contributions
 Jack+0.017
 subtract+0.017
 Luke+0.017
 gigg+0.017
 subt+0.016
Neg logit contributions
 vet-0.031
 hawk-0.030
 pilot-0.029
 mir-0.029
oster-0.029
Token over
Token ID625
Feature activation+2.81e+00

Pos logit contributions
 hips+0.113
igsaw+0.112
irms+0.112
idents+0.109
 Luke+0.108
Neg logit contributions
ull-0.087
 pilot-0.084
 wing-0.080
 mir-0.076
 vet-0.076
Token the
Token ID262
Feature activation+3.37e+00

Pos logit contributions
 subtract+0.064
 Luke+0.064
 subt+0.063
 Jack+0.063
igsaw+0.063
Neg logit contributions
 vet-0.073
 hawk-0.068
 pilot-0.068
 mir-0.067
 wing-0.067
Token porch
Token ID33179
Feature activation+1.21e+00

Pos logit contributions
irms+0.088
ksh+0.088
 gigg+0.087
 Luke+0.086
 subt+0.086
Neg logit contributions
 vet-0.066
 pilot-0.066
 wing-0.066
 or-0.061
 hawk-0.060
Token.
Token ID13
Feature activation+1.40e+00

Pos logit contributions
 Luke+0.025
igsaw+0.024
 subt+0.024
 subtract+0.024
 Jack+0.023
Neg logit contributions
 vet-0.034
 pilot-0.032
 wing-0.032
oster-0.031
 hawk-0.031
Token When
Token ID1649
Feature activation+1.44e+00

Pos logit contributions
 gigg+0.030
 subtract+0.030
 subt+0.030
 wrists+0.030
igsaw+0.029
Neg logit contributions
 vet-0.039
 hawk-0.035
 pilot-0.035
oster-0.035
 mir-0.035
Token.
Token ID13
Feature activation+1.52e+00

Pos logit contributions
 Luke+0.037
 subt+0.036
 Jack+0.036
 subtract+0.036
igsaw+0.036
Neg logit contributions
 vet-0.052
 wing-0.050
 hawk-0.049
 pilot-0.049
oster-0.048
Token She
Token ID1375
Feature activation-1.23e-02

Pos logit contributions
ci+0.037
 gigg+0.036
 wrists+0.036
 hips+0.035
 subt+0.035
Neg logit contributions
 vet-0.039
 hawk-0.034
 pilot-0.032
 veterinarian-0.032
 mir-0.032
Token tries
Token ID8404
Feature activation+1.66e+00

Pos logit contributions
 vet+0.000
 pilot+0.000
 or+0.000
 hawk+0.000
 doctor+0.000
Neg logit contributions
igsaw-0.000
ci-0.000
 Jack-0.000
whe-0.000
 subt-0.000
Token to
Token ID284
Feature activation+8.13e-01

Pos logit contributions
igsaw+0.045
 Luke+0.045
 subt+0.045
 subtract+0.045
 Jack+0.044
Neg logit contributions
 vet-0.036
 wing-0.032
 hawk-0.031
 pilot-0.031
 mir-0.031
Token make
Token ID787
Feature activation+2.39e+00

Pos logit contributions
 Luke+0.019
 subt+0.019
igsaw+0.019
 Jack+0.018
 subtract+0.018
Neg logit contributions
 vet-0.021
 pilot-0.020
 hawk-0.019
 wing-0.019
oster-0.019
Token one
Token ID530
Feature activation+4.12e+00

Pos logit contributions
ci+0.085
ksh+0.078
 subt+0.078
igsaw+0.077
 hips+0.077
Neg logit contributions
 vet-0.039
 fire-0.037
 wing-0.034
 doctor-0.034
 or-0.032
Token like
Token ID588
Feature activation+2.45e+00

Pos logit contributions
 subt+0.106
igsaw+0.100
 subtract+0.099
 Luke+0.099
 hips+0.099
Neg logit contributions
 vet-0.098
 wing-0.095
 pilot-0.090
 hawk-0.088
 or-0.083
Token his
Token ID465
Feature activation+3.76e+00

Pos logit contributions
igsaw+0.054
 subt+0.054
 Luke+0.054
 subtract+0.054
 gigg+0.054
Neg logit contributions
 vet-0.065
 hawk-0.061
 pilot-0.059
 wing-0.059
 mir-0.057
Token.
Token ID13
Feature activation+1.72e+00

Pos logit contributions
 subt+0.084
igsaw+0.080
arrass+0.078
 gigg+0.078
ksh+0.078
Neg logit contributions
 wing-0.100
 vet-0.099
 pilot-0.094
 hawk-0.090
 doctor-0.086
Token She
Token ID1375
Feature activation+6.24e-01

Pos logit contributions
 Luke+0.035
 subtract+0.035
 gigg+0.035
igsaw+0.035
 subt+0.035
Neg logit contributions
 vet-0.049
 hawk-0.045
 pilot-0.044
oster-0.044
 mir-0.044
Token puts
Token ID7584
Feature activation+2.99e+00

Pos logit contributions
igsaw+0.013
 Jack+0.012
 Luke+0.012
 subt+0.012
ci+0.011
Neg logit contributions
 vet-0.018
 pilot-0.016
 hawk-0.016
 wing-0.016
 or-0.016
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
 Jack+0.000
 gigg+0.000
 Luke+0.000
 hands+0.000
 subtract+0.000
Neg logit contributions
 vet-0.000
 hawk-0.000
oster-0.000
 mir-0.000
 pilot-0.000
Token candles
Token ID32268
Feature activation+1.04e+00

Pos logit contributions
 Jack+0.020
 subtract+0.020
 Luke+0.020
 gigg+0.020
 subt+0.019
Neg logit contributions
 vet-0.035
 hawk-0.034
 mir-0.033
 pilot-0.033
oster-0.033
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
 Jack+0.027
 Luke+0.025
 gigg+0.025
 subtract+0.024
 hips+0.024
Neg logit contributions
 vet-0.027
 hawk-0.025
 mir-0.025
oster-0.025
 pilot-0.024
Token everyone
Token ID2506
Feature activation+2.23e+00

Pos logit contributions
igsaw+0.022
 subtract+0.022
 Luke+0.022
 subt+0.022
 Jack+0.021
Neg logit contributions
 vet-0.028
 pilot-0.026
 hawk-0.026
 wing-0.026
 mir-0.025
Token sang
Token ID25889
Feature activation+3.73e-01

Pos logit contributions
igsaw+0.054
 subtract+0.054
 Luke+0.054
 subt+0.053
 Jack+0.052
Neg logit contributions
 vet-0.054
 pilot-0.053
 wing-0.051
 hawk-0.051
oster-0.051
Token "
Token ID366
Feature activation+4.10e+00

Pos logit contributions
 subtract+0.008
 Luke+0.008
 Jack+0.008
 subt+0.008
igsaw+0.008
Neg logit contributions
 vet-0.010
 hawk-0.010
 pilot-0.009
oster-0.009
 mir-0.009
TokenHappy
Token ID25082
Feature activation-4.41e-03

Pos logit contributions
 subtract+0.094
 Jack+0.092
 subt+0.092
 gigg+0.091
 Luke+0.091
Neg logit contributions
 vet-0.110
 hawk-0.105
 mir-0.102
 pilot-0.100
 wing-0.100
Token Birthday
Token ID33511
Feature activation-2.56e-01

Pos logit contributions
 vet+0.000
 hawk+0.000
 mir+0.000
 pilot+0.000
oster+0.000
Neg logit contributions
 Jack-0.000
 Luke-0.000
 subtract-0.000
 subt-0.000
 gigg-0.000
Token"
Token ID1
Feature activation+2.00e+00

Pos logit contributions
 vet+0.006
 hawk+0.006
 pilot+0.005
 mir+0.005
oster+0.005
Neg logit contributions
 Jack-0.007
 Luke-0.007
 subtract-0.007
 subt-0.007
 gigg-0.007
Token to
Token ID284
Feature activation+7.86e-01

Pos logit contributions
 Luke+0.049
 Jack+0.048
 subtract+0.048
 subt+0.048
 gigg+0.047
Neg logit contributions
 vet-0.050
 hawk-0.047
 pilot-0.046
 mir-0.046
oster-0.046
Token her
Token ID607
Feature activation+8.78e-01

Pos logit contributions
 subt+0.017
 subtract+0.017
 Luke+0.017
igsaw+0.017
 hips+0.017
Neg logit contributions
 vet-0.021
 pilot-0.020
 hawk-0.019
 wing-0.019
 mir-0.019
Token chalk
Token ID30860
Feature activation+2.67e+00

Pos logit contributions
 subt+0.047
 gigg+0.047
 Luke+0.046
irms+0.045
 wrists+0.045
Neg logit contributions
 vet-0.046
 wing-0.044
 pilot-0.044
 hawk-0.042
oster-0.040
Tokenboard
Token ID3526
Feature activation+7.43e-01

Pos logit contributions
 Luke+0.057
 subtract+0.057
 Jack+0.057
 subt+0.056
 gigg+0.056
Neg logit contributions
 vet-0.074
 hawk-0.070
 pilot-0.069
 wing-0.068
oster-0.068
Token.
Token ID13
Feature activation+2.60e-02

Pos logit contributions
 Jack+0.015
 Luke+0.015
 subtract+0.015
 subt+0.014
 gigg+0.014
Neg logit contributions
 vet-0.022
 hawk-0.021
 mir-0.021
 pilot-0.021
oster-0.021
Token Words
Token ID23087
Feature activation+8.81e-01

Pos logit contributions
 Luke+0.001
igsaw+0.001
 subtract+0.001
 subt+0.001
 gigg+0.001
Neg logit contributions
 vet-0.001
 pilot-0.001
 wing-0.001
 hawk-0.001
 mir-0.001
Token like
Token ID588
Feature activation+1.43e+00

Pos logit contributions
 Jack+0.021
 subtract+0.021
 Luke+0.020
 gigg+0.020
 subt+0.020
Neg logit contributions
 vet-0.024
 hawk-0.023
 mir-0.023
oster-0.022
 wing-0.022
Token "
Token ID366
Feature activation+4.04e+00

Pos logit contributions
 Luke+0.029
 subtract+0.029
 Jack+0.029
 subt+0.028
igsaw+0.028
Neg logit contributions
 vet-0.041
 hawk-0.039
 pilot-0.039
 wing-0.038
 mir-0.038
Tokenhello
Token ID31373
Feature activation+3.06e-01

Pos logit contributions
 subtract+0.097
 subt+0.090
 Jack+0.088
 gigg+0.086
igsaw+0.085
Neg logit contributions
 vet-0.109
 hawk-0.108
 mir-0.107
 wing-0.099
oster-0.099
Token"
Token ID1
Feature activation+1.68e+00

Pos logit contributions
 Jack+0.009
 Luke+0.009
 subtract+0.009
 subt+0.008
igsaw+0.008
Neg logit contributions
 vet-0.007
 hawk-0.006
 mir-0.006
oster-0.006
 pilot-0.006
Token and
Token ID290
Feature activation+1.00e+00

Pos logit contributions
 Jack+0.042
 Luke+0.042
 subtract+0.042
 subt+0.041
 gigg+0.041
Neg logit contributions
 vet-0.041
 hawk-0.039
 pilot-0.038
 mir-0.038
oster-0.038
Token "
Token ID366
Feature activation+3.41e+00

Pos logit contributions
igsaw+0.022
 Luke+0.021
 hips+0.020
 Jack+0.020
 subtract+0.020
Neg logit contributions
 vet-0.028
 pilot-0.026
 hawk-0.025
 wing-0.025
 mir-0.025
TokenI
Token ID40
Feature activation+8.58e-01

Pos logit contributions
 subtract+0.082
 subt+0.077
 Jack+0.076
 gigg+0.074
 Luke+0.074
Neg logit contributions
 hawk-0.090
 vet-0.090
 mir-0.087
 wing-0.084
 pilot-0.082
Token so
Token ID523
Feature activation+1.21e+00

Pos logit contributions
 subtract+0.027
 Luke+0.027
igsaw+0.027
 subt+0.026
 Jack+0.026
Neg logit contributions
 vet-0.031
 pilot-0.029
 hawk-0.029
 wing-0.029
 mir-0.029
Token happy
Token ID3772
Feature activation+1.01e+00

Pos logit contributions
 Luke+0.029
 subt+0.029
igsaw+0.029
 subtract+0.029
 hips+0.028
Neg logit contributions
 vet-0.030
 mir-0.029
 pilot-0.029
oster-0.029
 wing-0.028
Token that
Token ID326
Feature activation+1.87e+00

Pos logit contributions
igsaw+0.031
 subt+0.030
 wrists+0.030
 hips+0.030
 subtract+0.030
Neg logit contributions
 vet-0.019
 or-0.017
 wing-0.017
 pilot-0.017
 mir-0.017
Token he
Token ID339
Feature activation+1.38e+00

Pos logit contributions
igsaw+0.046
 subtract+0.045
 subt+0.045
 wrists+0.044
 Luke+0.044
Neg logit contributions
 vet-0.047
 pilot-0.044
 hawk-0.044
 mir-0.043
 wing-0.043
Token yelled
Token ID22760
Feature activation+6.29e-01

Pos logit contributions
 subtract+0.031
igsaw+0.031
 Luke+0.031
 subt+0.030
 Jack+0.030
Neg logit contributions
 vet-0.037
 hawk-0.035
 pilot-0.035
oster-0.034
 mir-0.034
Token "
Token ID366
Feature activation+4.02e+00

Pos logit contributions
 subtract+0.015
 Luke+0.014
 subt+0.014
igsaw+0.014
 Jack+0.014
Neg logit contributions
 vet-0.016
 pilot-0.015
 hawk-0.015
 wing-0.015
 mir-0.015
TokenY
Token ID56
Feature activation+2.93e+00

Pos logit contributions
 Luke+0.091
 Jack+0.091
 subtract+0.091
 subt+0.089
 gigg+0.088
Neg logit contributions
 vet-0.106
 hawk-0.101
 pilot-0.099
oster-0.098
 mir-0.098
Tokenay
Token ID323
Feature activation+1.45e+00

Pos logit contributions
 wrists+0.077
 Luke+0.076
 gigg+0.075
 hips+0.075
 subt+0.073
Neg logit contributions
 vet-0.064
oral-0.058
oster-0.058
 wing-0.057
 pilot-0.056
Token!"
Token ID2474
Feature activation+5.68e-01

Pos logit contributions
 subtract+0.026
 subt+0.025
igsaw+0.025
 Luke+0.025
 wrists+0.024
Neg logit contributions
 vet-0.045
 hawk-0.044
 pilot-0.043
oster-0.043
 wing-0.043
Token Tim
Token ID5045
Feature activation+1.62e+00

Pos logit contributions
igsaw+0.014
 Luke+0.014
 subt+0.014
 subtract+0.013
 gigg+0.013
Neg logit contributions
 vet-0.015
 pilot-0.013
 wing-0.013
oster-0.013
 hawk-0.013
Tokenmy
Token ID1820
Feature activation+8.75e-01

Pos logit contributions
igsaw+0.035
 subt+0.034
 Luke+0.034
 wrists+0.034
 subtract+0.033
Neg logit contributions
 vet-0.045
 wing-0.043
 pilot-0.043
oster-0.040
 hawk-0.040
Token.
Token ID13
Feature activation-6.30e-02

Pos logit contributions
 Jack+0.034
 Luke+0.034
 subtract+0.034
 gigg+0.034
 hips+0.033
Neg logit contributions
 hawk-0.038
 vet-0.038
 mir-0.037
oster-0.036
 pilot-0.035
Token She
Token ID1375
Feature activation+3.83e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
 pilot+0.002
 wing+0.002
 mir+0.002
Neg logit contributions
 subtract-0.001
 Luke-0.001
 subt-0.001
 Jack-0.001
 gigg-0.001
Token chooses
Token ID19769
Feature activation+1.59e+00

Pos logit contributions
igsaw+0.007
 Jack+0.007
 Luke+0.006
 subtract+0.006
 subt+0.006
Neg logit contributions
 vet-0.012
 pilot-0.011
 hawk-0.011
 mir-0.011
 wing-0.011
Token the
Token ID262
Feature activation+1.58e+00

Pos logit contributions
igsaw+0.037
 Luke+0.037
 Jack+0.037
 subtract+0.036
 subt+0.036
Neg logit contributions
 vet-0.041
 pilot-0.038
 hawk-0.038
 wing-0.037
oster-0.036
Token word
Token ID1573
Feature activation+2.39e+00

Pos logit contributions
 Jack+0.039
 Luke+0.039
 subt+0.039
igsaw+0.039
 gigg+0.038
Neg logit contributions
 vet-0.038
 pilot-0.035
 hawk-0.034
 wing-0.034
 mir-0.033
Token "
Token ID366
Feature activation+4.02e+00

Pos logit contributions
 Luke+0.049
 Jack+0.049
 subtract+0.049
 subt+0.047
 gigg+0.047
Neg logit contributions
 vet-0.068
 hawk-0.067
 mir-0.067
oster-0.066
 pilot-0.065
Tokencat
Token ID9246
Feature activation+2.75e-01

Pos logit contributions
 subtract+0.097
 subt+0.091
 gigg+0.088
 Jack+0.088
 Luke+0.087
Neg logit contributions
 vet-0.105
 hawk-0.105
 mir-0.104
 wing-0.098
 pilot-0.097
Token"
Token ID1
Feature activation+1.08e+00

Pos logit contributions
 Luke+0.006
 Jack+0.006
 subtract+0.006
 subt+0.006
 gigg+0.006
Neg logit contributions
 vet-0.007
 mir-0.007
 hawk-0.007
 pilot-0.007
oster-0.007
Token and
Token ID290
Feature activation+8.66e-01

Pos logit contributions
 Jack+0.024
 Luke+0.024
 subtract+0.024
 gigg+0.024
 subt+0.023
Neg logit contributions
 hawk-0.030
 mir-0.029
 vet-0.028
oster-0.028
 pilot-0.027
Token the
Token ID262
Feature activation+1.97e+00

Pos logit contributions
igsaw+0.021
 Jack+0.020
 Luke+0.020
 subtract+0.020
 subt+0.020
Neg logit contributions
 vet-0.022
 pilot-0.020
 hawk-0.019
 wing-0.019
 mir-0.018
Token number
Token ID1271
Feature activation+1.98e+00

Pos logit contributions
igsaw+0.053
 Jack+0.053
 Luke+0.052
 gigg+0.052
 subt+0.051
Neg logit contributions
 vet-0.045
 pilot-0.040
 hawk-0.039
 wing-0.038
 doctor-0.037
Token race
Token ID3234
Feature activation+1.61e-01

Pos logit contributions
 subt+0.010
 Luke+0.010
 subtract+0.010
igsaw+0.010
 Jack+0.010
Neg logit contributions
 vet-0.011
 pilot-0.010
 hawk-0.010
 wing-0.010
oster-0.009
Token.
Token ID13
Feature activation+3.61e-02

Pos logit contributions
igsaw+0.004
 subt+0.004
 subtract+0.004
 Luke+0.003
 gigg+0.003
Neg logit contributions
 vet-0.004
 pilot-0.004
 hawk-0.004
 wing-0.004
 or-0.004
Token Billy
Token ID15890
Feature activation+9.79e-01

Pos logit contributions
 Jack+0.001
 Luke+0.001
 subtract+0.001
 subt+0.001
igsaw+0.001
Neg logit contributions
 vet-0.001
 hawk-0.001
 pilot-0.001
 wing-0.001
oster-0.001
Token started
Token ID2067
Feature activation-1.96e-02

Pos logit contributions
igsaw+0.024
 subtract+0.023
 Luke+0.023
 subt+0.023
 Jack+0.022
Neg logit contributions
 vet-0.024
 pilot-0.023
 hawk-0.023
oster-0.022
 wing-0.022
Token counting
Token ID14143
Feature activation+6.72e-01

Pos logit contributions
 vet+0.000
 pilot+0.000
 hawk+0.000
 wing+0.000
 mir+0.000
Neg logit contributions
igsaw-0.001
 Luke-0.000
ksh-0.000
 wrists-0.000
idents-0.000
Token "
Token ID366
Feature activation+4.00e+00

Pos logit contributions
 subtract+0.017
 Luke+0.017
 subt+0.017
igsaw+0.017
 Jack+0.016
Neg logit contributions
 vet-0.016
 hawk-0.015
 pilot-0.015
 wing-0.014
 mir-0.014
Tokenone
Token ID505
Feature activation+1.63e+00

Pos logit contributions
 subtract+0.084
 Jack+0.082
 Luke+0.082
 subt+0.081
 gigg+0.080
Neg logit contributions
 vet-0.114
 hawk-0.109
 pilot-0.107
 mir-0.106
oster-0.106
Token,
Token ID11
Feature activation-1.14e-01

Pos logit contributions
 Luke+0.033
 Jack+0.033
 subt+0.032
 subtract+0.032
igsaw+0.032
Neg logit contributions
 vet-0.047
 hawk-0.045
 pilot-0.044
 wing-0.044
oster-0.044
Token two
Token ID734
Feature activation-4.98e-01

Pos logit contributions
 vet+0.003
 hawk+0.003
oster+0.003
 mir+0.003
 wing+0.003
Neg logit contributions
 Jack-0.002
 subtract-0.002
 Luke-0.002
 subt-0.002
 gigg-0.002
Token,
Token ID11
Feature activation-1.10e-02

Pos logit contributions
 vet+0.014
 pilot+0.013
 hawk+0.013
 wing+0.013
 mir+0.013
Neg logit contributions
 Luke-0.010
 subt-0.010
igsaw-0.010
 subtract-0.010
 Jack-0.010
Token three
Token ID1115
Feature activation-1.18e+00

Pos logit contributions
 vet+0.000
 hawk+0.000
oster+0.000
 mir+0.000
 wing+0.000
Neg logit contributions
 subtract-0.000
 Jack-0.000
 Luke-0.000
 subt-0.000
 gigg-0.000
Token twist
Token ID14528
Feature activation+1.51e+00

Pos logit contributions
 Jack+0.019
 subtract+0.019
 Luke+0.018
 gigg+0.018
 subt+0.018
Neg logit contributions
 vet-0.025
 hawk-0.024
oster-0.024
 mir-0.024
 pilot-0.024
Token and
Token ID290
Feature activation+1.81e+00

Pos logit contributions
 Jack+0.035
 Luke+0.035
 gigg+0.034
 subtract+0.034
 subt+0.034
Neg logit contributions
 vet-0.041
 hawk-0.038
oster-0.038
 mir-0.038
 pilot-0.037
Token turn
Token ID1210
Feature activation+2.12e+00

Pos logit contributions
igsaw+0.047
 batch+0.043
 Luke+0.042
ksh+0.042
 subt+0.042
Neg logit contributions
 vet-0.044
 pilot-0.042
 wing-0.042
 hawk-0.039
 doctor-0.037
Token the
Token ID262
Feature activation+1.26e+00

Pos logit contributions
 subtract+0.050
igsaw+0.050
 Luke+0.050
 subt+0.050
 wrists+0.049
Neg logit contributions
 vet-0.051
 hawk-0.049
 pilot-0.049
 wing-0.048
 mir-0.047
Token toy
Token ID13373
Feature activation+2.44e+00

Pos logit contributions
 subtract+0.029
 Jack+0.029
 Luke+0.028
 gigg+0.028
 subt+0.028
Neg logit contributions
 vet-0.033
oster-0.031
 mir-0.031
 hawk-0.031
 pilot-0.030
Token all
Token ID477
Feature activation+3.98e+00

Pos logit contributions
 Jack+0.050
 subtract+0.049
 Luke+0.049
 gigg+0.047
 subt+0.046
Neg logit contributions
 vet-0.072
 hawk-0.069
 mir-0.069
oster-0.069
 pilot-0.066
Token day
Token ID1110
Feature activation+1.74e+00

Pos logit contributions
 wrists+0.104
 subt+0.100
 hips+0.100
igsaw+0.098
 Luke+0.098
Neg logit contributions
 pilot-0.080
 wing-0.079
 or-0.078
 vet-0.077
ull-0.075
Token long
Token ID890
Feature activation+1.19e+00

Pos logit contributions
 subtract+0.039
 subt+0.039
igsaw+0.038
irms+0.038
ci+0.038
Neg logit contributions
 vet-0.044
 wing-0.041
 hawk-0.041
 mir-0.041
 pilot-0.040
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
 subtract+0.021
 Luke+0.021
 Jack+0.021
 subt+0.021
igsaw+0.021
Neg logit contributions
 vet-0.037
 hawk-0.035
 pilot-0.035
 mir-0.034
oster-0.034
Token
Token ID198
Feature activation+1.07e+00

Pos logit contributions
ci+0.039
 gigg+0.038
 wrists+0.038
igsaw+0.038
 subt+0.037
Neg logit contributions
 vet-0.034
oster-0.027
 doctor-0.027
 hawk-0.026
 veterinarian-0.026
Token
Token ID198
Feature activation+1.47e-02

Pos logit contributions
 subtract+0.024
 Luke+0.024
 Jack+0.024
 subt+0.024
 gigg+0.023
Neg logit contributions
 vet-0.029
 hawk-0.027
 pilot-0.027
oster-0.026
 mir-0.026
Token said
Token ID531
Feature activation-1.45e-02

Pos logit contributions
 Luke+0.010
 Jack+0.010
 subtract+0.010
 gigg+0.010
 subt+0.010
Neg logit contributions
 vet-0.017
 hawk-0.017
 pilot-0.016
 mir-0.016
oster-0.016
Token yes
Token ID3763
Feature activation+9.52e-01

Pos logit contributions
 vet+0.000
 hawk+0.000
 mir+0.000
 pilot+0.000
oster+0.000
Neg logit contributions
 Jack-0.000
 Luke-0.000
 subtract-0.000
 subt-0.000
 gigg-0.000
Token,
Token ID11
Feature activation+1.87e-01

Pos logit contributions
 subt+0.027
 subtract+0.027
igsaw+0.027
 Luke+0.026
 wrists+0.026
Neg logit contributions
 vet-0.020
 pilot-0.018
 wing-0.018
 hawk-0.018
oster-0.017
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
 Jack+0.004
 Luke+0.004
 subtract+0.004
 gigg+0.004
 subt+0.004
Neg logit contributions
 vet-0.005
 hawk-0.005
oster-0.005
 pilot-0.005
 mir-0.005
Token they
Token ID484
Feature activation+3.47e+00

Pos logit contributions
igsaw+0.029
 hips+0.028
 wrists+0.028
 subtract+0.028
irms+0.028
Neg logit contributions
 vet-0.042
 pilot-0.039
 hawk-0.038
 wing-0.038
 mir-0.037
Token all
Token ID477
Feature activation+3.98e+00

Pos logit contributions
igsaw+0.083
irms+0.079
 hips+0.079
idents+0.077
 subt+0.075
Neg logit contributions
 pilot-0.088
 vet-0.083
 captain-0.078
oster-0.078
 wing-0.076
Token got
Token ID1392
Feature activation+2.88e+00

Pos logit contributions
 hips+0.109
idents+0.107
igsaw+0.105
irms+0.102
 subtract+0.100
Neg logit contributions
 pilot-0.085
 vet-0.077
ull-0.077
oster-0.076
 wing-0.074
Token to
Token ID284
Feature activation+2.07e+00

Pos logit contributions
igsaw+0.072
 hips+0.068
ci+0.068
liv+0.066
irms+0.065
Neg logit contributions
 vet-0.067
 pilot-0.064
 doctor-0.062
 or-0.059
 fire-0.059
Token work
Token ID670
Feature activation+2.49e+00

Pos logit contributions
ksh+0.062
ci+0.059
hetically+0.057
lers+0.056
 coff+0.055
Neg logit contributions
 vet-0.042
 pilot-0.039
 doctor-0.037
 or-0.034
 mechanic-0.034
Token!
Token ID0
Feature activation+1.52e+00

Pos logit contributions
 wrists+0.052
irms+0.051
ksh+0.050
 subtract+0.050
 gigg+0.049
Neg logit contributions
 or-0.062
 vet-0.059
 pilot-0.057
 wing-0.055
 fire-0.055
Token All
Token ID1439
Feature activation+3.73e+00

Pos logit contributions
ci+0.038
 gigg+0.037
 wrists+0.037
rob+0.035
 forth+0.035
Neg logit contributions
 vet-0.036
oral-0.030
 doctor-0.030
ull-0.029
 wing-0.029
Token had
Token ID550
Feature activation-4.08e-02

Pos logit contributions
 vet+0.015
oster+0.014
 hawk+0.014
 wing+0.014
 mir+0.014
Neg logit contributions
 subt-0.012
 subtract-0.012
igsaw-0.011
 Luke-0.011
 Jack-0.011
Token to
Token ID284
Feature activation-8.12e-01

Pos logit contributions
 vet+0.001
 hawk+0.001
oster+0.001
 pilot+0.001
 mir+0.001
Neg logit contributions
 Jack-0.001
 Luke-0.001
 subtract-0.001
 gigg-0.001
 subt-0.001
Token use
Token ID779
Feature activation+6.65e-01

Pos logit contributions
 vet+0.022
 hawk+0.021
 pilot+0.020
 mir+0.020
oster+0.020
Neg logit contributions
 Jack-0.018
 Luke-0.018
 subtract-0.018
 gigg-0.018
 subt-0.018
Token the
Token ID262
Feature activation+7.18e-01

Pos logit contributions
 Luke+0.015
 subtract+0.015
 Jack+0.015
 subt+0.015
 gigg+0.015
Neg logit contributions
 vet-0.017
 hawk-0.016
 pilot-0.016
 wing-0.016
 mir-0.016
Token words
Token ID2456
Feature activation+1.05e+00

Pos logit contributions
 Jack+0.016
 subtract+0.016
 Luke+0.016
 subt+0.016
igsaw+0.016
Neg logit contributions
 vet-0.019
 hawk-0.018
oster-0.018
 mir-0.018
 pilot-0.018
Token '
Token ID705
Feature activation+3.97e+00

Pos logit contributions
 Jack+0.021
 Luke+0.021
 subtract+0.020
 gigg+0.019
 James+0.019
Neg logit contributions
 vet-0.033
 hawk-0.032
 mir-0.031
oster-0.031
 pilot-0.030
TokenPlease
Token ID5492
Feature activation-4.56e-02

Pos logit contributions
 Luke+0.089
 Jack+0.089
 subtract+0.088
 subt+0.087
 gigg+0.086
Neg logit contributions
 vet-0.106
 hawk-0.100
 pilot-0.099
oster-0.098
 mir-0.097
Token'
Token ID6
Feature activation+1.24e+00

Pos logit contributions
 vet+0.001
 hawk+0.001
 mir+0.001
 pilot+0.001
oster+0.001
Neg logit contributions
 Jack-0.001
 subtract-0.001
 Luke-0.001
 subt-0.001
 gigg-0.001
Token and
Token ID290
Feature activation+5.63e-01

Pos logit contributions
 Jack+0.028
 subtract+0.028
 Luke+0.027
 subt+0.027
 gigg+0.025
Neg logit contributions
 vet-0.033
 hawk-0.033
 mir-0.033
oster-0.032
 pilot-0.032
Token '
Token ID705
Feature activation+3.22e+00

Pos logit contributions
 Jack+0.012
 Luke+0.012
 subtract+0.012
 subt+0.012
 gigg+0.012
Neg logit contributions
 vet-0.015
 hawk-0.015
 mir-0.015
oster-0.015
 pilot-0.014
TokenThank
Token ID10449
Feature activation+1.07e+00

Pos logit contributions
 subtract+0.077
 Luke+0.076
 Jack+0.076
 subt+0.075
 gigg+0.074
Neg logit contributions
 vet-0.082
 hawk-0.077
 pilot-0.076
 mir-0.075
oster-0.075
Token,
Token ID11
Feature activation+4.25e-01

Pos logit contributions
 Jack+0.018
 Luke+0.017
 subtract+0.016
 gigg+0.016
 subt+0.016
Neg logit contributions
 vet-0.026
 hawk-0.025
oster-0.024
 pilot-0.024
 mir-0.024
Token he
Token ID339
Feature activation+1.57e+00

Pos logit contributions
 subtract+0.010
 subt+0.010
 wrists+0.009
igsaw+0.009
 gigg+0.009
Neg logit contributions
 vet-0.011
 hawk-0.010
 pilot-0.010
 mir-0.010
 wing-0.010
Token wrote
Token ID2630
Feature activation-4.86e-01

Pos logit contributions
 Jack+0.034
 Luke+0.034
 gigg+0.033
 subtract+0.033
 subt+0.032
Neg logit contributions
 vet-0.045
 hawk-0.045
 mir-0.042
oster-0.042
 wing-0.042
Token the
Token ID262
Feature activation+1.83e+00

Pos logit contributions
 vet+0.013
 hawk+0.013
 mir+0.012
 pilot+0.012
oster+0.012
Neg logit contributions
 Luke-0.011
 Jack-0.011
 subtract-0.011
 gigg-0.011
 subt-0.011
Token letter
Token ID3850
Feature activation+1.72e+00

Pos logit contributions
 Luke+0.043
 subtract+0.043
 Jack+0.043
 subt+0.042
 gigg+0.042
Neg logit contributions
 vet-0.047
 hawk-0.045
 pilot-0.044
 mir-0.043
oster-0.043
Token '
Token ID705
Feature activation+3.96e+00

Pos logit contributions
 Jack+0.040
 Luke+0.040
 subtract+0.039
 subt+0.038
 gigg+0.038
Neg logit contributions
 vet-0.046
 hawk-0.045
 mir-0.043
oster-0.043
 pilot-0.042
TokenM
Token ID44
Feature activation+2.07e-01

Pos logit contributions
 subtract+0.092
 Jack+0.089
 subt+0.089
 Luke+0.088
igsaw+0.087
Neg logit contributions
 vet-0.108
 hawk-0.105
 mir-0.101
 wing-0.100
 pilot-0.098
Token'
Token ID6
Feature activation+2.20e+00

Pos logit contributions
igsaw+0.004
 subtract+0.004
 subt+0.004
 Jack+0.004
 Luke+0.003
Neg logit contributions
 hawk-0.007
 vet-0.006
 pilot-0.006
 wing-0.006
oster-0.006
Token with
Token ID351
Feature activation+1.33e+00

Pos logit contributions
 subtract+0.049
 Jack+0.048
 Luke+0.047
 subt+0.047
 James+0.044
Neg logit contributions
 hawk-0.066
 vet-0.064
oster-0.062
 mir-0.061
 wing-0.058
Token his
Token ID465
Feature activation+2.03e+00

Pos logit contributions
 subt+0.032
 subtract+0.032
igsaw+0.032
 gigg+0.032
 hips+0.032
Neg logit contributions
 vet-0.032
 pilot-0.030
 wing-0.029
 hawk-0.029
 mir-0.029
Token special
Token ID2041
Feature activation+1.37e+00

Pos logit contributions
 subt+0.043
 subtract+0.043
igsaw+0.042
 Luke+0.042
 Jack+0.042
Neg logit contributions
 vet-0.055
 pilot-0.053
 wing-0.052
 hawk-0.051
 mir-0.050
Token.
Token ID13
Feature activation+6.62e-01

Pos logit contributions
 Jack+0.023
 Luke+0.023
 subtract+0.023
 gigg+0.022
 subt+0.022
Neg logit contributions
 vet-0.048
 hawk-0.046
 pilot-0.045
 mir-0.045
oster-0.045
Token Tim
Token ID5045
Feature activation+1.15e+00

Pos logit contributions
 subt+0.017
 gigg+0.016
 wrists+0.016
igsaw+0.016
 Luke+0.016
Neg logit contributions
 vet-0.017
 mir-0.014
 hawk-0.014
 pilot-0.014
 wing-0.014
Token would
Token ID561
Feature activation+5.98e-01

Pos logit contributions
 Luke+0.026
 subtract+0.026
 Jack+0.026
 subt+0.026
igsaw+0.025
Neg logit contributions
 vet-0.031
 hawk-0.029
 pilot-0.029
oster-0.028
 mir-0.028
Token spin
Token ID7906
Feature activation+1.27e+00

Pos logit contributions
 Jack+0.013
 Luke+0.013
 subtract+0.013
 gigg+0.012
 subt+0.012
Neg logit contributions
 vet-0.017
 hawk-0.016
 pilot-0.016
oster-0.016
 mir-0.016
Token the
Token ID262
Feature activation+2.64e+00

Pos logit contributions
 subtract+0.031
 subt+0.030
igsaw+0.030
 Luke+0.029
 wrists+0.029
Neg logit contributions
 vet-0.031
 pilot-0.030
 hawk-0.030
oster-0.029
 wing-0.029
Token top
Token ID1353
Feature activation+3.96e+00

Pos logit contributions
 subt+0.069
 Luke+0.069
 Jack+0.068
 subtract+0.068
igsaw+0.066
Neg logit contributions
 vet-0.061
 hawk-0.059
 pilot-0.058
 wing-0.056
oster-0.055
Token every
Token ID790
Feature activation+3.29e+00

Pos logit contributions
 Luke+0.096
 subtract+0.096
 Jack+0.095
 subt+0.095
igsaw+0.093
Neg logit contributions
 vet-0.098
 hawk-0.092
 pilot-0.092
 wing-0.090
oster-0.090
Token day
Token ID1110
Feature activation+2.20e+00

Pos logit contributions
 Jack+0.067
 Luke+0.066
 subtract+0.064
 gigg+0.064
igsaw+0.064
Neg logit contributions
 vet-0.096
 hawk-0.090
 mir-0.090
oster-0.089
 pilot-0.089
Token and
Token ID290
Feature activation+1.68e+00

Pos logit contributions
igsaw+0.058
 subt+0.058
 subtract+0.057
 wrists+0.055
 Luke+0.055
Neg logit contributions
 vet-0.049
 pilot-0.047
 wing-0.046
 hawk-0.044
 or-0.044
Token watch
Token ID2342
Feature activation+2.07e+00

Pos logit contributions
igsaw+0.046
ksh+0.041
 batch+0.040
 subt+0.040
 Luke+0.040
Neg logit contributions
 pilot-0.039
 vet-0.039
 wing-0.036
 hawk-0.035
 doctor-0.034
Token it
Token ID340
Feature activation+3.01e+00

Pos logit contributions
 Luke+0.048
 subtract+0.048
 subt+0.047
 Jack+0.047
igsaw+0.047
Neg logit contributions
 vet-0.054
 pilot-0.051
 hawk-0.050
 wing-0.049
 mir-0.049
TokenOne
Token ID3198
Feature activation-1.35e+00

Pos logit contributions
 wing+0.048
 mir+0.044
 hawk+0.044
 pilot+0.043
 vet+0.042
Neg logit contributions
 -0.026
 Jack-0.025
 Luke-0.025
 subtract-0.023
 gigg-0.023
Token day
Token ID1110
Feature activation-4.84e-01

Pos logit contributions
 vet+0.046
 hawk+0.045
 pilot+0.044
 wing+0.043
oster+0.042
Neg logit contributions
 Jack-0.022
 gigg-0.019
 g-0.019
 Luke-0.019
igsaw-0.018
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
 vet+0.018
oster+0.017
 pilot+0.017
 mir+0.017
 hawk+0.016
Neg logit contributions
 Jack-0.008
 Luke-0.007
 gigg-0.007
 hands-0.006
 -0.006
Token the
Token ID262
Feature activation-2.50e+00

Pos logit contributions
 vet+0.042
 mir+0.040
oster+0.040
 pilot+0.039
 wing+0.039
Neg logit contributions
 Jack-0.025
 Luke-0.022
 gigg-0.021
 -0.020
 hands-0.020
Token b
Token ID275
Feature activation-3.48e+00

Pos logit contributions
reetings+0.072
oster+0.072
 vet+0.070
ull+0.069
 hawk+0.068
Neg logit contributions
 gigg-0.049
 hands-0.046
 g-0.046
 Jack-0.046
 shoulders-0.044
Tokenunn
Token ID20935
Feature activation-5.27e+00

Pos logit contributions
 vet+0.117
 pilot+0.113
 hawk+0.113
oster+0.107
 wing+0.106
Neg logit contributions
 gigg-0.048
 hands-0.046
 Jack-0.046
igsaw-0.045
irms-0.042
Tokenies
Token ID444
Feature activation-2.20e+00

Pos logit contributions
 vet+0.162
 hawk+0.153
 pilot+0.149
oster+0.146
 mir+0.145
Neg logit contributions
 gigg-0.098
 Jack-0.097
 hands-0.092
 Luke-0.090
ci-0.089
Token happened
Token ID3022
Feature activation-1.54e+00

Pos logit contributions
 vet+0.075
oster+0.073
Santa+0.071
 mir+0.071
 hawk+0.070
Neg logit contributions
 Jack-0.038
 gigg-0.037
 laughed-0.031
 -0.031
hed-0.030
Token across
Token ID1973
Feature activation-1.43e+00

Pos logit contributions
 vet+0.043
 hawk+0.042
oster+0.041
 pilot+0.041
 mir+0.040
Neg logit contributions
 Jack-0.033
 Luke-0.033
 gigg-0.033
 subtract-0.032
 hips-0.031
Token an
Token ID281
Feature activation-3.92e-01

Pos logit contributions
oster+0.048
 pilot+0.048
 vet+0.047
 hawk+0.045
 mir+0.045
Neg logit contributions
 Jack-0.026
 Luke-0.022
 -0.021
 gigg-0.021
 hands-0.020
Token elderly
Token ID13830
Feature activation-2.58e+00

Pos logit contributions
oster+0.010
 vet+0.010
reetings+0.010
Will+0.010
God+0.010
Neg logit contributions
 Jack-0.008
 gigg-0.008
 shoulders-0.008
igsaw-0.007
 g-0.007
Token with
Token ID351
Feature activation+7.34e-02

Pos logit contributions
 vet+0.000
 hawk+0.000
 mir+0.000
 pilot+0.000
oster+0.000
Neg logit contributions
 Jack-0.000
 Luke-0.000
 gigg-0.000
 subtract-0.000
igsaw-0.000
Token."
Token ID526
Feature activation+4.06e-01

Pos logit contributions
 Jack+0.002
 Luke+0.001
 gigg+0.001
 subtract+0.001
 hips+0.001
Neg logit contributions
 vet-0.002
 pilot-0.002
 hawk-0.002
 mir-0.002
oster-0.002
Token
Token ID198
Feature activation-6.63e-01

Pos logit contributions
 subtract+0.011
 subt+0.010
igsaw+0.010
 Luke+0.010
 gigg+0.010
Neg logit contributions
 vet-0.010
 hawk-0.009
 wing-0.008
 pilot-0.008
oster-0.008
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
 vet+0.018
 hawk+0.017
 pilot+0.017
oster+0.016
 mir+0.016
Neg logit contributions
 Luke-0.015
 subtract-0.015
 Jack-0.015
 subt-0.015
 gigg-0.014
TokenThe
Token ID464
Feature activation-2.99e+00

Pos logit contributions
 mir+0.027
 wing+0.026
 hawk+0.026
 pilot+0.025
 vet+0.025
Neg logit contributions
 subtract-0.033
 Luke-0.032
 subt-0.032
 gigg-0.030
 -0.030
Token kind
Token ID1611
Feature activation-5.18e+00

Pos logit contributions
ull+0.056
 mir+0.054
 vet+0.054
oster+0.053
 wing+0.052
Neg logit contributions
 gigg-0.083
 shoulders-0.078
 g-0.078
 Luke-0.077
 wrists-0.077
Token sheep
Token ID15900
Feature activation-6.86e-01

Pos logit contributions
oster+0.103
 mir+0.103
 vet+0.101
reetings+0.098
 wing+0.097
Neg logit contributions
 gigg-0.128
 Jack-0.127
 hands-0.122
 shoulders-0.121
 -0.118
Token said
Token ID531
Feature activation-9.61e-01

Pos logit contributions
 vet+0.022
 mir+0.021
 hawk+0.021
 pilot+0.021
 wing+0.020
Neg logit contributions
 gigg-0.012
 Jack-0.012
 Luke-0.012
 subtract-0.011
 hips-0.011
Token,
Token ID11
Feature activation-5.83e-01

Pos logit contributions
 vet+0.030
 hawk+0.029
 mir+0.029
 pilot+0.028
oster+0.028
Neg logit contributions
 Jack-0.018
 Luke-0.018
 gigg-0.017
 subtract-0.017
 hips-0.016
Token "
Token ID366
Feature activation+1.48e-01

Pos logit contributions
 vet+0.019
 hawk+0.019
 mir+0.019
 pilot+0.019
oster+0.019
Neg logit contributions
 Jack-0.010
 -0.010
 gigg-0.009
 Luke-0.009
 subtract-0.009
TokenI
Token ID40
Feature activation-1.62e+00

Pos logit contributions
 subtract+0.003
 Luke+0.003
 Jack+0.003
 subt+0.003
 gigg+0.003
Neg logit contributions
 vet-0.004
 hawk-0.004
 mir-0.004
 pilot-0.004
 wing-0.004
Token.
Token ID13
Feature activation-4.76e-02

Pos logit contributions
 vet+0.017
 hawk+0.016
 pilot+0.016
oster+0.016
 mir+0.016
Neg logit contributions
 Jack-0.014
 Luke-0.013
 gigg-0.013
 hips-0.013
 subtract-0.012
Token
Token ID198
Feature activation-1.50e-01

Pos logit contributions
 vet+0.001
oster+0.001
 hawk+0.001
 mir+0.001
 wing+0.001
Neg logit contributions
 subtract-0.001
 subt-0.001
 gigg-0.001
 wrists-0.001
 hips-0.001
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 vet+0.004
 hawk+0.004
 pilot+0.004
 mir+0.004
 wing+0.004
Neg logit contributions
 Jack-0.003
 Luke-0.003
 subtract-0.003
 gigg-0.003
 subt-0.003
TokenThe
Token ID464
Feature activation-1.43e+00

Pos logit contributions
 wing+0.033
 hawk+0.032
 mir+0.031
 pilot+0.031
 vet+0.030
Neg logit contributions
 subtract-0.033
 Luke-0.033
 subt-0.032
 Jack-0.032
 gigg-0.032
Token b
Token ID275
Feature activation-3.20e+00

Pos logit contributions
oster+0.034
 vet+0.033
 hawk+0.033
 mir+0.032
 pilot+0.031
Neg logit contributions
 Jack-0.035
 gigg-0.034
 Luke-0.033
 subt-0.033
 subtract-0.032
Tokenunn
Token ID20935
Feature activation-5.01e+00

Pos logit contributions
 vet+0.109
 pilot+0.106
 hawk+0.106
 mir+0.101
 wing+0.099
Neg logit contributions
 gigg-0.043
igsaw-0.041
 Jack-0.041
 hands-0.040
 subtract-0.038
Tokenies
Token ID444
Feature activation-5.95e-01

Pos logit contributions
 vet+0.159
 hawk+0.150
 pilot+0.146
 mir+0.144
oster+0.142
Neg logit contributions
 gigg-0.090
 Jack-0.087
 hands-0.084
 Luke-0.081
ci-0.080
Token showed
Token ID3751
Feature activation-5.56e-01

Pos logit contributions
 vet+0.020
 mir+0.020
 hawk+0.019
 vaccine+0.018
oster+0.018
Neg logit contributions
 gigg-0.011
 Jack-0.010
 laughed-0.010
 g-0.009
 Luke-0.009
Token the
Token ID262
Feature activation-2.11e+00

Pos logit contributions
 vet+0.014
 hawk+0.013
 pilot+0.013
 wing+0.013
oster+0.012
Neg logit contributions
 subtract-0.014
 subt-0.014
igsaw-0.013
 hips-0.013
 Luke-0.013
Token elderly
Token ID13830
Feature activation-3.35e+00

Pos logit contributions
oster+0.050
 vet+0.050
 pilot+0.047
 hawk+0.047
 mir+0.046
Neg logit contributions
 gigg-0.053
 Jack-0.053
 shoulders-0.050
 Luke-0.049
 hands-0.049
Token rabbit
Token ID22746
Feature activation-1.32e+00

Pos logit contributions
 vet+0.059
 hawk+0.055
 pilot+0.053
oster+0.052
 mir+0.052
Neg logit contributions
 Luke-0.106
 Jack-0.106
 subtract-0.106
 subt-0.104
 gigg-0.104
Token lonely
Token ID21757
Feature activation-7.43e-01

Pos logit contributions
 vet+0.015
 hawk+0.015
 pilot+0.014
oster+0.014
 mir+0.014
Neg logit contributions
 Jack-0.012
 gigg-0.012
 Luke-0.012
 subtract-0.012
 subt-0.011
Token.
Token ID13
Feature activation-2.82e-02

Pos logit contributions
 vet+0.024
 hawk+0.023
 pilot+0.023
oster+0.023
 mir+0.023
Neg logit contributions
 Jack-0.012
 Luke-0.012
 subtract-0.012
 gigg-0.012
 subt-0.012
Token
Token ID198
Feature activation-3.44e-01

Pos logit contributions
 vet+0.001
 hawk+0.001
 pilot+0.001
oster+0.001
 mir+0.001
Neg logit contributions
 subtract-0.001
 subt-0.001
 Luke-0.001
 gigg-0.001
igsaw-0.001
Token
Token ID198
Feature activation-9.80e-01

Pos logit contributions
 vet+0.010
 hawk+0.009
 pilot+0.009
 mir+0.009
 wing+0.009
Neg logit contributions
 Jack-0.007
 Luke-0.007
 subtract-0.007
 subt-0.007
 gigg-0.007
TokenThe
Token ID464
Feature activation-2.74e+00

Pos logit contributions
 wing+0.019
 mir+0.018
 pilot+0.018
 hawk+0.018
 vet+0.018
Neg logit contributions
 Luke-0.029
 subtract-0.029
 Jack-0.028
 subt-0.028
igsaw-0.027
Token kind
Token ID1611
Feature activation-5.01e+00

Pos logit contributions
ull+0.043
oster+0.040
 mir+0.040
 vet+0.038
 wing+0.038
Neg logit contributions
 gigg-0.085
 Jack-0.081
 shoulders-0.081
 Luke-0.080
 wrists-0.080
Token sheep
Token ID15900
Feature activation-1.78e+00

Pos logit contributions
 mir+0.093
oster+0.092
 vet+0.088
reetings+0.087
 wing+0.087
Neg logit contributions
 Jack-0.134
 gigg-0.131
 hands-0.126
 shoulders-0.125
 Luke-0.124
Token asked
Token ID1965
Feature activation-5.38e-01

Pos logit contributions
 mir+0.058
 vet+0.055
 hawk+0.055
oster+0.054
reetings+0.054
Neg logit contributions
 gigg-0.032
 Jack-0.031
 -0.028
 Luke-0.027
 laughed-0.027
Token,
Token ID11
Feature activation-7.60e-01

Pos logit contributions
 vet+0.017
 hawk+0.016
 mir+0.016
oster+0.016
 wing+0.016
Neg logit contributions
 Jack-0.011
 Luke-0.010
 gigg-0.009
 James-0.009
 subtract-0.009
Token "
Token ID366
Feature activation-6.42e-01

Pos logit contributions
oster+0.027
 hawk+0.026
 mir+0.026
 vet+0.026
 pilot+0.026
Neg logit contributions
 Jack-0.013
 -0.012
 Luke-0.011
 gigg-0.011
 subtract-0.010
TokenCan
Token ID6090
Feature activation-4.89e-01

Pos logit contributions
 mir+0.018
 wing+0.017
oster+0.017
 pilot+0.016
 hawk+0.016
Neg logit contributions
 gigg-0.013
 Jack-0.012
 Luke-0.012
 subtract-0.012
ci-0.011
Token toast
Token ID27805
Feature activation-6.81e-01

Pos logit contributions
 vet+0.021
oster+0.021
 hawk+0.021
 pilot+0.020
 mir+0.020
Neg logit contributions
 Jack-0.017
 Luke-0.015
 gigg-0.015
 subtract-0.015
 James-0.014
Token?
Token ID30
Feature activation+2.95e-01

Pos logit contributions
 vet+0.022
 hawk+0.021
 pilot+0.021
oster+0.021
 mir+0.020
Neg logit contributions
 Jack-0.012
 Luke-0.012
 subtract-0.011
 gigg-0.011
 subt-0.011
Token
Token ID198
Feature activation+7.89e-02

Pos logit contributions
 Jack+0.006
 Luke+0.006
 subtract+0.006
 subt+0.006
igsaw+0.005
Neg logit contributions
 vet-0.009
 hawk-0.009
 mir-0.008
 pilot-0.008
oster-0.008
Token
Token ID198
Feature activation-5.67e-01

Pos logit contributions
 Jack+0.002
 Luke+0.002
 subtract+0.002
 subt+0.002
 gigg+0.002
Neg logit contributions
 vet-0.002
 hawk-0.002
 pilot-0.002
 mir-0.002
 wing-0.002
TokenThe
Token ID464
Feature activation-2.91e+00

Pos logit contributions
 wing+0.012
 mir+0.012
 hawk+0.012
 pilot+0.012
 vet+0.011
Neg logit contributions
 Luke-0.016
 Jack-0.016
 subtract-0.016
 subt-0.015
 -0.015
Token c
Token ID269
Feature activation-5.00e+00

Pos logit contributions
ull+0.063
 pilot+0.060
bul+0.059
 mir+0.058
 hawk+0.058
Neg logit contributions
 gigg-0.074
 g-0.065
 laughs-0.064
 cries-0.063
 hands-0.062
Tokenrows
Token ID8516
Feature activation-1.05e+00

Pos logit contributions
 pilot+0.128
 hawk+0.128
 vet+0.127
 wing+0.120
 mir+0.120
Neg logit contributions
 gigg-0.103
igsaw-0.097
idents-0.094
zy-0.093
ops-0.092
Token happily
Token ID18177
Feature activation-4.16e-01

Pos logit contributions
 vet+0.036
 mir+0.034
 hawk+0.032
 vaccine+0.032
oster+0.031
Neg logit contributions
 gigg-0.020
 Jack-0.018
 g-0.018
 laughed-0.017
 -0.017
Token ate
Token ID15063
Feature activation-7.90e-01

Pos logit contributions
 vet+0.013
 hawk+0.012
 pilot+0.012
 mir+0.012
oster+0.012
Neg logit contributions
 gigg-0.008
 Jack-0.008
 Luke-0.008
 subtract-0.007
 subt-0.007
Token the
Token ID262
Feature activation+1.79e-02

Pos logit contributions
 vet+0.023
 pilot+0.023
 hawk+0.022
oster+0.022
 mir+0.022
Neg logit contributions
 Jack-0.017
 Luke-0.016
 gigg-0.016
 subtract-0.015
 g-0.014
Token toast
Token ID27805
Feature activation+4.44e-01

Pos logit contributions
 Luke+0.000
 Jack+0.000
 subtract+0.000
 subt+0.000
 gigg+0.000
Neg logit contributions
 vet-0.001
 hawk-0.001
 pilot-0.001
oster-0.001
 mir-0.001
Token all
Token ID477
Feature activation+1.43e+00

Pos logit contributions
 Jack+0.004
 gigg+0.004
 Luke+0.004
 subtract+0.004
 subt+0.003
Neg logit contributions
 vet-0.006
 hawk-0.006
oster-0.005
 mir-0.005
 pilot-0.005
Token knew
Token ID2993
Feature activation-1.71e+00

Pos logit contributions
 subtract+0.031
igsaw+0.030
 Luke+0.030
 subt+0.030
 hips+0.029
Neg logit contributions
 vet-0.040
 hawk-0.038
 pilot-0.038
oster-0.038
 mir-0.038
Token that
Token ID326
Feature activation+4.89e-02

Pos logit contributions
oster+0.056
 vet+0.054
 hawk+0.053
 pilot+0.052
 mir+0.052
Neg logit contributions
 Jack-0.033
 Luke-0.030
 gigg-0.029
 James-0.028
 Alex-0.027
Token the
Token ID262
Feature activation-2.16e+00

Pos logit contributions
 Jack+0.001
 Luke+0.001
 gigg+0.001
 subtract+0.001
 subt+0.001
Neg logit contributions
 vet-0.001
oster-0.001
 hawk-0.001
 pilot-0.001
 mir-0.001
Token b
Token ID275
Feature activation-3.63e+00

Pos logit contributions
oster+0.055
 vet+0.054
ull+0.052
 pilot+0.052
 hawk+0.052
Neg logit contributions
 gigg-0.049
 g-0.046
 Jack-0.045
 shoulders-0.045
 wrists-0.045
Tokenunn
Token ID20935
Feature activation-4.99e+00

Pos logit contributions
 vet+0.114
 pilot+0.110
 hawk+0.109
oster+0.105
 mir+0.105
Neg logit contributions
 gigg-0.062
 Jack-0.060
igsaw-0.060
 subtract-0.060
 subt-0.058
Tokenies
Token ID444
Feature activation-2.21e+00

Pos logit contributions
 vet+0.143
 hawk+0.135
 pilot+0.133
oster+0.130
 mir+0.130
Neg logit contributions
 Jack-0.103
 gigg-0.103
 Luke-0.099
 subtract-0.098
 hips-0.096
Token were
Token ID547
Feature activation-9.27e-01

Pos logit contributions
 vet+0.066
 hawk+0.062
oster+0.060
 mir+0.060
 pilot+0.059
Neg logit contributions
 Jack-0.047
 gigg-0.047
 Luke-0.043
 g-0.043
 laughs-0.042
Token having
Token ID1719
Feature activation-6.24e-01

Pos logit contributions
 vet+0.026
oster+0.025
 hawk+0.025
 pilot+0.025
oral+0.024
Neg logit contributions
 Jack-0.021
 gigg-0.020
 Luke-0.019
 James-0.018
 hips-0.018
Token a
Token ID257
Feature activation+3.39e-01

Pos logit contributions
 vet+0.017
 hawk+0.016
 mir+0.016
 wing+0.016
 pilot+0.016
Neg logit contributions
 subtract-0.013
 Luke-0.013
igsaw-0.013
 subt-0.013
 Jack-0.013
Token very
Token ID845
Feature activation-1.23e+00

Pos logit contributions
 Jack+0.007
 gigg+0.007
 Luke+0.006
 subtract+0.006
igsaw+0.006
Neg logit contributions
 vet-0.010
 hawk-0.010
 pilot-0.009
oster-0.009
 wing-0.009
Token please
Token ID3387
Feature activation-9.93e-01

Pos logit contributions
oster+0.052
 vet+0.050
oral+0.048
 mir+0.048
 wing+0.047
Neg logit contributions
 Jack-0.037
 Luke-0.033
 g-0.030
 gigg-0.030
 Alex-0.030
Token!"
Token ID2474
Feature activation+1.14e-01

Pos logit contributions
 vet+0.030
 hawk+0.029
 pilot+0.029
 mir+0.029
oster+0.028
Neg logit contributions
 Jack-0.019
 Luke-0.019
 subtract-0.018
 gigg-0.018
 hips-0.017
Token
Token ID198
Feature activation-8.74e-01

Pos logit contributions
 subtract+0.003
 Luke+0.003
 subt+0.002
 Jack+0.002
igsaw+0.002
Neg logit contributions
 vet-0.003
 hawk-0.003
 pilot-0.003
oster-0.003
 wing-0.003
Token
Token ID198
Feature activation-1.42e+00

Pos logit contributions
 vet+0.024
 hawk+0.023
 pilot+0.023
 mir+0.022
oster+0.022
Neg logit contributions
 Luke-0.019
 Jack-0.019
 subtract-0.019
 subt-0.019
 gigg-0.018
TokenThe
Token ID464
Feature activation-2.86e+00

Pos logit contributions
 wing+0.030
 mir+0.030
 hawk+0.029
 pilot+0.029
 vet+0.028
Neg logit contributions
 subtract-0.039
 subt-0.038
 Luke-0.038
 gigg-0.037
 -0.036
Token kind
Token ID1611
Feature activation-4.93e+00

Pos logit contributions
ull+0.050
 mir+0.048
oster+0.048
 vet+0.047
 wing+0.045
Neg logit contributions
 gigg-0.084
 shoulders-0.081
 wrists-0.081
 g-0.079
 Luke-0.079
Token sheep
Token ID15900
Feature activation-8.50e-01

Pos logit contributions
oster+0.093
 mir+0.091
 vet+0.090
 wing+0.087
reetings+0.085
Neg logit contributions
 Jack-0.133
 gigg-0.132
 hands-0.126
 shoulders-0.125
 Luke-0.123
Token said
Token ID531
Feature activation-1.25e+00

Pos logit contributions
 vet+0.027
 mir+0.027
 hawk+0.026
 pilot+0.026
 wing+0.025
Neg logit contributions
 gigg-0.015
 Jack-0.015
 Luke-0.014
 subtract-0.014
 hips-0.013
Token,
Token ID11
Feature activation-8.76e-01

Pos logit contributions
 vet+0.041
 hawk+0.040
 mir+0.040
 pilot+0.039
oster+0.039
Neg logit contributions
 Jack-0.022
 Luke-0.021
 gigg-0.021
 hips-0.019
 James-0.019
Token "
Token ID366
Feature activation+4.80e-01

Pos logit contributions
 hawk+0.030
 vet+0.030
 mir+0.030
oster+0.029
 pilot+0.029
Neg logit contributions
 Jack-0.014
 -0.014
 gigg-0.013
 Luke-0.013
 subtract-0.013
TokenI
Token ID40
Feature activation-1.41e+00

Pos logit contributions
 subtract+0.010
 Luke+0.010
 Jack+0.010
 subt+0.010
 gigg+0.010
Neg logit contributions
 vet-0.013
 hawk-0.013
 mir-0.012
 pilot-0.012
 wing-0.012
Token seemed
Token ID3947
Feature activation-6.67e-01

Pos logit contributions
 vet+0.007
 hawk+0.006
 pilot+0.006
 mir+0.006
 wing+0.006
Neg logit contributions
 gigg-0.004
 Jack-0.004
 Luke-0.004
 laughed-0.004
 Alex-0.003
Token lonely
Token ID21757
Feature activation-1.28e+00

Pos logit contributions
 vet+0.018
 hawk+0.017
 pilot+0.017
oster+0.017
 wing+0.016
Neg logit contributions
 Jack-0.015
 gigg-0.015
 Luke-0.015
 subtract-0.014
 hips-0.014
Token.
Token ID13
Feature activation-4.01e-01

Pos logit contributions
 vet+0.044
oster+0.042
 hawk+0.042
 pilot+0.041
 mir+0.041
Neg logit contributions
 Jack-0.021
 Luke-0.020
 gigg-0.020
 hips-0.018
 subtract-0.018
Token The
Token ID383
Feature activation-1.83e+00

Pos logit contributions
 vet+0.012
 hawk+0.011
 pilot+0.011
 mir+0.011
oster+0.011
Neg logit contributions
 Luke-0.008
 Jack-0.008
 subtract-0.008
 subt-0.008
 gigg-0.008
Token b
Token ID275
Feature activation-3.12e+00

Pos logit contributions
 vet+0.043
oster+0.042
 hawk+0.041
 pilot+0.040
 mir+0.040
Neg logit contributions
 Jack-0.046
 gigg-0.045
 Luke-0.044
 subtract-0.043
 subt-0.043
Tokenunn
Token ID20935
Feature activation-4.92e+00

Pos logit contributions
 vet+0.103
 pilot+0.099
 hawk+0.098
 mir+0.096
oster+0.094
Neg logit contributions
 gigg-0.048
 Jack-0.045
igsaw-0.044
 hands-0.044
 subtract-0.042
Tokenies
Token ID444
Feature activation-1.01e+00

Pos logit contributions
 vet+0.152
 hawk+0.141
 pilot+0.139
 mir+0.137
oster+0.136
Neg logit contributions
 gigg-0.094
 Jack-0.091
 hands-0.086
 Luke-0.085
 hips-0.083
Token invited
Token ID9392
Feature activation-7.60e-01

Pos logit contributions
 vet+0.036
 mir+0.035
oster+0.033
Santa+0.032
 vaccine+0.032
Neg logit contributions
 gigg-0.019
 Jack-0.016
 laughed-0.016
 g-0.015
 -0.015
Token him
Token ID683
Feature activation-1.49e+00

Pos logit contributions
 vet+0.024
 hawk+0.023
 pilot+0.022
oster+0.022
 mir+0.022
Neg logit contributions
 Jack-0.014
 Luke-0.014
 subtract-0.013
 gigg-0.013
 subt-0.013
Token to
Token ID284
Feature activation-1.46e+00

Pos logit contributions
 hawk+0.044
 vet+0.043
 pilot+0.043
oster+0.043
 mir+0.042
Neg logit contributions
 Jack-0.031
 gigg-0.029
 Luke-0.029
 hands-0.027
 -0.027
Token join
Token ID4654
Feature activation+7.78e-01

Pos logit contributions
oster+0.044
 hawk+0.043
 pilot+0.042
 vet+0.042
 mir+0.041
Neg logit contributions
 Jack-0.031
 Luke-0.029
 gigg-0.027
 g-0.027
 subtract-0.026
Token so
Token ID523
Feature activation+4.41e-01

Pos logit contributions
 gigg+0.011
 Jack+0.010
 Luke+0.010
 subtract+0.010
 James+0.010
Neg logit contributions
 vet-0.017
 hawk-0.016
 mir-0.016
oster-0.016
 pilot-0.016
Token happy
Token ID3772
Feature activation+4.46e-01

Pos logit contributions
 Jack+0.008
 Luke+0.008
 gigg+0.008
 subtract+0.008
 subt+0.008
Neg logit contributions
 vet-0.014
 hawk-0.013
 pilot-0.013
 mir-0.013
oster-0.013
Token and
Token ID290
Feature activation+1.54e-01

Pos logit contributions
 subt+0.013
 subtract+0.013
igsaw+0.013
 wrists+0.013
irms+0.013
Neg logit contributions
 vet-0.009
 hawk-0.008
 wing-0.008
 pilot-0.008
 mir-0.007
Token hugged
Token ID41130
Feature activation-8.46e-01

Pos logit contributions
igsaw+0.003
 subtract+0.003
 subt+0.003
 Luke+0.003
 hips+0.003
Neg logit contributions
 vet-0.004
 pilot-0.004
 hawk-0.004
 wing-0.004
 mir-0.004
Token the
Token ID262
Feature activation-3.21e+00

Pos logit contributions
 vet+0.023
 hawk+0.022
 pilot+0.021
oster+0.021
 mir+0.021
Neg logit contributions
 subtract-0.019
 Luke-0.019
 Jack-0.019
 subt-0.019
igsaw-0.018
Token kind
Token ID1611
Feature activation-4.91e+00

Pos logit contributions
ull+0.057
 vet+0.056
 mir+0.056
oster+0.055
 wing+0.053
Neg logit contributions
 gigg-0.091
 shoulders-0.088
 -0.086
 wrists-0.086
 hands-0.086
Token sheep
Token ID15900
Feature activation-1.04e-01

Pos logit contributions
oster+0.095
 vet+0.094
 hawk+0.091
 mir+0.090
 pilot+0.089
Neg logit contributions
 gigg-0.129
 Jack-0.128
 shoulders-0.124
 hands-0.123
 Luke-0.122
Token tightly
Token ID17707
Feature activation-1.15e-01

Pos logit contributions
 vet+0.003
 wing+0.002
 pilot+0.002
oster+0.002
 hawk+0.002
Neg logit contributions
 subt-0.003
 subtract-0.003
igsaw-0.003
 Luke-0.002
irms-0.002
Token.
Token ID13
Feature activation-5.68e-01

Pos logit contributions
 vet+0.003
 hawk+0.003
 pilot+0.003
 wing+0.003
oster+0.003
Neg logit contributions
 subtract-0.002
 subt-0.002
 Luke-0.002
igsaw-0.002
 Jack-0.002
Token The
Token ID383
Feature activation-3.23e+00

Pos logit contributions
 vet+0.015
 hawk+0.014
 pilot+0.013
 wing+0.013
 mir+0.013
Neg logit contributions
 subtract-0.013
 gigg-0.013
 subt-0.013
 hips-0.013
 Luke-0.013
Token sheep
Token ID15900
Feature activation-1.98e-01

Pos logit contributions
 vet+0.063
oster+0.061
 mir+0.061
ull+0.060
 wing+0.059
Neg logit contributions
 gigg-0.088
 Luke-0.083
 shoulders-0.083
 Jack-0.082
 g-0.082
Token,
Token ID11
Feature activation-1.49e+00

Pos logit contributions
 vet+0.045
 hawk+0.043
 pilot+0.042
oster+0.042
 mir+0.042
Neg logit contributions
 Jack-0.026
 Luke-0.026
 subtract-0.026
 gigg-0.025
 subt-0.025
Token leaving
Token ID4305
Feature activation-1.17e+00

Pos logit contributions
 vet+0.039
oster+0.037
 hawk+0.037
 pilot+0.036
 mir+0.036
Neg logit contributions
 Jack-0.036
 gigg-0.035
 Luke-0.034
 subtract-0.034
 hips-0.033
Token it
Token ID340
Feature activation-8.96e-01

Pos logit contributions
 vet+0.034
 hawk+0.033
oster+0.032
 pilot+0.032
 mir+0.032
Neg logit contributions
 Jack-0.025
 Luke-0.024
 gigg-0.023
 subtract-0.022
 James-0.022
Token to
Token ID284
Feature activation-9.69e-01

Pos logit contributions
 vet+0.024
 hawk+0.023
 pilot+0.022
oster+0.022
 mir+0.022
Neg logit contributions
 Jack-0.021
 gigg-0.020
 Luke-0.020
 subtract-0.020
 hips-0.019
Token its
Token ID663
Feature activation-1.84e+00

Pos logit contributions
 vet+0.025
oster+0.025
 pilot+0.024
 hawk+0.024
 mir+0.023
Neg logit contributions
 Jack-0.023
 Luke-0.022
 gigg-0.022
 subtract-0.021
 g-0.021
Token former
Token ID1966
Feature activation-4.88e+00

Pos logit contributions
 vet+0.043
oster+0.042
 hawk+0.041
 pilot+0.041
 mir+0.040
Neg logit contributions
 Jack-0.045
 gigg-0.045
 Luke-0.043
 hips-0.043
 hands-0.043
Token state
Token ID1181
Feature activation-2.65e+00

Pos logit contributions
 vet+0.145
 hawk+0.138
 pilot+0.136
oster+0.134
 mir+0.132
Neg logit contributions
 subtract-0.096
 Jack-0.095
 subt-0.094
 Luke-0.094
 gigg-0.094
Token.
Token ID13
Feature activation+7.13e-01

Pos logit contributions
 vet+0.095
 hawk+0.094
oster+0.091
 pilot+0.091
 mir+0.089
Neg logit contributions
 Jack-0.037
 gigg-0.034
 Luke-0.034
 subtract-0.033
 hips-0.033
Token
Token ID220
Feature activation+6.14e-01

Pos logit contributions
 subtract+0.012
 gigg+0.012
 subt+0.012
 wrists+0.012
igsaw+0.011
Neg logit contributions
 vet-0.023
 hawk-0.021
oster-0.021
 pilot-0.020
 wing-0.020
Token
Token ID198
Feature activation+3.88e-01

Pos logit contributions
 subt+0.015
 subtract+0.015
 gigg+0.015
 Luke+0.015
igsaw+0.015
Neg logit contributions
 vet-0.015
oster-0.014
 hawk-0.013
 wing-0.013
 pilot-0.013
Token
Token ID198
Feature activation-3.20e-01

Pos logit contributions
 Luke+0.008
 Jack+0.008
 subtract+0.008
 subt+0.008
 gigg+0.008
Neg logit contributions
 vet-0.011
 hawk-0.010
 pilot-0.010
 mir-0.010
 wing-0.010
Token.
Token ID13
Feature activation-4.74e-01

Pos logit contributions
 vet+0.047
 hawk+0.045
oster+0.045
 pilot+0.044
 mir+0.044
Neg logit contributions
 Jack-0.020
 gigg-0.019
 Luke-0.018
 subtract-0.018
 hips-0.017
Token
Token ID220
Feature activation+4.31e-01

Pos logit contributions
 vet+0.015
 hawk+0.014
 pilot+0.014
 mir+0.014
oster+0.014
Neg logit contributions
 Jack-0.009
 Luke-0.009
 subtract-0.009
 subt-0.009
 gigg-0.008
Token But
Token ID887
Feature activation-7.66e-01

Pos logit contributions
 Luke+0.010
 subtract+0.010
 Jack+0.009
 subt+0.009
 gigg+0.009
Neg logit contributions
 vet-0.012
 hawk-0.011
 pilot-0.011
oster-0.011
 mir-0.011
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
 vet+0.025
oster+0.024
 mir+0.024
 hawk+0.024
 pilot+0.024
Neg logit contributions
 Jack-0.016
 gigg-0.014
 Luke-0.014
 -0.013
 Alex-0.013
Token b
Token ID275
Feature activation-3.20e+00

Pos logit contributions
 vet+0.051
oster+0.049
 hawk+0.048
 mir+0.048
 pilot+0.048
Neg logit contributions
 gigg-0.047
 Jack-0.045
 g-0.044
 wrists-0.043
 shoulders-0.043
Tokenunn
Token ID20935
Feature activation-4.87e+00

Pos logit contributions
 vet+0.099
 pilot+0.095
 hawk+0.094
 mir+0.090
oster+0.090
Neg logit contributions
 gigg-0.057
igsaw-0.056
 Jack-0.055
 subtract-0.054
 subt-0.052
Tokenies
Token ID444
Feature activation-2.26e+00

Pos logit contributions
 vet+0.141
 hawk+0.132
 pilot+0.130
 mir+0.127
oster+0.127
Neg logit contributions
 gigg-0.101
 Jack-0.100
 Luke-0.097
 subtract-0.094
 hips-0.094
Token didn
Token ID1422
Feature activation+1.36e-01

Pos logit contributions
 vet+0.075
 mir+0.069
 hawk+0.067
oster+0.067
 pilot+0.066
Neg logit contributions
 gigg-0.045
 Jack-0.041
 g-0.039
 laughed-0.038
 -0.038
Token't
Token ID470
Feature activation-7.92e-01

Pos logit contributions
 Jack+0.003
 Luke+0.003
igsaw+0.003
 +0.003
 subtract+0.003
Neg logit contributions
 vet-0.004
 mir-0.004
 pilot-0.004
 hawk-0.004
oster-0.004
Token wake
Token ID7765
Feature activation-4.17e-01

Pos logit contributions
 vet+0.024
 hawk+0.023
oster+0.023
 wing+0.022
 pilot+0.022
Neg logit contributions
 Jack-0.016
 gigg-0.016
 Luke-0.015
 g-0.015
 subtract-0.015
Token up
Token ID510
Feature activation-1.12e+00

Pos logit contributions
 vet+0.016
 hawk+0.015
 mir+0.015
oster+0.015
 pilot+0.015
Neg logit contributions
 Jack-0.006
 Luke-0.005
 gigg-0.005
 hips-0.005
 James-0.005
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
 subtract+0.011
 Luke+0.010
 subt+0.010
 Jack+0.010
igsaw+0.010
Neg logit contributions
 vet-0.019
 hawk-0.018
 pilot-0.018
 wing-0.017
 mir-0.017
Token They
Token ID1119
Feature activation-3.87e-01

Pos logit contributions
 hawk+0.036
 vet+0.036
 pilot+0.036
oster+0.036
 mir+0.035
Neg logit contributions
 Jack-0.021
 Luke-0.021
 subtract-0.019
 subt-0.019
 -0.019
Token learned
Token ID4499
Feature activation-2.71e+00

Pos logit contributions
 vet+0.011
 hawk+0.010
oster+0.010
 pilot+0.010
 mir+0.010
Neg logit contributions
 gigg-0.008
 Jack-0.008
 Luke-0.008
 subtract-0.008
 subt-0.008
Token that
Token ID326
Feature activation+1.05e-01

Pos logit contributions
oster+0.089
 hawk+0.085
 mir+0.083
 pilot+0.083
umber+0.081
Neg logit contributions
 Jack-0.051
 gigg-0.046
 Luke-0.045
 subtract-0.044
 subt-0.043
Token some
Token ID617
Feature activation-1.14e+00

Pos logit contributions
 Jack+0.002
 subtract+0.002
 gigg+0.002
 Luke+0.002
 subt+0.002
Neg logit contributions
oster-0.003
 vet-0.003
 hawk-0.003
 pilot-0.003
 mir-0.003
Token chambers
Token ID23204
Feature activation-4.81e+00

Pos logit contributions
oster+0.033
 vet+0.032
 hawk+0.031
igi+0.030
 mir+0.030
Neg logit contributions
 Jack-0.025
 subtract-0.024
 laughs-0.024
 gigg-0.023
 subt-0.022
Token were
Token ID547
Feature activation-1.85e+00

Pos logit contributions
 vet+0.151
 hawk+0.146
oster+0.143
 mir+0.142
 pilot+0.139
Neg logit contributions
 Jack-0.089
 gigg-0.087
 laughs-0.085
 subtract-0.084
 hands-0.083
Token not
Token ID407
Feature activation-1.71e+00

Pos logit contributions
oster+0.059
 pilot+0.056
 hawk+0.055
umber+0.055
oral+0.054
Neg logit contributions
 Jack-0.036
 gigg-0.031
 boun-0.031
 fun-0.031
 Luke-0.031
Token for
Token ID329
Feature activation+3.60e-01

Pos logit contributions
oster+0.058
 vet+0.055
oral+0.054
 hawk+0.054
umber+0.053
Neg logit contributions
 Jack-0.033
 Luke-0.027
 James-0.027
 subtract-0.026
 gigg-0.026
Token them
Token ID606
Feature activation-6.66e-01

Pos logit contributions
 Jack+0.006
 subtract+0.006
 gigg+0.006
 Luke+0.006
 subt+0.005
Neg logit contributions
 vet-0.012
oster-0.012
 hawk-0.012
 pilot-0.012
 mir-0.011
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
 hawk+0.022
 vet+0.022
oster+0.022
 pilot+0.022
 mir+0.021
Neg logit contributions
 Jack-0.011
 gigg-0.010
 Luke-0.010
 subtract-0.010
 hips-0.010
Token the
Token ID262
Feature activation-4.96e-01

Pos logit contributions
 vet+0.034
 hawk+0.032
 pilot+0.031
 wing+0.031
 mir+0.031
Neg logit contributions
 subtract-0.030
 Luke-0.030
 Jack-0.030
 subt-0.030
igsaw-0.030
Token harbor
Token ID25451
Feature activation-2.48e+00

Pos logit contributions
oster+0.012
 vet+0.012
 hawk+0.012
 wing+0.011
ull+0.011
Neg logit contributions
 Jack-0.011
 Luke-0.011
 gigg-0.011
 subtract-0.011
igsaw-0.011
Token.
Token ID13
Feature activation-8.86e-01

Pos logit contributions
 vet+0.070
 hawk+0.066
 pilot+0.066
oster+0.065
 mir+0.065
Neg logit contributions
 subtract-0.052
 Luke-0.052
 Jack-0.052
 subt-0.052
igsaw-0.051
Token The
Token ID383
Feature activation-3.21e+00

Pos logit contributions
 vet+0.028
 hawk+0.027
 pilot+0.026
oster+0.026
 mir+0.026
Neg logit contributions
 Jack-0.016
 Luke-0.016
 subtract-0.016
 subt-0.016
 gigg-0.015
Token harbor
Token ID25451
Feature activation-3.07e+00

Pos logit contributions
 vet+0.061
 hawk+0.057
reetings+0.056
oster+0.055
igi+0.054
Neg logit contributions
 hands-0.086
 boun-0.084
 gigg-0.083
 Jack-0.083
 -0.081
Token has
Token ID468
Feature activation-4.76e+00

Pos logit contributions
 vet+0.082
 hawk+0.078
 pilot+0.076
 mir+0.076
oster+0.075
Neg logit contributions
 Luke-0.069
 Jack-0.069
 subtract-0.068
 gigg-0.068
 subt-0.067
Token many
Token ID867
Feature activation-4.44e+00

Pos logit contributions
oster+0.155
 vet+0.151
 hawk+0.149
oral+0.146
 pilot+0.144
Neg logit contributions
 Jack-0.080
 gigg-0.077
 hands-0.074
 g-0.071
 Luke-0.070
Token boats
Token ID16659
Feature activation-2.62e+00

Pos logit contributions
 vet+0.135
 hawk+0.125
oster+0.125
 wing+0.119
 pilot+0.119
Neg logit contributions
 gigg-0.091
 hands-0.086
 laughs-0.083
 wrists-0.083
 Jack-0.082
Token.
Token ID13
Feature activation-1.13e+00

Pos logit contributions
 vet+0.080
 hawk+0.076
oster+0.074
 pilot+0.074
 mir+0.074
Neg logit contributions
 Jack-0.050
 gigg-0.049
 subtract-0.049
 Luke-0.049
 subt-0.047
Token Some
Token ID2773
Feature activation-3.35e+00

Pos logit contributions
 vet+0.039
 hawk+0.038
 pilot+0.037
oster+0.037
 wing+0.037
Neg logit contributions
 Jack-0.017
 Luke-0.017
 subtract-0.017
 subt-0.016
 gigg-0.016
Token boats
Token ID16659
Feature activation-2.79e+00

Pos logit contributions
 vet+0.095
 hawk+0.088
oster+0.087
 hen+0.085
 wing+0.083
Neg logit contributions
 gigg-0.074
 hands-0.072
 Jack-0.071
 laughs-0.070
 subtract-0.069
Tokenunn
Token ID20935
Feature activation-3.13e+00

Pos logit contributions
 vet+0.035
 mir+0.033
oster+0.032
 wing+0.032
 hawk+0.032
Neg logit contributions
 Luke-0.041
 Jack-0.039
 subt-0.039
 James-0.038
 subtract-0.038
Tokenies
Token ID444
Feature activation-1.76e+00

Pos logit contributions
 wing+0.060
 vet+0.059
 pilot+0.059
 mir+0.057
 hawk+0.057
Neg logit contributions
 subtract-0.100
 subt-0.098
 Luke-0.098
igsaw-0.097
 Jack-0.092
Token.
Token ID13
Feature activation-2.09e+00

Pos logit contributions
 vet+0.055
 hawk+0.054
 mir+0.053
oster+0.053
 pilot+0.052
Neg logit contributions
 Jack-0.031
 gigg-0.030
 Luke-0.029
 subtract-0.027
ci-0.027
Token The
Token ID383
Feature activation-3.24e+00

Pos logit contributions
 vet+0.071
 hawk+0.070
oster+0.068
 pilot+0.068
 wing+0.067
Neg logit contributions
 Jack-0.036
 Luke-0.033
 James-0.031
 gigg-0.031
igsaw-0.030
Token b
Token ID275
Feature activation-3.13e+00

Pos logit contributions
reetings+0.090
oster+0.089
 hawk+0.087
ull+0.086
 vet+0.085
Neg logit contributions
 gigg-0.068
 g-0.066
 hands-0.065
 shoulders-0.062
 Jack-0.060
Tokenunn
Token ID20935
Feature activation-4.72e+00

Pos logit contributions
 vet+0.103
 hawk+0.099
 pilot+0.097
 mir+0.094
 wing+0.093
Neg logit contributions
 gigg-0.050
 Jack-0.048
 hands-0.046
igsaw-0.046
 wrists-0.045
Tokenies
Token ID444
Feature activation-1.82e+00

Pos logit contributions
 vet+0.137
 hawk+0.129
 pilot+0.126
 mir+0.124
oster+0.123
Neg logit contributions
 gigg-0.097
 Jack-0.097
 Luke-0.093
 subtract-0.090
 wrists-0.089
Token lived
Token ID5615
Feature activation-1.00e+00

Pos logit contributions
 vet+0.061
 hawk+0.057
 mir+0.055
oster+0.054
 pilot+0.053
Neg logit contributions
 gigg-0.035
 Jack-0.034
 g-0.030
 -0.030
 laughed-0.029
Token in
Token ID287
Feature activation-1.18e+00

Pos logit contributions
 vet+0.030
 hawk+0.030
 mir+0.030
 pilot+0.029
oster+0.028
Neg logit contributions
 gigg-0.021
 Jack-0.020
 boun-0.018
 Luke-0.018
 hands-0.018
Token a
Token ID257
Feature activation+2.73e-01

Pos logit contributions
 vet+0.034
 hawk+0.033
oster+0.033
 pilot+0.032
 mir+0.032
Neg logit contributions
 Jack-0.025
 Luke-0.024
 gigg-0.023
igsaw-0.023
 subtract-0.023
Token cozy
Token ID37438
Feature activation-2.05e+00

Pos logit contributions
 Jack+0.005
 +0.005
 gigg+0.005
 boun+0.005
 Luke+0.005
Neg logit contributions
 vet-0.008
oster-0.008
 hawk-0.008
resp-0.007
reetings-0.007
Token bed
Token ID3996
Feature activation-1.71e+00

Pos logit contributions
 vet+0.008
 wing+0.007
 hawk+0.007
 pilot+0.007
 mir+0.007
Neg logit contributions
 subtract-0.009
 Luke-0.009
 subt-0.009
 Jack-0.009
 gigg-0.009
Token,
Token ID11
Feature activation-1.34e+00

Pos logit contributions
 vet+0.050
 hawk+0.049
 pilot+0.047
 mir+0.047
oster+0.047
Neg logit contributions
 Jack-0.034
 Luke-0.034
 subtract-0.033
 gigg-0.033
 subt-0.033
Token knowing
Token ID6970
Feature activation-1.57e+00

Pos logit contributions
 vet+0.036
 hawk+0.035
oster+0.034
 mir+0.034
 pilot+0.033
Neg logit contributions
 Jack-0.031
 gigg-0.030
 Luke-0.030
 subtract-0.029
 hips-0.029
Token the
Token ID262
Feature activation-2.10e+00

Pos logit contributions
oster+0.056
 vet+0.053
 hawk+0.053
 pilot+0.051
 mir+0.051
Neg logit contributions
 Jack-0.028
 gigg-0.024
 Luke-0.024
 James-0.022
 subtract-0.022
Token b
Token ID275
Feature activation-3.04e+00

Pos logit contributions
 vet+0.047
oster+0.045
 mir+0.044
 pilot+0.044
 hawk+0.044
Neg logit contributions
 gigg-0.054
 Jack-0.053
 subtract-0.053
 wrists-0.053
 Luke-0.052
Tokenunn
Token ID20935
Feature activation-4.70e+00

Pos logit contributions
 vet+0.082
 hawk+0.078
 pilot+0.077
 mir+0.076
 wing+0.075
Neg logit contributions
 subtract-0.066
 Jack-0.065
igsaw-0.065
 gigg-0.065
 subt-0.064
Tokenies
Token ID444
Feature activation-2.27e+00

Pos logit contributions
 vet+0.129
 hawk+0.122
 pilot+0.120
 mir+0.119
oster+0.118
Neg logit contributions
 Jack-0.102
 gigg-0.101
 Luke-0.100
 subtract-0.100
 subt-0.098
Token couldn
Token ID3521
Feature activation+1.65e-01

Pos logit contributions
 vet+0.069
 hawk+0.064
oster+0.064
 mir+0.063
 pilot+0.061
Neg logit contributions
 Jack-0.048
 gigg-0.046
 Luke-0.044
 g-0.043
 laughs-0.042
Token't
Token ID470
Feature activation-8.85e-01

Pos logit contributions
 Jack+0.004
 Luke+0.004
 subtract+0.004
 gigg+0.004
igsaw+0.004
Neg logit contributions
 vet-0.004
 hawk-0.004
 pilot-0.004
 mir-0.004
oster-0.004
Token get
Token ID651
Feature activation+3.44e-01

Pos logit contributions
 vet+0.024
 hawk+0.023
oster+0.023
 mir+0.023
 pilot+0.022
Neg logit contributions
 gigg-0.019
 Jack-0.019
 g-0.018
 subtract-0.018
 hips-0.017
Token in
Token ID287
Feature activation-5.42e-01

Pos logit contributions
 Jack+0.008
 gigg+0.008
 Luke+0.008
 subtract+0.008
 subt+0.007
Neg logit contributions
 vet-0.009
 hawk-0.009
oster-0.008
 pilot-0.008
 mir-0.008
Token.
Token ID13
Feature activation-5.27e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
 pilot+0.002
 wing+0.002
 mir+0.002
Neg logit contributions
 subtract-0.001
 Luke-0.001
 subt-0.001
 Jack-0.001
igsaw-0.001
Token
Token ID220
Feature activation+4.53e-01

Pos logit contributions
 vet+0.014
oster+0.012
 mir+0.012
 doctor+0.011
 ranc+0.011
Neg logit contributions
 subt-0.012
igsaw-0.012
 subtract-0.012
 wrists-0.012
 hips-0.011
Token
Token ID198
Feature activation-4.36e-01

Pos logit contributions
 subt+0.012
 subtract+0.012
igsaw+0.012
 Luke+0.012
 gigg+0.012
Neg logit contributions
 vet-0.010
oster-0.009
 hawk-0.009
 wing-0.009
 pilot-0.009
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
 vet+0.012
 hawk+0.011
 pilot+0.011
oster+0.011
 mir+0.011
Neg logit contributions
 subtract-0.010
 Luke-0.010
 Jack-0.010
 subt-0.010
igsaw-0.010
TokenThe
Token ID464
Feature activation-2.93e+00

Pos logit contributions
 wing+0.042
 hawk+0.041
 mir+0.040
 hen+0.040
 pilot+0.038
Neg logit contributions
 subtract-0.038
 Luke-0.038
 -0.037
 Jack-0.036
 gigg-0.036
Token sw
Token ID1509
Feature activation-4.70e+00

Pos logit contributions
 vet+0.066
 hawk+0.061
 wing+0.060
oster+0.060
 pilot+0.060
Neg logit contributions
 gigg-0.076
 g-0.069
 -0.069
 Jack-0.068
 hands-0.068
Tokenan
Token ID272
Feature activation-1.17e+00

Pos logit contributions
 vet+0.096
 hawk+0.088
 pilot+0.087
God+0.083
 hen+0.080
Neg logit contributions
 gigg-0.135
 wrists-0.130
 hips-0.128
ci-0.127
 hands-0.127
Token on
Token ID319
Feature activation-1.96e+00

Pos logit contributions
 vet+0.036
 mir+0.035
 hawk+0.034
 vaccine+0.033
Santa+0.032
Neg logit contributions
 gigg-0.024
 Jack-0.021
 laughed-0.021
ci-0.020
 -0.020
Token the
Token ID262
Feature activation-1.67e+00

Pos logit contributions
reetings+0.084
Dear+0.081
igi+0.081
 mir+0.080
umber+0.080
Neg logit contributions
 Jack-0.021
 -0.020
 Luke-0.014
 Jake-0.013
 hands-0.013
Token right
Token ID826
Feature activation-1.69e+00

Pos logit contributions
 vet+0.037
 hawk+0.035
 pilot+0.034
oster+0.034
 mir+0.033
Neg logit contributions
 Luke-0.045
 Jack-0.045
 subtract-0.045
 gigg-0.045
 subt-0.044
Token flew
Token ID13112
Feature activation-9.53e-01

Pos logit contributions
 vet+0.044
oster+0.041
 pilot+0.041
 hawk+0.040
 mir+0.039
Neg logit contributions
 hands-0.038
 gigg-0.037
 Jack-0.037
 Luke-0.036
 wrists-0.036
Token in
Token ID287
Feature activation-5.96e-01

Pos logit contributions
 vet+0.009
oster+0.009
 pilot+0.009
 hawk+0.008
 mir+0.008
Neg logit contributions
 Jack-0.008
 gigg-0.008
 Luke-0.007
 hips-0.007
 hands-0.007
Token some
Token ID617
Feature activation-1.33e+00

Pos logit contributions
oster+0.019
 pilot+0.019
 vet+0.019
 mir+0.018
 hawk+0.017
Neg logit contributions
 Jack-0.011
 Luke-0.010
 gigg-0.010
 hands-0.010
 -0.010
Token weeds
Token ID36708
Feature activation-1.64e+00

Pos logit contributions
 pilot+0.036
oster+0.035
 vet+0.035
 hawk+0.033
reetings+0.033
Neg logit contributions
 hands-0.028
 Jack-0.027
 g-0.026
 gigg-0.026
 subtract-0.026
Token.
Token ID13
Feature activation-8.51e-01

Pos logit contributions
 vet+0.056
 pilot+0.054
oster+0.053
 hawk+0.053
 mir+0.053
Neg logit contributions
 Jack-0.026
 Luke-0.025
 gigg-0.025
 hips-0.024
 subtract-0.023
Token The
Token ID383
Feature activation-3.13e+00

Pos logit contributions
 vet+0.024
 hawk+0.023
 pilot+0.022
oster+0.022
 wing+0.022
Neg logit contributions
 subtract-0.018
 Luke-0.018
 subt-0.018
igsaw-0.018
 gigg-0.017
Token sw
Token ID1509
Feature activation-4.65e+00

Pos logit contributions
reetings+0.071
God+0.070
 vet+0.066
bul+0.065
resp+0.064
Neg logit contributions
 gigg-0.076
 hands-0.073
 boun-0.071
 g-0.071
 -0.070
Tokenan
Token ID272
Feature activation-1.55e+00

Pos logit contributions
 vet+0.092
 pilot+0.088
God+0.084
 hawk+0.084
Santa+0.082
Neg logit contributions
 gigg-0.134
 hands-0.131
 wrists-0.130
 shoulders-0.129
 hips-0.129
Token paused
Token ID24487
Feature activation-4.36e-01

Pos logit contributions
 vet+0.049
 mir+0.047
 pilot+0.046
 hawk+0.045
reetings+0.044
Neg logit contributions
 gigg-0.031
 Jack-0.028
 laughed-0.026
 Luke-0.026
 -0.025
Token again
Token ID757
Feature activation-1.19e-01

Pos logit contributions
oster+0.016
 pilot+0.015
 vet+0.015
 tou+0.015
 hawk+0.015
Neg logit contributions
 Jack-0.008
 gigg-0.007
 g-0.006
 Ted-0.006
 -0.006
Token and
Token ID290
Feature activation+4.67e-01

Pos logit contributions
oster+0.003
 vet+0.003
 pilot+0.003
 hawk+0.003
 mir+0.003
Neg logit contributions
 Jack-0.003
 gigg-0.003
 Luke-0.003
 -0.002
 hips-0.002
Token decided
Token ID3066
Feature activation-1.77e+00

Pos logit contributions
 Jack+0.010
 Luke+0.010
 gigg+0.010
 subtract+0.010
 subt+0.010
Neg logit contributions
 vet-0.013
 hawk-0.012
 pilot-0.012
oster-0.012
 mir-0.012
Token you
Token ID345
Feature activation-7.69e-02

Pos logit contributions
 Jack+0.010
 Luke+0.010
 subtract+0.010
 gigg+0.010
 subt+0.010
Neg logit contributions
 vet-0.017
 hawk-0.016
 pilot-0.016
oster-0.016
 mir-0.016
Token!"
Token ID2474
Feature activation+4.01e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
 pilot+0.002
oster+0.002
 mir+0.002
Neg logit contributions
 Jack-0.001
 Luke-0.001
 subtract-0.001
 gigg-0.001
 hips-0.001
Token
Token ID198
Feature activation-1.96e-01

Pos logit contributions
 subtract+0.008
 Luke+0.008
 Jack+0.008
 subt+0.008
igsaw+0.008
Neg logit contributions
 vet-0.011
 hawk-0.011
 pilot-0.010
oster-0.010
 mir-0.010
Token
Token ID198
Feature activation-7.19e-01

Pos logit contributions
 vet+0.006
 hawk+0.005
 pilot+0.005
 mir+0.005
 wing+0.005
Neg logit contributions
 Jack-0.004
 Luke-0.004
 subtract-0.004
 gigg-0.004
 subt-0.004
TokenThe
Token ID464
Feature activation-2.52e+00

Pos logit contributions
 wing+0.016
 mir+0.015
 pilot+0.015
 hawk+0.015
 vet+0.014
Neg logit contributions
 subtract-0.020
 Luke-0.019
 subt-0.019
 Jack-0.018
 gigg-0.018
Token c
Token ID269
Feature activation-4.64e+00

Pos logit contributions
ull+0.055
bul+0.053
reetings+0.052
 pilot+0.052
God+0.052
Neg logit contributions
 gigg-0.063
 g-0.056
 laughs-0.054
 cries-0.053
 wrists-0.052
Tokenrows
Token ID8516
Feature activation-8.54e-01

Pos logit contributions
 pilot+0.122
 vet+0.120
 hawk+0.119
 wing+0.114
 mir+0.113
Neg logit contributions
 gigg-0.094
igsaw-0.090
idents-0.087
zy-0.086
irms-0.084
Token were
Token ID547
Feature activation+1.66e-01

Pos logit contributions
 vet+0.029
 mir+0.028
 hawk+0.026
 pilot+0.026
oster+0.025
Neg logit contributions
 gigg-0.016
 g-0.014
 Jack-0.014
 laughed-0.014
 laughs-0.014
Token relieved
Token ID22598
Feature activation+1.12e-01

Pos logit contributions
 gigg+0.003
 Jack+0.003
 Luke+0.003
 hips+0.003
 subtract+0.003
Neg logit contributions
 vet-0.005
 pilot-0.005
 hawk-0.005
 mir-0.005
oster-0.005
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
 Jack+0.003
 Luke+0.003
 gigg+0.003
 subtract+0.003
 subt+0.003
Neg logit contributions
 vet-0.003
 hawk-0.002
oster-0.002
 pilot-0.002
 mir-0.002
Token and
Token ID290
Feature activation-1.72e-01

Pos logit contributions
 vet+0.031
oster+0.030
 hawk+0.029
 pilot+0.029
 mir+0.029
Neg logit contributions
 Jack-0.028
 gigg-0.027
 Luke-0.027
 subtract-0.026
 hips-0.025
Tokenan
Token ID272
Feature activation-6.42e-01

Pos logit contributions
 vet+0.085
 pilot+0.080
 hawk+0.078
God+0.074
Santa+0.071
Neg logit contributions
 gigg-0.131
 wrists-0.130
 hips-0.130
 shoulders-0.129
 hands-0.129
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
 vet+0.023
 hawk+0.022
 pilot+0.022
 mir+0.022
oster+0.022
Neg logit contributions
 Jack-0.009
 gigg-0.008
 Luke-0.008
 hips-0.008
 hands-0.007
Token
Token ID198
Feature activation-8.42e-01

Pos logit contributions
 vet+0.015
 pilot+0.014
 hawk+0.014
oster+0.014
 mir+0.014
Neg logit contributions
 Jack-0.009
 Luke-0.008
 subtract-0.008
 gigg-0.008
 subt-0.008
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
 vet+0.022
 hawk+0.021
 pilot+0.021
 mir+0.020
oster+0.020
Neg logit contributions
 Luke-0.019
 subtract-0.019
 Jack-0.019
 subt-0.019
 gigg-0.019
TokenThe
Token ID464
Feature activation-2.94e+00

Pos logit contributions
 pilot+0.029
 vet+0.028
 hawk+0.028
 wing+0.028
 mir+0.027
Neg logit contributions
 Luke-0.033
 Jack-0.032
 gigg-0.031
 -0.031
 subtract-0.031
Token sw
Token ID1509
Feature activation-4.60e+00

Pos logit contributions
 vet+0.064
oster+0.063
 pilot+0.062
 wing+0.059
God+0.059
Neg logit contributions
 gigg-0.074
 g-0.066
 laughs-0.066
 boun-0.066
 hands-0.065
Tokenan
Token ID272
Feature activation-1.81e+00

Pos logit contributions
 vet+0.089
 pilot+0.083
 hawk+0.081
God+0.078
Santa+0.076
Neg logit contributions
 gigg-0.134
 wrists-0.130
 hands-0.129
 shoulders-0.129
 hips-0.129
Token stops
Token ID9911
Feature activation+1.42e+00

Pos logit contributions
 vet+0.059
 pilot+0.057
 hawk+0.057
 wing+0.056
oster+0.056
Neg logit contributions
 gigg-0.031
 laughs-0.031
 Luke-0.028
 smiles-0.027
 Jack-0.027
Token at
Token ID379
Feature activation+7.15e-01

Pos logit contributions
 gigg+0.028
 Jack+0.027
 Luke+0.026
 subtract+0.025
 hips+0.025
Neg logit contributions
 vet-0.044
oster-0.043
 pilot-0.042
 hawk-0.042
 mir-0.040
Token the
Token ID262
Feature activation-2.14e+00

Pos logit contributions
 Jack+0.015
 Luke+0.015
 subtract+0.015
 gigg+0.014
 subt+0.014
Neg logit contributions
 vet-0.020
 hawk-0.019
 pilot-0.019
oster-0.019
 mir-0.019
Token trash
Token ID13913
Feature activation-9.24e-01

Pos logit contributions
oster+0.054
reetings+0.054
God+0.052
oral+0.052
 pilot+0.051
Neg logit contributions
 wrists-0.045
 shoulders-0.043
 Jack-0.043
 boun-0.043
 gigg-0.042
Token.
Token ID13
Feature activation+7.71e-01

Pos logit contributions
 vet+0.012
 hawk+0.012
oster+0.012
 pilot+0.011
 mir+0.011
Neg logit contributions
 Jack-0.010
 Luke-0.010
 gigg-0.009
 subtract-0.009
 subt-0.009
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
 subtract+0.017
 Luke+0.017
 subt+0.017
 gigg+0.016
 Jack+0.016
Neg logit contributions
 vet-0.021
 hawk-0.020
 pilot-0.019
oster-0.019
 mir-0.019
Token
Token ID198
Feature activation-5.23e-01

Pos logit contributions
 Jack+0.007
 Luke+0.007
 subtract+0.007
 gigg+0.007
 subt+0.007
Neg logit contributions
 vet-0.010
 hawk-0.009
 pilot-0.009
 mir-0.009
 wing-0.009
TokenBut
Token ID1537
Feature activation+4.01e-01

Pos logit contributions
 wing+0.012
 pilot+0.012
 hawk+0.011
 mir+0.011
 vet+0.010
Neg logit contributions
 Luke-0.014
 Jack-0.014
 subtract-0.013
 subt-0.013
 -0.013
Token the
Token ID262
Feature activation-2.58e+00

Pos logit contributions
 Jack+0.008
 Luke+0.008
 gigg+0.007
 James+0.007
 Alex+0.007
Neg logit contributions
 vet-0.012
 mir-0.012
oster-0.012
 hawk-0.012
 pilot-0.012
Token persistent
Token ID16218
Feature activation-4.58e+00

Pos logit contributions
 vet+0.052
 hawk+0.048
 pilot+0.048
 mir+0.047
oster+0.047
Neg logit contributions
 Luke-0.075
 Jack-0.075
 subtract-0.075
 gigg-0.074
 subt-0.074
Token sheep
Token ID15900
Feature activation-1.01e+00

Pos logit contributions
 vet+0.079
 mir+0.071
 hawk+0.071
 wing+0.071
 pilot+0.070
Neg logit contributions
 Jack-0.140
 gigg-0.139
 Luke-0.139
 hips-0.134
 subtract-0.133
Token refused
Token ID6520
Feature activation-3.82e-02

Pos logit contributions
 vet+0.028
 mir+0.028
 hawk+0.027
 pilot+0.027
oster+0.026
Neg logit contributions
 Jack-0.023
 gigg-0.022
 Luke-0.021
 -0.020
 James-0.019
Token to
Token ID284
Feature activation+3.29e-02

Pos logit contributions
 vet+0.001
 hawk+0.001
 pilot+0.001
oster+0.001
 mir+0.001
Neg logit contributions
 Jack-0.001
 Luke-0.001
 subtract-0.001
 gigg-0.001
 subt-0.001
Token give
Token ID1577
Feature activation+2.92e-01

Pos logit contributions
 Jack+0.001
 gigg+0.001
 g+0.001
 subtract+0.001
 Luke+0.001
Neg logit contributions
oster-0.001
 mir-0.001
 vet-0.001
 hawk-0.001
 pilot-0.001
Token up
Token ID510
Feature activation-6.36e-01

Pos logit contributions
 subtract+0.007
 subt+0.007
igsaw+0.006
 gigg+0.006
 Luke+0.006
Neg logit contributions
 vet-0.008
 hawk-0.008
 wing-0.008
 pilot-0.007
oster-0.007
Token heart
Token ID2612
Feature activation-2.36e-01

Pos logit contributions
 Luke+0.012
 subtract+0.012
 Jack+0.012
 subt+0.012
igsaw+0.011
Neg logit contributions
 vet-0.015
 pilot-0.015
 hawk-0.015
 wing-0.014
 mir-0.014
Token.
Token ID13
Feature activation+8.97e-01

Pos logit contributions
 vet+0.007
 hawk+0.007
 pilot+0.007
 wing+0.007
oster+0.007
Neg logit contributions
 Luke-0.004
 subtract-0.004
 Jack-0.004
 subt-0.004
igsaw-0.004
Token
Token ID198
Feature activation+5.31e-01

Pos logit contributions
igsaw+0.023
 subtract+0.022
ci+0.022
 subt+0.022
 gigg+0.022
Neg logit contributions
 vet-0.022
 hawk-0.020
 pilot-0.019
 mir-0.019
oster-0.018
Token
Token ID198
Feature activation-6.98e-01

Pos logit contributions
 subtract+0.013
 Luke+0.013
 subt+0.013
 Jack+0.012
igsaw+0.012
Neg logit contributions
 vet-0.013
 hawk-0.012
oster-0.012
 mir-0.012
 pilot-0.012
TokenTom
Token ID13787
Feature activation+9.75e-01

Pos logit contributions
 vet+0.012
 hawk+0.011
 pilot+0.011
oster+0.011
 mir+0.010
Neg logit contributions
 Jack-0.022
 Luke-0.022
 subtract-0.022
 subt-0.022
 gigg-0.022
Token and
Token ID290
Feature activation+2.17e+00

Pos logit contributions
igsaw+0.019
 subtract+0.018
 subt+0.018
 Jack+0.018
 Luke+0.018
Neg logit contributions
 vet-0.029
 pilot-0.027
 hawk-0.027
 wing-0.026
 mir-0.026
Token Anna
Token ID11735
Feature activation+1.35e+00

Pos logit contributions
igsaw+0.059
ci+0.058
 subtract+0.056
 subt+0.056
icol+0.055
Neg logit contributions
 vet-0.050
 doctor-0.048
 firefighter-0.045
 pilot-0.044
 nurse-0.042
Token look
Token ID804
Feature activation+1.50e+00

Pos logit contributions
igsaw+0.032
 subt+0.031
 Luke+0.030
 subtract+0.030
 Jack+0.029
Neg logit contributions
 pilot-0.035
 vet-0.035
 wing-0.032
 hawk-0.031
oster-0.031
Token at
Token ID379
Feature activation+1.61e+00

Pos logit contributions
 subtract+0.049
igsaw+0.048
 subt+0.047
 Luke+0.045
 hips+0.045
Neg logit contributions
 or-0.026
 pilot-0.025
 vet-0.024
 wing-0.022
 from-0.021
Token each
Token ID1123
Feature activation+1.56e+00

Pos logit contributions
 subt+0.046
igsaw+0.045
 subtract+0.044
ksh+0.042
 hips+0.041
Neg logit contributions
 vet-0.038
 hawk-0.035
 pilot-0.034
 or-0.034
 wing-0.032
Token other
Token ID584
Feature activation+1.20e+00

Pos logit contributions
 Luke+0.044
 Jack+0.043
 subtract+0.042
 gigg+0.042
igsaw+0.041
Neg logit contributions
 vet-0.034
 hawk-0.033
 mir-0.032
oster-0.032
 pilot-0.031
Token sweet
Token ID6029
Feature activation+5.89e-01

Pos logit contributions
 Jack+0.007
 Luke+0.007
 subtract+0.007
 gigg+0.007
 subt+0.007
Neg logit contributions
 vet-0.009
 hawk-0.009
 pilot-0.009
oster-0.009
 mir-0.008
Token and
Token ID290
Feature activation+6.07e-01

Pos logit contributions
 Jack+0.017
 Luke+0.017
 subtract+0.017
 gigg+0.017
 subt+0.017
Neg logit contributions
 vet-0.012
 hawk-0.011
 pilot-0.011
oster-0.011
 mir-0.011
Token soft
Token ID2705
Feature activation+5.74e-01

Pos logit contributions
igsaw+0.013
 subtract+0.013
 Luke+0.013
 subt+0.013
 hips+0.013
Neg logit contributions
 vet-0.016
 mir-0.015
 hawk-0.015
 wing-0.015
 crow-0.014
Token,
Token ID11
Feature activation-2.56e-01

Pos logit contributions
 Luke+0.014
 subtract+0.014
 Jack+0.013
 subt+0.013
 gigg+0.013
Neg logit contributions
 vet-0.015
 hawk-0.014
 pilot-0.014
 mir-0.014
oster-0.014
Token but
Token ID475
Feature activation+8.39e-01

Pos logit contributions
 vet+0.007
 hawk+0.007
oster+0.007
 pilot+0.007
 mir+0.007
Neg logit contributions
 Jack-0.005
 Luke-0.005
 gigg-0.005
 subtract-0.005
 subt-0.005
Token it
Token ID340
Feature activation+2.12e+00

Pos logit contributions
 Jack+0.018
 Luke+0.018
 subtract+0.018
 subt+0.018
 gigg+0.018
Neg logit contributions
 vet-0.023
 hawk-0.022
 pilot-0.022
oster-0.022
 mir-0.022
Token was
Token ID373
Feature activation+1.18e+00

Pos logit contributions
 subtract+0.054
 Luke+0.054
 subt+0.054
igsaw+0.054
 Jack+0.054
Neg logit contributions
 vet-0.050
 hawk-0.047
 pilot-0.046
oster-0.045
 mir-0.045
Token salty
Token ID36021
Feature activation+5.59e-01

Pos logit contributions
 Jack+0.026
 Luke+0.026
 subtract+0.026
 gigg+0.026
 subt+0.025
Neg logit contributions
 vet-0.032
 hawk-0.031
 pilot-0.030
oster-0.030
 mir-0.030
Token and
Token ID290
Feature activation+1.64e+00

Pos logit contributions
 subtract+0.015
 Luke+0.015
 subt+0.015
igsaw+0.015
 Jack+0.015
Neg logit contributions
 vet-0.012
 hawk-0.011
 pilot-0.011
 wing-0.011
 mir-0.011
Token crunch
Token ID23527
Feature activation+4.36e-01

Pos logit contributions
igsaw+0.038
 subtract+0.036
 subt+0.036
 Luke+0.035
 hips+0.033
Neg logit contributions
 vet-0.043
 wing-0.042
 mir-0.041
 hawk-0.041
 crow-0.039
Tokeny
Token ID88
Feature activation+3.31e-01

Pos logit contributions
 Jack+0.010
 Luke+0.009
 gigg+0.009
 subtract+0.009
igsaw+0.009
Neg logit contributions
 vet-0.013
 hawk-0.012
 pilot-0.012
oster-0.011
 mir-0.011
Token Do
Token ID2141
Feature activation+6.08e-01

Pos logit contributions
 Jack+0.030
 subtract+0.029
 Luke+0.029
 subt+0.028
 Jake+0.027
Neg logit contributions
 hawk-0.068
 vet-0.067
 mir-0.066
oster-0.066
 pilot-0.066
Token you
Token ID345
Feature activation+1.07e+00

Pos logit contributions
igsaw+0.016
 subt+0.016
 hips+0.016
 subtract+0.016
ksh+0.016
Neg logit contributions
 vet-0.014
 hawk-0.013
 pilot-0.012
 wing-0.012
 mir-0.012
Token know
Token ID760
Feature activation+3.73e-01

Pos logit contributions
 Jack+0.017
 gigg+0.017
 subtract+0.015
 Luke+0.015
 g+0.015
Neg logit contributions
 vet-0.038
 hawk-0.037
 pilot-0.036
oster-0.036
 mir-0.036
Token how
Token ID703
Feature activation+1.23e+00

Pos logit contributions
 Jack+0.007
 Luke+0.006
 subtract+0.006
 James+0.006
 gigg+0.006
Neg logit contributions
oster-0.013
 mir-0.012
 vet-0.012
 hawk-0.012
 pilot-0.011
Token dangerous
Token ID4923
Feature activation+9.01e-01

Pos logit contributions
 Jack+0.024
 subtract+0.022
 gigg+0.022
 hands+0.021
 Luke+0.021
Neg logit contributions
 vet-0.037
oster-0.037
 hawk-0.036
 pilot-0.036
 ranc-0.034
Token that
Token ID326
Feature activation+2.50e+00

Pos logit contributions
 Jack+0.019
 Luke+0.018
 subtract+0.017
 gigg+0.017
 James+0.016
Neg logit contributions
 vet-0.027
oster-0.026
 mir-0.025
 hawk-0.025
 pilot-0.025
Token is
Token ID318
Feature activation+3.85e-01

Pos logit contributions
 Jack+0.059
 Luke+0.057
 subtract+0.056
 gigg+0.054
 James+0.054
Neg logit contributions
 vet-0.067
oster-0.064
 hawk-0.063
 mir-0.062
 pilot-0.061
Token?
Token ID30
Feature activation+1.83e+00

Pos logit contributions
 Jack+0.008
 Luke+0.007
 subtract+0.007
 gigg+0.007
 boun+0.006
Neg logit contributions
oster-0.012
oral-0.011
 pilot-0.011
umber-0.011
 mir-0.011
Token You
Token ID921
Feature activation+4.47e-01

Pos logit contributions
 Jack+0.030
 Luke+0.029
 subtract+0.029
 subt+0.028
 James+0.027
Neg logit contributions
 hawk-0.061
 vet-0.061
 mir-0.060
oster-0.060
 pilot-0.059
Token could
Token ID714
Feature activation+5.84e-01

Pos logit contributions
 Jack+0.010
 gigg+0.009
 Luke+0.009
 subtract+0.009
 James+0.009
Neg logit contributions
 vet-0.013
 mir-0.013
 hawk-0.012
oster-0.012
oral-0.012
Token have
Token ID423
Feature activation+8.88e-01

Pos logit contributions
 Jack+0.013
 gigg+0.013
 subtract+0.013
 Luke+0.013
 g+0.012
Neg logit contributions
oster-0.015
 mir-0.015
 vet-0.015
 hawk-0.015
 pilot-0.015
Token friends
Token ID2460
Feature activation+8.84e-01

Pos logit contributions
 subtract+0.018
igsaw+0.017
 hips+0.017
 Luke+0.017
 subt+0.017
Neg logit contributions
 vet-0.019
 pilot-0.018
 hawk-0.018
 wing-0.017
 mir-0.017
Token.
Token ID13
Feature activation+6.98e-01

Pos logit contributions
 subtract+0.023
 subt+0.023
igsaw+0.022
 Luke+0.021
 sauces+0.021
Neg logit contributions
 vet-0.022
 pilot-0.021
 wing-0.020
 hawk-0.020
 or-0.020
Token They
Token ID1119
Feature activation+1.55e+00

Pos logit contributions
 subtract+0.018
 subt+0.018
ci+0.017
igsaw+0.017
 hips+0.017
Neg logit contributions
 vet-0.017
 mir-0.015
 hawk-0.015
oster-0.015
 wing-0.015
Token danced
Token ID39480
Feature activation+7.37e-01

Pos logit contributions
 subtract+0.028
 Luke+0.027
 Jack+0.027
 subt+0.027
igsaw+0.027
Neg logit contributions
 vet-0.049
 hawk-0.047
 pilot-0.046
oster-0.046
 wing-0.045
Token together
Token ID1978
Feature activation+1.99e+00

Pos logit contributions
 subtract+0.016
 subt+0.015
igsaw+0.015
 Luke+0.015
 hips+0.014
Neg logit contributions
 vet-0.020
 pilot-0.020
 hawk-0.019
oster-0.019
 wing-0.019
Token and
Token ID290
Feature activation+2.04e+00

Pos logit contributions
 subtract+0.051
 subt+0.050
igsaw+0.050
 Luke+0.049
 Jack+0.048
Neg logit contributions
 vet-0.047
 pilot-0.044
 hawk-0.043
 wing-0.043
oster-0.042
Token had
Token ID550
Feature activation+2.19e-01

Pos logit contributions
igsaw+0.049
 subtract+0.047
 hips+0.047
idents+0.045
ksh+0.044
Neg logit contributions
 pilot-0.049
 vet-0.048
 hawk-0.048
 wing-0.047
 mir-0.046
Token lots
Token ID6041
Feature activation-2.90e-01

Pos logit contributions
ci+0.006
hetically+0.006
igsaw+0.005
 hips+0.005
 subtract+0.005
Neg logit contributions
 vet-0.005
 wing-0.005
 mir-0.005
 hawk-0.005
 pilot-0.004
Token of
Token ID286
Feature activation+5.89e-01

Pos logit contributions
 vet+0.004
 hawk+0.003
 pilot+0.003
 mir+0.003
oster+0.003
Neg logit contributions
 Luke-0.010
 subtract-0.010
 Jack-0.010
 subt-0.010
 gigg-0.010
Token fun
Token ID1257
Feature activation+1.13e+00

Pos logit contributions
ci+0.009
 Luke+0.009
igsaw+0.009
 subtract+0.009
hetically+0.009
Neg logit contributions
 vet-0.019
 pilot-0.018
 mir-0.018
 hawk-0.018
 wing-0.018
Token.
Token ID13
Feature activation+1.09e+00

Pos logit contributions
igsaw+0.029
 Luke+0.029
 subtract+0.028
hetically+0.028
ksh+0.028
Neg logit contributions
 or-0.024
 pilot-0.024
 wing-0.023
 vet-0.023
 hawk-0.023
Token counted
Token ID14789
Feature activation+1.68e+00

Pos logit contributions
 Jack+0.055
 Luke+0.054
 subtract+0.054
 gigg+0.054
 subt+0.053
Neg logit contributions
 vet-0.071
 hawk-0.068
 wing-0.066
 pilot-0.066
oster-0.065
Token to
Token ID284
Feature activation+1.52e+00

Pos logit contributions
 Luke+0.037
 subtract+0.037
 subt+0.037
 Jack+0.037
igsaw+0.036
Neg logit contributions
 vet-0.045
 hawk-0.042
 pilot-0.042
 mir-0.041
 wing-0.041
Token ten
Token ID3478
Feature activation+2.41e+00

Pos logit contributions
 Luke+0.034
 Jack+0.034
igsaw+0.034
 subtract+0.034
 subt+0.033
Neg logit contributions
 vet-0.040
 pilot-0.037
 hawk-0.037
 mir-0.036
 wing-0.036
Token all
Token ID477
Feature activation+2.87e+00

Pos logit contributions
ci+0.074
idents+0.071
ksh+0.070
irms+0.069
arrass+0.068
Neg logit contributions
 or-0.044
 vet-0.040
 pilot-0.038
 mir-0.037
 hawk-0.037
Token of
Token ID286
Feature activation+1.40e+00

Pos logit contributions
irms+0.085
ksh+0.085
 wrists+0.083
idents+0.083
 hips+0.081
Neg logit contributions
 pilot-0.051
 vet-0.048
 or-0.047
 hawk-0.045
 adult-0.045
Token the
Token ID262
Feature activation+2.18e+00

Pos logit contributions
 subtract+0.032
 Luke+0.032
 subt+0.032
igsaw+0.032
 hips+0.032
Neg logit contributions
 vet-0.035
 hawk-0.033
 pilot-0.032
 mir-0.032
 wing-0.031
Token children
Token ID1751
Feature activation+2.85e+00

Pos logit contributions
ci+0.059
ishly+0.059
 wrists+0.058
icol+0.057
ksh+0.056
Neg logit contributions
 adult-0.043
 or-0.042
 grown-0.040
 doctor-0.040
 mir-0.039
Token cheered
Token ID34767
Feature activation+7.63e-01

Pos logit contributions
igsaw+0.073
irms+0.070
 subt+0.070
ksh+0.069
 Luke+0.069
Neg logit contributions
 vet-0.063
 pilot-0.062
 or-0.058
 hawk-0.058
 wing-0.057
Token,
Token ID11
Feature activation+2.17e-01

Pos logit contributions
 subtract+0.018
 subt+0.018
igsaw+0.017
 Luke+0.017
 gigg+0.017
Neg logit contributions
 vet-0.019
 pilot-0.018
 hawk-0.018
 wing-0.018
oster-0.018
Token they
Token ID484
Feature activation+2.33e+00

Pos logit contributions
 Jack+0.004
 Luke+0.004
 subtract+0.004
 gigg+0.004
 subt+0.004
Neg logit contributions
 vet-0.006
 hawk-0.006
oster-0.006
 mir-0.006
 pilot-0.006
Token had
Token ID550
Feature activation+1.63e+00

Pos logit contributions
igsaw+0.050
 subt+0.046
 subtract+0.046
irms+0.044
 hips+0.044
Neg logit contributions
 pilot-0.066
 vet-0.063
 hawk-0.062
oster-0.061
 wing-0.060
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
 vet+0.004
oster+0.004
 pilot+0.004
 hawk+0.004
 mir+0.004
Neg logit contributions
 Jack-0.001
 gigg-0.001
 Luke-0.001
 subtract-0.001
 hips-0.001
Token<|endoftext|>
Token ID50256
Feature activation+4.16e-01

Pos logit contributions
 vet+0.009
 hawk+0.008
 mir+0.008
 wing+0.008
 pilot+0.008
Neg logit contributions
 subtract-0.009
 wrists-0.009
 hips-0.009
 subt-0.009
 Luke-0.009
TokenOnce
Token ID7454
Feature activation+5.68e-01

Pos logit contributions
 subtract+0.011
 subt+0.011
 wrists+0.011
igsaw+0.011
 Luke+0.011
Neg logit contributions
 vet-0.009
 hawk-0.009
oster-0.008
 wing-0.008
 mir-0.008
Token upon
Token ID2402
Feature activation-1.19e+00

Pos logit contributions
 subtract+0.019
 subt+0.019
 wrists+0.018
 Luke+0.018
 gigg+0.018
Neg logit contributions
 vet-0.009
 hawk-0.009
 pilot-0.009
 mir-0.008
 wing-0.008
Token a
Token ID257
Feature activation+1.26e+00

Pos logit contributions
 vet+0.031
 hawk+0.029
 pilot+0.029
 mir+0.028
oster+0.028
Neg logit contributions
 Luke-0.028
 Jack-0.028
 subtract-0.028
 subt-0.027
 gigg-0.027
Token time
Token ID640
Feature activation-2.70e-03

Pos logit contributions
 subtract+0.049
 subt+0.048
 wrists+0.047
 Luke+0.046
igsaw+0.045
Neg logit contributions
 vet-0.015
oster-0.014
 hawk-0.013
 mir-0.013
 pilot-0.012
Token,
Token ID11
Feature activation-4.05e-03

Pos logit contributions
 vet+0.000
 hawk+0.000
 wing+0.000
 mir+0.000
 or+0.000
Neg logit contributions
 subtract-0.000
 wrists-0.000
 subt-0.000
irms-0.000
igsaw-0.000
Token there
Token ID612
Feature activation-4.40e-01

Pos logit contributions
 vet+0.000
 mir+0.000
 pilot+0.000
 hawk+0.000
oster+0.000
Neg logit contributions
 Jack-0.000
 Luke-0.000
 gigg-0.000
 James-0.000
 -0.000
Token was
Token ID373
Feature activation-3.40e-01

Pos logit contributions
 vet+0.011
 hawk+0.010
 pilot+0.010
oster+0.010
 mir+0.010
Neg logit contributions
 Jack-0.011
 Luke-0.011
 subtract-0.011
 gigg-0.011
 subt-0.011
Token a
Token ID257
Feature activation+9.22e-03

Pos logit contributions
 vet+0.010
 hawk+0.009
 pilot+0.009
oster+0.009
 mir+0.009
Neg logit contributions
 Jack-0.008
 Luke-0.007
 gigg-0.007
 subtract-0.007
igsaw-0.007
Token little
Token ID1310
Feature activation+1.28e+00

Pos logit contributions
 Jack+0.000
 Luke+0.000
 gigg+0.000
igsaw+0.000
 g+0.000
Neg logit contributions
 vet-0.000
 hawk-0.000
 wing-0.000
oster-0.000
 mir-0.000
Token.
Token ID13
Feature activation-7.41e-01

Pos logit contributions
 vet+0.005
 hawk+0.004
 pilot+0.004
 mir+0.004
oster+0.004
Neg logit contributions
 subtract-0.002
 Luke-0.002
 Jack-0.002
 subt-0.002
igsaw-0.002
Token<|endoftext|>
Token ID50256
Feature activation+1.27e-01

Pos logit contributions
 vet+0.022
 hawk+0.020
 pilot+0.020
 mir+0.020
oster+0.020
Neg logit contributions
 Luke-0.015
 subtract-0.015
 Jack-0.015
 subt-0.015
 gigg-0.014
TokenOnce
Token ID7454
Feature activation+3.80e-01

Pos logit contributions
 subtract+0.003
 Luke+0.003
 Jack+0.003
 subt+0.003
 gigg+0.003
Neg logit contributions
 vet-0.003
 hawk-0.003
 pilot-0.003
oster-0.003
 mir-0.003
Token upon
Token ID2402
Feature activation-1.20e+00

Pos logit contributions
 subtract+0.014
 subt+0.013
 wrists+0.013
 Luke+0.013
 gigg+0.013
Neg logit contributions
 vet-0.005
 pilot-0.005
 hawk-0.005
 mir-0.005
 wing-0.005
Token a
Token ID257
Feature activation+1.13e+00

Pos logit contributions
 vet+0.030
 hawk+0.028
 pilot+0.028
 mir+0.027
oster+0.027
Neg logit contributions
 subtract-0.029
 Luke-0.029
 subt-0.029
 Jack-0.029
igsaw-0.028
Token time
Token ID640
Feature activation+3.44e-03

Pos logit contributions
 subtract+0.049
 wrists+0.048
 subt+0.047
ci+0.045
nam+0.045
Neg logit contributions
 vet-0.009
oster-0.007
 mir-0.006
 hawk-0.006
oral-0.005
Token,
Token ID11
Feature activation-3.35e-01

Pos logit contributions
 wrists+0.000
 subtract+0.000
 subt+0.000
irms+0.000
 Luke+0.000
Neg logit contributions
 vet-0.000
 hawk-0.000
 mir-0.000
 pilot-0.000
 wing-0.000
Token there
Token ID612
Feature activation-4.27e-01

Pos logit contributions
 vet+0.008
 mir+0.008
 hawk+0.008
oster+0.008
 pilot+0.007
Neg logit contributions
 Jack-0.009
 Luke-0.009
 gigg-0.008
 James-0.008
 -0.008
Token was
Token ID373
Feature activation-7.75e-01

Pos logit contributions
 vet+0.010
 hawk+0.009
 pilot+0.009
oster+0.009
 mir+0.009
Neg logit contributions
 Luke-0.011
 Jack-0.011
 subtract-0.011
 subt-0.011
 gigg-0.011
Token an
Token ID281
Feature activation-4.32e-01

Pos logit contributions
 vet+0.022
 hawk+0.021
oster+0.021
 pilot+0.021
 mir+0.021
Neg logit contributions
 Jack-0.017
 Luke-0.016
 gigg-0.016
 subtract-0.016
igsaw-0.015
Token old
Token ID1468
Feature activation-1.27e+00

Pos logit contributions
 vet+0.012
 hawk+0.011
oster+0.011
 mir+0.011
 wing+0.011
Neg logit contributions
 Jack-0.010
 gigg-0.009
igsaw-0.009
 Luke-0.009
 subtract-0.009
Token moral
Token ID6573
Feature activation-2.01e+00

Pos logit contributions
 vet+0.008
 mir+0.008
oster+0.007
 hawk+0.007
 pilot+0.007
Neg logit contributions
 Jack-0.015
 Luke-0.015
 subtract-0.015
 gigg-0.015
 subt-0.015
Token of
Token ID286
Feature activation-2.26e-01

Pos logit contributions
 pilot+0.042
oster+0.041
 hawk+0.039
 mir+0.038
igi+0.037
Neg logit contributions
 Jack-0.056
 subtract-0.054
 subt-0.053
 Luke-0.051
 -0.051
Token the
Token ID262
Feature activation-1.14e+00

Pos logit contributions
 vet+0.007
 pilot+0.006
 hawk+0.006
oster+0.006
 mir+0.006
Neg logit contributions
 Jack-0.005
 Luke-0.005
 subtract-0.004
 gigg-0.004
igsaw-0.004
Token story
Token ID1621
Feature activation-2.08e+00

Pos logit contributions
 vet+0.022
oster+0.020
 pilot+0.020
 hawk+0.020
 mir+0.019
Neg logit contributions
 Jack-0.035
 Luke-0.034
 subtract-0.034
igsaw-0.034
 subt-0.033
Token is
Token ID318
Feature activation-1.48e+00

Pos logit contributions
 vet+0.059
 hawk+0.057
 pilot+0.056
 mir+0.056
oster+0.056
Neg logit contributions
 Jack-0.045
 Luke-0.044
 subtract-0.043
 subt-0.042
igsaw-0.042
Token that
Token ID326
Feature activation+5.55e-01

Pos logit contributions
 pilot+0.046
oster+0.046
 hawk+0.045
 vet+0.044
 mir+0.043
Neg logit contributions
 Jack-0.031
 subtract-0.026
 Luke-0.026
igsaw-0.025
 gigg-0.025
Token we
Token ID356
Feature activation-5.87e-01

Pos logit contributions
 Jack+0.012
 Luke+0.011
 subtract+0.011
 gigg+0.011
 subt+0.011
Neg logit contributions
 vet-0.016
oster-0.016
 hawk-0.015
 pilot-0.015
 mir-0.015
Token should
Token ID815
Feature activation-2.51e+00

Pos logit contributions
 vet+0.012
 hawk+0.011
 mir+0.011
 pilot+0.011
oster+0.011
Neg logit contributions
 Jack-0.017
 Luke-0.017
 subtract-0.017
 gigg-0.017
 subt-0.016
Token always
Token ID1464
Feature activation-1.54e+00

Pos logit contributions
 hawk+0.059
 vet+0.058
oster+0.057
 mir+0.057
 pilot+0.057
Neg logit contributions
 Jack-0.065
 subtract-0.063
 Luke-0.061
 gigg-0.061
 hips-0.059
Token forgive
Token ID20927
Feature activation+8.04e-01

Pos logit contributions
 vet+0.038
 hawk+0.036
 pilot+0.035
oster+0.035
 mir+0.035
Neg logit contributions
 subtract-0.038
 Jack-0.038
 Luke-0.038
 subt-0.037
 gigg-0.037
Token.
Token ID13
Feature activation-5.72e-01

Pos logit contributions
 Luke+0.018
 Jack+0.018
 subtract+0.018
 subt+0.018
 gigg+0.017
Neg logit contributions
 vet-0.022
 hawk-0.021
 pilot-0.020
oster-0.020
 mir-0.020
Token He
Token ID679
Feature activation-6.04e-01

Pos logit contributions
 Jack+0.001
 Luke+0.001
 subtract+0.001
 subt+0.001
igsaw+0.001
Neg logit contributions
 vet-0.001
 hawk-0.001
 pilot-0.001
oster-0.001
 mir-0.001
Token looked
Token ID3114
Feature activation+7.31e-01

Pos logit contributions
 vet+0.018
 hawk+0.017
oster+0.017
 pilot+0.016
 mir+0.016
Neg logit contributions
 gigg-0.013
 Luke-0.012
 Jack-0.012
 subtract-0.012
 subt-0.012
Token everywhere
Token ID8347
Feature activation+2.10e-01

Pos logit contributions
 subtract+0.015
 subt+0.014
 Luke+0.014
igsaw+0.014
 Jack+0.014
Neg logit contributions
 vet-0.022
 hawk-0.021
 pilot-0.020
 wing-0.020
 mir-0.020
Token but
Token ID475
Feature activation+2.27e-01

Pos logit contributions
 Jack+0.004
 Luke+0.004
 gigg+0.004
 subtract+0.004
 hips+0.004
Neg logit contributions
 vet-0.007
 hawk-0.006
oster-0.006
 pilot-0.006
 mir-0.006
Token could
Token ID714
Feature activation-3.84e-01

Pos logit contributions
 Jack+0.005
 Luke+0.005
 gigg+0.004
 James+0.004
 hips+0.004
Neg logit contributions
 vet-0.007
 hawk-0.007
oster-0.007
 pilot-0.007
 mir-0.007
Token not
Token ID407
Feature activation+3.53e-01

Pos logit contributions
 vet+0.009
 hawk+0.008
 mir+0.008
oster+0.008
 pilot+0.008
Neg logit contributions
 Jack-0.010
 Luke-0.010
 gigg-0.010
 subtract-0.010
 hips-0.010
Token find
Token ID1064
Feature activation+1.47e+00

Pos logit contributions
 Jack+0.007
 Luke+0.007
 gigg+0.007
 subtract+0.007
 hips+0.006
Neg logit contributions
 vet-0.010
 hawk-0.010
oster-0.010
 mir-0.010
 pilot-0.010
Token it
Token ID340
Feature activation+8.44e-01

Pos logit contributions
 subt+0.039
igsaw+0.038
 subtract+0.038
 Luke+0.037
 gigg+0.037
Neg logit contributions
 vet-0.035
 hawk-0.033
 pilot-0.032
 wing-0.032
 mir-0.030
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
 Jack+0.011
 Luke+0.010
 gigg+0.009
 James+0.009
 hips+0.009
Neg logit contributions
 vet-0.032
 hawk-0.031
oster-0.031
 mir-0.031
 pilot-0.031
Token Tom
Token ID4186
Feature activation-2.84e-01

Pos logit contributions
 subtract+0.003
 subt+0.003
 gigg+0.003
igsaw+0.003
 Luke+0.003
Neg logit contributions
 vet-0.003
 hawk-0.003
 wing-0.003
 pilot-0.003
 mir-0.003
Token felt
Token ID2936
Feature activation-1.42e+00

Pos logit contributions
 vet+0.008
 hawk+0.008
 mir+0.008
 pilot+0.008
oster+0.008
Neg logit contributions
 gigg-0.006
 Jack-0.006
 Luke-0.006
 subtract-0.006
 hips-0.006
Token wanted
Token ID2227
Feature activation+1.78e+00

Pos logit contributions
 Luke+0.048
igsaw+0.047
 subtract+0.047
 Jack+0.047
 subt+0.046
Neg logit contributions
 vet-0.052
 hawk-0.048
 pilot-0.048
 mir-0.048
 wing-0.047
Token to
Token ID284
Feature activation-4.67e-02

Pos logit contributions
 Jack+0.036
 Luke+0.036
 subtract+0.036
 gigg+0.035
 subt+0.035
Neg logit contributions
 vet-0.052
 hawk-0.050
 pilot-0.049
oster-0.049
 mir-0.048
Token try
Token ID1949
Feature activation+2.21e-01

Pos logit contributions
 vet+0.001
 hawk+0.001
oster+0.001
 pilot+0.001
 mir+0.001
Neg logit contributions
 subtract-0.001
 Jack-0.001
 gigg-0.001
 Luke-0.001
 subt-0.001
Token something
Token ID1223
Feature activation+9.38e-01

Pos logit contributions
 subtract+0.005
 Luke+0.005
 subt+0.005
igsaw+0.005
 Jack+0.005
Neg logit contributions
 vet-0.005
 wing-0.005
 hawk-0.005
 mir-0.005
 pilot-0.005
Token new
Token ID649
Feature activation+1.18e+00

Pos logit contributions
 Luke+0.021
 subtract+0.021
 Jack+0.021
 subt+0.020
igsaw+0.020
Neg logit contributions
 vet-0.025
 hawk-0.024
 pilot-0.024
 mir-0.023
 wing-0.023
Token.
Token ID13
Feature activation+6.54e-01

Pos logit contributions
 Luke+0.025
 subtract+0.025
 subt+0.025
 Jack+0.024
igsaw+0.024
Neg logit contributions
 vet-0.033
 wing-0.031
 hawk-0.031
 pilot-0.031
 mir-0.030
Token<|endoftext|>
Token ID50256
Feature activation+7.58e-01

Pos logit contributions
 subtract+0.017
 hips+0.017
 wrists+0.017
 subt+0.017
 gigg+0.017
Neg logit contributions
 vet-0.016
 pilot-0.013
 mir-0.013
 hawk-0.013
 veterinarian-0.013
TokenOnce
Token ID7454
Feature activation+6.63e-01

Pos logit contributions
 subtract+0.020
 subt+0.020
 wrists+0.019
 Luke+0.019
 hips+0.019
Neg logit contributions
 vet-0.018
 hawk-0.016
oster-0.016
 pilot-0.016
 mir-0.016
Token upon
Token ID2402
Feature activation-8.37e-01

Pos logit contributions
 subt+0.024
 subtract+0.024
 wrists+0.023
 Luke+0.022
 gigg+0.022
Neg logit contributions
 vet-0.010
 pilot-0.009
 hawk-0.009
 wing-0.008
 mir-0.008
Token a
Token ID257
Feature activation+1.66e+00

Pos logit contributions
 vet+0.020
 hawk+0.018
 pilot+0.018
 wing+0.018
 mir+0.017
Neg logit contributions
 subt-0.022
 subtract-0.022
igsaw-0.021
 Luke-0.021
 Jack-0.021
Token time
Token ID640
Feature activation+4.82e-01

Pos logit contributions
 subtract+0.069
 subt+0.067
 wrists+0.066
ci+0.063
 Luke+0.063
Neg logit contributions
 vet-0.016
oster-0.013
 hawk-0.013
 mir-0.013
 pilot-0.011
Token.
Token ID13
Feature activation-7.97e-02

Pos logit contributions
 vet+0.024
 hawk+0.022
 pilot+0.022
 mir+0.022
oster+0.022
Neg logit contributions
 subtract-0.014
 Luke-0.014
 subt-0.013
 Jack-0.013
igsaw-0.013
Token When
Token ID1649
Feature activation+1.12e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
 pilot+0.002
 mir+0.002
oster+0.002
Neg logit contributions
 Luke-0.002
 subtract-0.002
 Jack-0.002
 subt-0.002
 gigg-0.002
Token he
Token ID339
Feature activation+6.19e-01

Pos logit contributions
 Jack+0.002
 Luke+0.002
 James+0.002
 subtract+0.002
 subt+0.002
Neg logit contributions
 vet-0.004
oster-0.003
 hawk-0.003
 wing-0.003
 pilot-0.003
Token got
Token ID1392
Feature activation+3.19e-02

Pos logit contributions
 Jack+0.012
 gigg+0.012
 Luke+0.011
 laughed+0.010
 +0.010
Neg logit contributions
 hawk-0.021
 wing-0.021
 vet-0.021
oster-0.020
 pilot-0.019
Token there
Token ID612
Feature activation-2.04e-01

Pos logit contributions
 Jack+0.001
 Luke+0.001
 gigg+0.001
 James+0.001
 subtract+0.001
Neg logit contributions
 vet-0.001
 hawk-0.001
oster-0.001
 pilot-0.001
 mir-0.001
Token,
Token ID11
Feature activation-4.65e-01

Pos logit contributions
 vet+0.007
 hawk+0.007
oster+0.007
 wing+0.007
 mir+0.007
Neg logit contributions
 Jack-0.004
 Luke-0.003
 James-0.003
 gigg-0.003
 Alex-0.003
Token the
Token ID262
Feature activation-7.40e-01

Pos logit contributions
 vet+0.013
 hawk+0.013
 pilot+0.012
oster+0.012
 mir+0.012
Neg logit contributions
 Jack-0.010
 Luke-0.010
 subtract-0.010
 subt-0.009
 gigg-0.009
Token grown
Token ID7334
Feature activation-2.07e+00

Pos logit contributions
 hawk+0.018
 vet+0.017
 wing+0.017
 mir+0.017
oster+0.017
Neg logit contributions
 Jack-0.018
 Luke-0.018
 subtract-0.018
 subt-0.018
 gigg-0.018
Token-
Token ID12
Feature activation-6.40e-02

Pos logit contributions
 vet+0.053
 hawk+0.050
 pilot+0.049
oster+0.049
 mir+0.049
Neg logit contributions
 Luke-0.050
 Jack-0.050
 subtract-0.050
 subt-0.049
igsaw-0.048
Tokenups
Token ID4739
Feature activation-1.12e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
 pilot+0.002
 mir+0.002
 wing+0.001
Neg logit contributions
 subtract-0.002
 Jack-0.002
 Luke-0.002
 subt-0.001
 gigg-0.001
Token asked
Token ID1965
Feature activation+3.20e-01

Pos logit contributions
 vet+0.003
 hawk+0.003
 mir+0.003
oster+0.003
 wing+0.003
Neg logit contributions
 Jack-0.002
 gigg-0.002
 subtract-0.002
 Luke-0.002
 subt-0.002
Token.
Token ID13
Feature activation-8.38e-01

Pos logit contributions
 vet+0.006
 hawk+0.006
 pilot+0.006
oster+0.006
 mir+0.006
Neg logit contributions
 Luke-0.004
 subtract-0.004
 Jack-0.004
 subt-0.004
igsaw-0.004
Token They
Token ID1119
Feature activation-9.04e-02

Pos logit contributions
 vet+0.026
 hawk+0.026
 pilot+0.025
oster+0.025
 mir+0.025
Neg logit contributions
 Jack-0.016
 Luke-0.015
 subtract-0.015
 subt-0.015
 gigg-0.015
Token hugged
Token ID41130
Feature activation-2.12e-01

Pos logit contributions
 vet+0.002
 hawk+0.002
 pilot+0.002
 mir+0.002
oster+0.002
Neg logit contributions
 Luke-0.002
 Jack-0.002
 subtract-0.002
 subt-0.002
 gigg-0.002
Token and
Token ID290
Feature activation-1.87e-01

Pos logit contributions
 hawk+0.007
 mir+0.007
oster+0.007
 vet+0.006
 pilot+0.006
Neg logit contributions
 Jack-0.004
 gigg-0.004
 Luke-0.004
 hands-0.004
 wrists-0.004
Token smiled
Token ID13541
Feature activation-6.16e-01

Pos logit contributions
 vet+0.005
 pilot+0.005
 wing+0.005
 mir+0.004
 hawk+0.004
Neg logit contributions
igsaw-0.004
 subtract-0.004
 Luke-0.004
 hips-0.004
idents-0.004
Token.
Token ID13
Feature activation-9.15e-01

Pos logit contributions
 vet+0.020
 hawk+0.020
oster+0.020
 mir+0.019
 pilot+0.019
Neg logit contributions
 Jack-0.011
 gigg-0.010
 Luke-0.010
 subtract-0.009
 hips-0.009
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
 hawk+0.029
 vet+0.029
 pilot+0.028
oster+0.028
 mir+0.028
Neg logit contributions
 Jack-0.017
 Luke-0.016
 subtract-0.016
 subt-0.016
 gigg-0.015
Token
Token ID198
Feature activation-8.04e-01

Pos logit contributions
 vet+0.009
 hawk+0.009
 pilot+0.009
 mir+0.008
oster+0.008
Neg logit contributions
 Jack-0.007
 Luke-0.007
 subtract-0.007
 gigg-0.006
 subt-0.006
TokenThey
Token ID2990
Feature activation-2.07e-01

Pos logit contributions
 hawk+0.023
 mir+0.022
 pilot+0.022
 wing+0.021
 vet+0.021
Neg logit contributions
 subtract-0.018
 subt-0.018
 -0.018
 Jack-0.017
 Luke-0.017
Token went
Token ID1816
Feature activation-3.02e-01

Pos logit contributions
 vet+0.005
 hawk+0.005
 pilot+0.005
 mir+0.005
oster+0.005
Neg logit contributions
 Jack-0.005
 Luke-0.005
 subtract-0.005
 gigg-0.005
 subt-0.005
Token to
Token ID284
Feature activation+2.31e-01

Pos logit contributions
 vet+0.008
 hawk+0.007
 pilot+0.007
oster+0.007
 mir+0.007
Neg logit contributions
 Jack-0.007
 Luke-0.007
 subtract-0.007
 gigg-0.007
 subt-0.007
Token was
Token ID373
Feature activation-4.59e-01

Pos logit contributions
 vet+0.010
 hawk+0.009
 pilot+0.009
oster+0.009
 mir+0.009
Neg logit contributions
 Jack-0.010
 Luke-0.010
 gigg-0.010
 subtract-0.010
 subt-0.009
Token a
Token ID257
Feature activation-1.94e-02

Pos logit contributions
 vet+0.012
 hawk+0.012
 pilot+0.012
oster+0.012
 mir+0.012
Neg logit contributions
 Jack-0.010
 Luke-0.010
 subtract-0.010
 gigg-0.010
 subt-0.010
Token little
Token ID1310
Feature activation+1.17e+00

Pos logit contributions
 vet+0.000
 hawk+0.000
 wing+0.000
oster+0.000
 mir+0.000
Neg logit contributions
 Jack-0.001
 Luke-0.001
 gigg-0.001
igsaw-0.000
 subtract-0.000
Token girl
Token ID2576
Feature activation-5.86e-01

Pos logit contributions
 subtract+0.033
 subt+0.032
 Luke+0.032
 Jack+0.031
 hips+0.031
Neg logit contributions
 vet-0.026
 hawk-0.025
 pilot-0.025
 wing-0.023
 mir-0.023
Token named
Token ID3706
Feature activation-2.47e-03

Pos logit contributions
 vet+0.008
 pilot+0.007
 hawk+0.007
 wing+0.007
 mir+0.007
Neg logit contributions
 subtract-0.021
 Luke-0.021
igsaw-0.021
 subt-0.021
 Jack-0.021
Token Lily
Token ID20037
Feature activation-1.08e+00

Pos logit contributions
 vet+0.000
 wing+0.000
 hen+0.000
 pilot+0.000
 mir+0.000
Neg logit contributions
 subtract-0.000
 subt-0.000
 wrists-0.000
 Luke-0.000
 hips-0.000
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
 vet+0.028
 pilot+0.027
 wing+0.026
 hawk+0.025
 mir+0.024
Neg logit contributions
 subtract-0.028
 subt-0.028
igsaw-0.028
 Luke-0.026
 hips-0.026
Token She
Token ID1375
Feature activation-7.24e-01

Pos logit contributions
 vet+0.005
 or+0.004
 wing+0.004
 veterinarian+0.004
 mir+0.004
Neg logit contributions
 subtract-0.007
ci-0.007
 subt-0.006
 wrists-0.006
 Luke-0.006
Token was
Token ID373
Feature activation+6.43e-01

Pos logit contributions
 vet+0.021
 hawk+0.021
 pilot+0.020
 mir+0.020
oster+0.020
Neg logit contributions
 Jack-0.015
 gigg-0.015
 Luke-0.014
 subtract-0.014
 subt-0.014
Token playing
Token ID2712
Feature activation-6.58e-03

Pos logit contributions
 Luke+0.015
 subtract+0.015
 Jack+0.014
 subt+0.014
igsaw+0.014
Neg logit contributions
 vet-0.017
 hawk-0.016
 pilot-0.016
 mir-0.016
oster-0.016
Token in
Token ID287
Feature activation+7.44e-01

Pos logit contributions
 vet+0.000
 hawk+0.000
 pilot+0.000
 mir+0.000
oster+0.000
Neg logit contributions
 Luke-0.000
 Jack-0.000
 subtract-0.000
 subt-0.000
 gigg-0.000
Token mom
Token ID1995
Feature activation-6.30e-01

Pos logit contributions
 vet+0.032
oster+0.032
 mir+0.031
 hawk+0.031
 pilot+0.031
Neg logit contributions
 gigg-0.025
 Jack-0.025
 Luke-0.025
 hands-0.024
 subtract-0.024
Tokenmy
Token ID1820
Feature activation-1.08e+00

Pos logit contributions
 mir+0.020
 hawk+0.020
oster+0.020
 vet+0.019
 wing+0.018
Neg logit contributions
 Jack-0.012
 gigg-0.011
 Luke-0.011
 Emily-0.010
 Jake-0.010
Token gave
Token ID2921
Feature activation+1.65e+00

Pos logit contributions
 mir+0.032
oster+0.031
 hawk+0.031
 vet+0.031
 pilot+0.030
Neg logit contributions
 Jack-0.022
 gigg-0.021
 Luke-0.021
 Emily-0.019
 -0.019
Token him
Token ID683
Feature activation-2.06e+00

Pos logit contributions
 subtract+0.040
 subt+0.040
 wrists+0.039
 hips+0.039
igsaw+0.038
Neg logit contributions
 vet-0.043
 wing-0.040
 hawk-0.040
 pilot-0.039
oster-0.037
Token some
Token ID617
Feature activation-1.95e+00

Pos logit contributions
 vet+0.054
 hawk+0.050
 pilot+0.049
 wing+0.049
oster+0.049
Neg logit contributions
 subtract-0.049
 Luke-0.048
 subt-0.048
 Jack-0.047
igsaw-0.047
Token medicine
Token ID9007
Feature activation-1.38e+00

Pos logit contributions
 pilot+0.058
 hawk+0.055
oster+0.055
reetings+0.055
igi+0.053
Neg logit contributions
 hands-0.038
 hugs-0.037
 g-0.034
 Jack-0.034
 spaghetti-0.034
Token and
Token ID290
Feature activation-1.13e+00

Pos logit contributions
 vet+0.035
 pilot+0.034
 hawk+0.034
 mir+0.033
oster+0.033
Neg logit contributions
 Jack-0.034
 Luke-0.033
 gigg-0.032
 subtract-0.031
 hips-0.031
Token he
Token ID339
Feature activation-3.60e-01

Pos logit contributions
 vet+0.034
oster+0.033
 hawk+0.033
 pilot+0.033
 mir+0.033
Neg logit contributions
 Jack-0.023
 Luke-0.021
 gigg-0.021
 subtract-0.020
 subt-0.020
Token felt
Token ID2936
Feature activation-1.63e+00

Pos logit contributions
 hawk+0.011
 vet+0.011
 mir+0.011
 pilot+0.011
oster+0.010
Neg logit contributions
 gigg-0.007
 Jack-0.007
 Luke-0.007
 subtract-0.006
 James-0.006
Token better
Token ID1365
Feature activation-8.00e-01

Pos logit contributions
 hawk+0.045
 pilot+0.045
 vet+0.045
oster+0.044
 mir+0.042
Neg logit contributions
 Jack-0.034
 gigg-0.034
 g-0.032
 -0.032
 Luke-0.032
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
 vet+0.025
 hawk+0.024
 pilot+0.024
oster+0.023
 mir+0.023
Neg logit contributions
 Luke-0.014
 Jack-0.014
 subtract-0.014
 subt-0.014
 gigg-0.014
Token glove
Token ID29144
Feature activation-9.11e-02

Pos logit contributions
 vet+0.018
 hawk+0.017
 pilot+0.017
oster+0.017
 mir+0.017
Neg logit contributions
 Luke-0.016
 Jack-0.016
 subtract-0.016
 gigg-0.016
 subt-0.016
Token back
Token ID736
Feature activation-3.19e-01

Pos logit contributions
 vet+0.003
 mir+0.003
 hawk+0.003
oral+0.002
 pilot+0.002
Neg logit contributions
 hips-0.002
 Jack-0.002
 gigg-0.002
 hands-0.002
 Luke-0.002
Token on
Token ID319
Feature activation+3.18e-02

Pos logit contributions
 vet+0.010
 hawk+0.009
oster+0.009
 mir+0.009
 pilot+0.009
Neg logit contributions
 Jack-0.007
 gigg-0.006
 hips-0.006
 hands-0.006
ci-0.006
Token.
Token ID13
Feature activation+4.41e-01

Pos logit contributions
 Jack+0.001
 Luke+0.001
 James+0.001
 gigg+0.001
 hips+0.000
Neg logit contributions
oster-0.001
 vet-0.001
 mir-0.001
 pilot-0.001
 hawk-0.001
Token He
Token ID679
Feature activation-4.89e-02

Pos logit contributions
 Luke+0.010
 subtract+0.010
 wrists+0.010
 gigg+0.010
 subt+0.010
Neg logit contributions
 vet-0.012
 hawk-0.010
 wing-0.010
 mir-0.010
 pilot-0.010
Token remembered
Token ID12086
Feature activation-1.20e+00

Pos logit contributions
 vet+0.001
 hawk+0.001
 mir+0.001
oster+0.001
 pilot+0.001
Neg logit contributions
 gigg-0.001
 Jack-0.001
 Luke-0.001
 wrists-0.001
 subtract-0.001
Token just
Token ID655
Feature activation-1.11e+00

Pos logit contributions
oster+0.041
 vet+0.039
 hawk+0.038
 pilot+0.038
 mir+0.037
Neg logit contributions
 Jack-0.024
 gigg-0.021
 Luke-0.021
 subtract-0.019
 James-0.018
Token as
Token ID355
Feature activation-3.04e-01

Pos logit contributions
 vet+0.030
 hawk+0.028
 pilot+0.028
oster+0.028
 mir+0.028
Neg logit contributions
 Luke-0.025
 Jack-0.025
 subtract-0.025
 subt-0.024
 gigg-0.024
Token he
Token ID339
Feature activation-3.43e-01

Pos logit contributions
 vet+0.009
 hawk+0.008
oster+0.008
 mir+0.008
 pilot+0.008
Neg logit contributions
 Jack-0.007
 Luke-0.007
 gigg-0.006
 subtract-0.006
igsaw-0.006
Token was
Token ID373
Feature activation-3.16e-01

Pos logit contributions
 vet+0.010
 hawk+0.010
 wing+0.010
 mir+0.010
 pilot+0.010
Neg logit contributions
 gigg-0.007
 wrists-0.006
 subtract-0.006
 Jack-0.006
ci-0.006
Token about
Token ID546
Feature activation-2.65e-01

Pos logit contributions
 vet+0.011
 hawk+0.011
oster+0.010
 pilot+0.010
 mir+0.010
Neg logit contributions
 gigg-0.005
 Jack-0.005
 Luke-0.005
 subtract-0.005
 hips-0.004
Token.
Token ID13
Feature activation-2.95e-01

Pos logit contributions
 Jack+0.001
 Luke+0.001
 subtract+0.000
 gigg+0.000
 subt+0.000
Neg logit contributions
 vet-0.001
 hawk-0.001
 pilot-0.001
oster-0.001
 mir-0.001
Token And
Token ID843
Feature activation-6.75e-01

Pos logit contributions
 vet+0.008
 hawk+0.007
 pilot+0.007
 wing+0.007
 mir+0.007
Neg logit contributions
 subtract-0.007
 Luke-0.007
 subt-0.007
 gigg-0.007
 hips-0.007
Token so
Token ID523
Feature activation+2.10e-01

Pos logit contributions
 vet+0.020
oster+0.020
 hawk+0.019
 mir+0.019
 pilot+0.019
Neg logit contributions
 Jack-0.015
 Luke-0.014
 gigg-0.013
 subtract-0.013
 subt-0.012
Token,
Token ID11
Feature activation-3.71e-01

Pos logit contributions
 Jack+0.004
 Luke+0.004
 subtract+0.004
 gigg+0.004
 subt+0.004
Neg logit contributions
 vet-0.006
 hawk-0.006
 pilot-0.006
 mir-0.006
oster-0.006
Token the
Token ID262
Feature activation-2.40e+00

Pos logit contributions
 vet+0.011
oster+0.011
 mir+0.011
 hawk+0.011
 pilot+0.011
Neg logit contributions
 Jack-0.007
 Luke-0.007
 gigg-0.007
 subtract-0.006
 -0.006
Token sw
Token ID1509
Feature activation-4.41e+00

Pos logit contributions
 vet+0.054
oster+0.051
 pilot+0.049
resp+0.048
 mir+0.047
Neg logit contributions
 gigg-0.061
 g-0.056
 -0.056
 hands-0.056
 Jack-0.055
Tokenan
Token ID272
Feature activation-9.17e-01

Pos logit contributions
 vet+0.093
 hawk+0.083
 pilot+0.083
 hen+0.080
God+0.079
Neg logit contributions
 gigg-0.122
ci-0.117
 shoulders-0.116
 hands-0.116
 hips-0.116
Token continued
Token ID3767
Feature activation-3.38e-01

Pos logit contributions
 vet+0.026
 hawk+0.025
 mir+0.024
 vaccine+0.023
oral+0.023
Neg logit contributions
 gigg-0.020
 Jack-0.019
ci-0.018
 Luke-0.018
 laughed-0.018
Token to
Token ID284
Feature activation-7.78e-01

Pos logit contributions
 vet+0.009
 hawk+0.009
oster+0.009
 pilot+0.009
 mir+0.008
Neg logit contributions
 Jack-0.008
 gigg-0.008
 Luke-0.007
 subtract-0.007
 subt-0.007
Token live
Token ID2107
Feature activation-1.91e+00

Pos logit contributions
 vet+0.023
 hawk+0.022
 pilot+0.022
oster+0.022
 mir+0.021
Neg logit contributions
 gigg-0.016
 Jack-0.015
 Luke-0.015
 g-0.015
 subtract-0.015
Token in
Token ID287
Feature activation-4.81e-01

Pos logit contributions
 vet+0.056
 hawk+0.053
 pilot+0.051
 mir+0.051
oster+0.050
Neg logit contributions
 Jack-0.041
 gigg-0.040
 Luke-0.039
 hips-0.036
 hands-0.036
Token again
Token ID757
Feature activation-4.14e-01

Pos logit contributions
 vet+0.020
 hawk+0.019
 pilot+0.019
oster+0.019
 mir+0.019
Neg logit contributions
 Jack-0.013
 Luke-0.013
 subtract-0.013
 gigg-0.012
igsaw-0.012
Token.
Token ID13
Feature activation-9.62e-01

Pos logit contributions
 vet+0.015
oster+0.015
 pilot+0.015
 hawk+0.015
 mir+0.014
Neg logit contributions
 Jack-0.006
 Luke-0.005
 gigg-0.005
 hips-0.005
 subtract-0.005
Token
Token ID198
Feature activation-7.00e-01

Pos logit contributions
 hawk+0.030
 vet+0.030
 pilot+0.030
oster+0.030
 mir+0.030
Neg logit contributions
 Jack-0.018
 Luke-0.017
 subtract-0.016
 subt-0.016
 James-0.016
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
 vet+0.019
 hawk+0.019
 pilot+0.019
 mir+0.018
oster+0.018
Neg logit contributions
 Jack-0.015
 Luke-0.015
 subtract-0.015
 gigg-0.014
 subt-0.014
TokenThey
Token ID2990
Feature activation-5.27e-01

Pos logit contributions
 mir+0.027
 hawk+0.026
 pilot+0.026
 wing+0.025
 vet+0.025
Neg logit contributions
 Luke-0.026
 Jack-0.025
 subtract-0.025
 subt-0.025
 -0.024
Token learned
Token ID4499
Feature activation-3.35e+00

Pos logit contributions
 vet+0.015
 hawk+0.014
 pilot+0.014
 wing+0.014
 mir+0.014
Neg logit contributions
 Jack-0.011
 gigg-0.011
 Luke-0.011
 subtract-0.011
 subt-0.011
Token that
Token ID326
Feature activation-5.80e-01

Pos logit contributions
oster+0.101
 hawk+0.099
 pilot+0.098
 mir+0.096
 vet+0.095
Neg logit contributions
 Jack-0.065
 gigg-0.062
 Luke-0.060
 subtract-0.059
 shoulders-0.058
Token digging
Token ID18894
Feature activation-2.84e+00

Pos logit contributions
oster+0.017
 vet+0.016
 pilot+0.016
 hawk+0.015
 mir+0.015
Neg logit contributions
 Jack-0.013
 gigg-0.012
 Luke-0.012
 subtract-0.012
 subt-0.011
Token a
Token ID257
Feature activation-8.79e-01

Pos logit contributions
 vet+0.083
 pilot+0.081
 hawk+0.079
oster+0.076
 mir+0.076
Neg logit contributions
 Jack-0.061
 gigg-0.059
 Luke-0.058
 laughs-0.058
 hands-0.056
Token tunnel
Token ID13275
Feature activation-1.96e+00

Pos logit contributions
 vet+0.023
 pilot+0.023
oster+0.023
 hawk+0.022
 ranc+0.021
Neg logit contributions
 boun-0.017
 Jack-0.017
 hands-0.017
 g-0.016
 gigg-0.016
Token was
Token ID373
Feature activation-1.69e+00

Pos logit contributions
 vet+0.054
 hawk+0.052
 pilot+0.051
 mir+0.051
oster+0.050
Neg logit contributions
 Jack-0.043
 Luke-0.042
 subtract-0.042
 gigg-0.041
 subt-0.041
Token.
Token ID13
Feature activation+6.43e-01

Pos logit contributions
 subtract+0.010
 subt+0.010
 Luke+0.010
igsaw+0.010
 Jack+0.009
Neg logit contributions
 vet-0.008
 hawk-0.008
 wing-0.008
 pilot-0.008
 mir-0.007
Token He
Token ID679
Feature activation-2.57e-01

Pos logit contributions
igsaw+0.018
 wrists+0.017
 gigg+0.017
 subt+0.017
 hips+0.017
Neg logit contributions
 vet-0.015
 hawk-0.012
oster-0.012
 doctor-0.012
 pilot-0.011
Token gave
Token ID2921
Feature activation+1.15e+00

Pos logit contributions
 hawk+0.008
 mir+0.008
 pilot+0.008
 vet+0.008
 wing+0.008
Neg logit contributions
 gigg-0.004
 Jack-0.004
 Luke-0.004
 subtract-0.004
 subt-0.004
Token him
Token ID683
Feature activation-1.38e+00

Pos logit contributions
 subtract+0.033
igsaw+0.032
 subt+0.032
 hips+0.031
 wrists+0.031
Neg logit contributions
 vet-0.026
 hawk-0.024
 pilot-0.024
 wing-0.023
oster-0.022
Token his
Token ID465
Feature activation-1.82e+00

Pos logit contributions
 vet+0.033
 wing+0.029
 hawk+0.029
 pilot+0.028
oster+0.028
Neg logit contributions
 subtract-0.037
 subt-0.037
igsaw-0.035
 Luke-0.035
 hips-0.035
Token own
Token ID898
Feature activation-3.11e+00

Pos logit contributions
 vet+0.050
 hawk+0.047
 pilot+0.047
oster+0.046
 mir+0.046
Neg logit contributions
 Luke-0.040
 Jack-0.040
 subtract-0.040
 subt-0.039
 gigg-0.039
Token bag
Token ID6131
Feature activation-2.18e+00

Pos logit contributions
 vet+0.090
 hawk+0.087
 pilot+0.085
oster+0.084
 mir+0.084
Neg logit contributions
 Jack-0.063
 Luke-0.062
 subtract-0.062
 gigg-0.061
igsaw-0.060
Token of
Token ID286
Feature activation-2.27e+00

Pos logit contributions
 vet+0.048
 hawk+0.046
 pilot+0.044
 mir+0.044
oster+0.043
Neg logit contributions
 Jack-0.061
 Luke-0.060
 subtract-0.059
 gigg-0.058
igsaw-0.058
Token food
Token ID2057
Feature activation-1.20e+00

Pos logit contributions
 vet+0.064
 hawk+0.060
 mir+0.059
 pilot+0.059
 wing+0.058
Neg logit contributions
 Luke-0.049
 subtract-0.048
 subt-0.048
 Jack-0.048
igsaw-0.047
Token and
Token ID290
Feature activation-8.07e-01

Pos logit contributions
 vet+0.030
 hawk+0.029
 pilot+0.029
oster+0.028
 mir+0.027
Neg logit contributions
 Jack-0.030
 Luke-0.029
 gigg-0.029
 subtract-0.028
 hips-0.028
Token said
Token ID531
Feature activation-4.43e-01

Pos logit contributions
 vet+0.023
 hawk+0.022
 pilot+0.021
 mir+0.021
 wing+0.021
Neg logit contributions
 subtract-0.017
 Luke-0.017
 Jack-0.017
 subt-0.017
igsaw-0.017
Token time
Token ID640
Feature activation+1.11e-01

Pos logit contributions
 subtract+0.043
 subt+0.042
 wrists+0.041
ci+0.039
igsaw+0.039
Neg logit contributions
 vet-0.011
oster-0.009
 hawk-0.009
 mir-0.008
 pilot-0.008
Token,
Token ID11
Feature activation-3.56e-01

Pos logit contributions
 subtract+0.003
 wrists+0.003
 subt+0.003
 Luke+0.003
irms+0.003
Neg logit contributions
 vet-0.002
 hawk-0.002
 wing-0.002
 pilot-0.002
 or-0.002
Token in
Token ID287
Feature activation-6.03e-01

Pos logit contributions
 vet+0.009
 mir+0.008
 hawk+0.008
 pilot+0.008
oster+0.008
Neg logit contributions
 Jack-0.009
 Luke-0.009
 gigg-0.009
 James-0.009
 -0.008
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
 vet+0.015
 hawk+0.015
 pilot+0.014
oster+0.014
 mir+0.014
Neg logit contributions
 subtract-0.014
 Luke-0.014
 Jack-0.014
 subt-0.014
 gigg-0.014
Token big
Token ID1263
Feature activation+9.57e-01

Pos logit contributions
 Luke+0.026
 Jack+0.026
 gigg+0.025
 subtract+0.025
igsaw+0.025
Neg logit contributions
 vet-0.027
 hawk-0.026
 mir-0.025
 pilot-0.025
oster-0.025
Token forest
Token ID8222
Feature activation-2.97e+00

Pos logit contributions
 Jack+0.026
 Luke+0.026
 subtract+0.025
 gigg+0.025
igsaw+0.025
Neg logit contributions
 vet-0.022
 hawk-0.020
oster-0.020
 pilot-0.020
 mir-0.020
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
 vet+0.099
 hawk+0.093
 mir+0.093
 pilot+0.092
oster+0.092
Neg logit contributions
 Jack-0.050
 gigg-0.047
 Luke-0.046
 hands-0.043
igsaw-0.043
Token there
Token ID612
Feature activation-9.64e-01

Pos logit contributions
 vet+0.034
 hawk+0.031
 mir+0.031
 pilot+0.031
oster+0.031
Neg logit contributions
 Jack-0.043
 Luke-0.043
 gigg-0.042
 subtract-0.042
 subt-0.041
Token lived
Token ID5615
Feature activation-1.21e+00

Pos logit contributions
 vet+0.026
oster+0.025
 hawk+0.025
 pilot+0.024
 mir+0.024
Neg logit contributions
 Jack-0.024
 gigg-0.022
 Luke-0.022
 -0.021
 James-0.021
Token a
Token ID257
Feature activation-6.50e-01

Pos logit contributions
 hawk+0.040
 pilot+0.039
 mir+0.039
 vet+0.039
oster+0.038
Neg logit contributions
 Jack-0.022
 Luke-0.020
 gigg-0.020
 -0.019
 g-0.018
Token squirrel
Token ID33039
Feature activation-7.36e-01

Pos logit contributions
 vet+0.015
oster+0.015
 wing+0.015
 mir+0.015
 hawk+0.014
Neg logit contributions
 Jack-0.016
 gigg-0.015
 Luke-0.015
 g-0.014
 boun-0.014
Token shelter
Token ID11772
Feature activation-1.60e+00

Pos logit contributions
oster+0.002
reetings+0.002
oral+0.002
resp+0.002
umber+0.002
Neg logit contributions
 boun-0.002
 g-0.002
 Jack-0.002
 -0.002
 gigg-0.002
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
 vet+0.051
 hawk+0.049
 pilot+0.048
oster+0.048
 mir+0.048
Neg logit contributions
 Jack-0.028
 Luke-0.028
 subtract-0.027
 gigg-0.027
 subt-0.026
Token But
Token ID887
Feature activation-1.05e+00

Pos logit contributions
 hawk+0.038
 vet+0.037
 mir+0.037
oster+0.037
 pilot+0.037
Neg logit contributions
 Jack-0.020
 -0.019
 subtract-0.019
 Luke-0.018
 James-0.017
Token,
Token ID11
Feature activation-4.10e-01

Pos logit contributions
resp+0.043
oster+0.043
reetings+0.042
oral+0.042
 mir+0.041
Neg logit contributions
 -0.012
 Jack-0.011
 hands-0.010
 shoulders-0.008
 gigg-0.008
Token the
Token ID262
Feature activation-3.02e+00

Pos logit contributions
oster+0.016
 mir+0.016
reetings+0.015
igi+0.015
oral+0.015
Neg logit contributions
 Jack-0.006
 -0.005
 hands-0.005
 Luke-0.004
 James-0.004
Token shelter
Token ID11772
Feature activation-3.26e+00

Pos logit contributions
reetings+0.099
resp+0.087
ull+0.081
mate+0.080
umber+0.080
Neg logit contributions
 hands-0.057
 shoulders-0.056
 -0.054
 boun-0.053
 fun-0.051
Token was
Token ID373
Feature activation-1.01e+00

Pos logit contributions
 vet+0.101
 mir+0.099
God+0.096
Santa+0.096
 hawk+0.095
Neg logit contributions
 Jack-0.060
ci-0.060
 gigg-0.057
 shoulders-0.056
 hands-0.055
Token always
Token ID1464
Feature activation-1.12e+00

Pos logit contributions
umber+0.037
 vet+0.037
oster+0.037
resp+0.036
oral+0.036
Neg logit contributions
 boun-0.014
 round-0.014
 gigg-0.013
 Jack-0.013
 -0.012
Token a
Token ID257
Feature activation-1.89e+00

Pos logit contributions
 vet+0.034
oster+0.031
 hawk+0.031
 pilot+0.031
oral+0.030
Neg logit contributions
 Jack-0.023
 gigg-0.023
 Luke-0.022
 hips-0.022
 shoulders-0.021
Token little
Token ID1310
Feature activation-7.73e-03

Pos logit contributions
reetings+0.055
oster+0.054
ull+0.052
igi+0.052
oral+0.052
Neg logit contributions
 boun-0.034
 g-0.033
 hands-0.031
 gigg-0.030
 -0.030
Token bit
Token ID1643
Feature activation-4.53e-01

Pos logit contributions
 vet+0.000
 hawk+0.000
oster+0.000
 pilot+0.000
 mir+0.000
Neg logit contributions
 Jack-0.000
 Luke-0.000
 subtract-0.000
 gigg-0.000
 subt-0.000