TOP ACTIVATIONS
MAX = 3.659

Let 's tie the r ags together ," Tom says .
helps Tom tie the r ags with knots . They put
don 't you write a nice message to each other and
" We tied the r ags and we were alert ."
beard . He wore a very old coat which was thick
. Suddenly , a folder fell from the sky . She
, a big canvas sack fell from the sky . Jo
, Emma could hear a wh inn ying sound . She
escape . She used her big trunk to make the hole
she spun around in a wh irl ig ig .
Mom . A big dog ruined our snow man . He
, who was wearing a very fine dress .
lies on his bed and wh ines . Anna is worried
him . He used a big truck to reverse the car
ay ons and write a nice message to each other .
farm . He used a big rake to scrape all the
listened carefully and heard the wh izzy sound until it went
and the printer began to wh ir r and print the
faster than the clouds and wh izz ed past the trees
icked Anna and Ben and wh ined . "

MIN ACTIVATIONS
MIN = -2.999

round . S oph ie had had a very
so much fun . K ait lyn was so happy to
It is the rh in oc eros !" The
It was the rh in oc eros . It lifted its
have stopped the rh in oc eros . He is sleeping
In the end , K ait lyn picked a spark ly
The rh in oc eros walked to the fence
had never seen the av oc ados . They wished they
careful ." S oph ie thanked him and gave
pushed and pulled on the seaw eed until finally , the
hair ! S oph ie smiled . She knew
. K ait lyn had so much fun
agreed . K ait lyn and Alex showed that
Ben say . Offic er Mike shows them his
The little girl eagerly helped mom my open the box .
my see the rh in oc eros up close . Tim
mom . S oph ie began to feel frustrated
than the park . K ait lyn ran over to the
happy to see our big cuc umber ." Lily says .
â S oph ie used her hands and

INTERVAL 1.994 - 3.659
CONTAINS 0.006%

But then , the door fell down . It made a
keep the bone . Max wh ined and bark ed until
the old lady like a wh irl ig ig . His
day , he dug a very big hole .
hello . The dog w ags its tail and l icks

INTERVAL 0.330 - 1.994
CONTAINS 22.023%

her mom . Her mom hugged her and said she was
and could never get enough to eat . She would go
. The bear was looking for honey near
. So , the family shared their spray and gave some
, it 's easy ." The little boy

INTERVAL -1.335 - 0.330
CONTAINS 77.604%

" Those are Mom my 's flowers . You can 't
to be honest and kind . Do you understand ?"
, stop it !" Sara said . " You are making
and thanked Mama . They put their pieces of the magnet
Max and play with him . They wait for the woman

INTERVAL -2.999 - -1.335
CONTAINS 0.368%

, " That is an aer opl ane ! It 's
, I 'm scared of that gate . Can you help
ay , let â s buy it ! â
lived a little girl named Gab by . She woke up
Ben were twins who loved to play with their toys .
TokenLet
Token ID5756
Feature activation-3.64e-02

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.006
 cash+0.005
pen+0.005
Neg logit contributions
 Judy-0.005
 Janet-0.005
arge-0.005
imi-0.005
 Betty-0.005
Token's
Token ID338
Feature activation-5.55e-02

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
pen+0.000
 cash+0.000
Neg logit contributions
 Judy-0.001
 Janet-0.001
imi-0.001
arge-0.001
 Betty-0.001
Token tie
Token ID9839
Feature activation-3.22e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 marry+0.001
 cash+0.001
 eighty+0.001
Neg logit contributions
anne-0.002
arge-0.002
 Judy-0.002
imi-0.002
 Janet-0.002
Token the
Token ID262
Feature activation+9.84e-01

Pos logit contributions
 Evan+0.001
 cand+0.000
 eighty+0.000
 cash+0.000
 penn+0.000
Neg logit contributions
arge-0.001
anne-0.001
 Judy-0.001
Bet-0.001
 Janet-0.001
Token r
Token ID374
Feature activation+3.22e-01

Pos logit contributions
anne+0.027
 Judy+0.027
arge+0.027
 Janet+0.027
imi+0.025
Neg logit contributions
 cand-0.024
 eighty-0.023
 Evan-0.022
 cash-0.022
 penn-0.021
Tokenags
Token ID3775
Feature activation+2.85e+00

Pos logit contributions
 Judy+0.009
 Janet+0.008
anne+0.008
 Betty+0.008
Bet+0.008
Neg logit contributions
 cand-0.007
 Evan-0.007
 cash-0.007
 eighty-0.007
 himself-0.007
Token together
Token ID1978
Feature activation+9.02e-01

Pos logit contributions
Bet+0.111
imi+0.105
iqu+0.104
arl+0.104
Jud+0.104
Neg logit contributions
 with-0.042
 himself-0.030
 in-0.029
e-0.027
 from-0.025
Token,"
Token ID553
Feature activation+8.99e-01

Pos logit contributions
 Janet+0.023
arge+0.022
 Judy+0.022
Bet+0.022
imi+0.022
Neg logit contributions
 Evan-0.023
 cand-0.022
 eighty-0.021
pen-0.020
 cash-0.020
Token Tom
Token ID4186
Feature activation+2.47e-01

Pos logit contributions
Bet+0.025
iet+0.025
imi+0.025
anne+0.024
arge+0.024
Neg logit contributions
 Evan-0.021
 cand-0.019
 cash-0.018
 penn-0.017
 eighty-0.017
Token says
Token ID1139
Feature activation-5.49e-01

Pos logit contributions
arge+0.005
Bet+0.005
 Janet+0.005
 Judy+0.005
imi+0.005
Neg logit contributions
 Evan-0.007
 cand-0.007
 eighty-0.007
 cash-0.006
pen-0.006
Token.
Token ID13
Feature activation+5.38e-02

Pos logit contributions
 Evan+0.015
 cand+0.014
 eighty+0.014
 cash+0.013
pen+0.013
Neg logit contributions
 Judy-0.013
 Janet-0.013
arge-0.012
anne-0.012
 Betty-0.012
Token helps
Token ID5419
Feature activation-1.36e-01

Pos logit contributions
 Judy+0.011
arge+0.011
 Janet+0.011
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.011
 cand-0.010
 eighty-0.010
 cash-0.010
pen-0.009
Token Tom
Token ID4186
Feature activation-3.70e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 cash+0.003
 eighty+0.003
pen+0.003
Neg logit contributions
arge-0.003
 Judy-0.003
 Janet-0.003
imi-0.003
anne-0.003
Token tie
Token ID9839
Feature activation-3.04e-01

Pos logit contributions
 Evan+0.008
 cand+0.007
 eighty+0.007
 cash+0.007
 penn+0.006
Neg logit contributions
 Judy-0.011
 Janet-0.011
arge-0.010
imi-0.010
 Betty-0.010
Token the
Token ID262
Feature activation+1.31e+00

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.006
 cash+0.005
pen+0.005
Neg logit contributions
 Janet-0.009
 Judy-0.009
arge-0.009
 Betty-0.009
imi-0.009
Token r
Token ID374
Feature activation+2.27e-01

Pos logit contributions
 Judy+0.034
arge+0.034
 Janet+0.034
anne+0.034
imi+0.033
Neg logit contributions
 cand-0.033
 eighty-0.031
 cash-0.031
 Evan-0.031
 penn-0.030
Tokenags
Token ID3775
Feature activation+2.77e+00

Pos logit contributions
 Judy+0.006
anne+0.005
 Betty+0.005
 Janet+0.005
 June+0.005
Neg logit contributions
 cand-0.006
 cash-0.005
 penn-0.005
 himself-0.005
 eighty-0.005
Token with
Token ID351
Feature activation-4.06e-02

Pos logit contributions
imi+0.103
Bet+0.102
arl+0.101
arge+0.100
oky+0.100
Neg logit contributions
 himself-0.037
 with-0.031
 Evan-0.028
 his-0.026
 penn-0.025
Token knots
Token ID33620
Feature activation-4.24e-01

Pos logit contributions
 Evan+0.001
 eighty+0.001
 cand+0.001
pen+0.001
 cash+0.001
Neg logit contributions
 Judy-0.001
 Janet-0.001
arge-0.001
 Betty-0.001
imi-0.001
Token.
Token ID13
Feature activation+2.18e-01

Pos logit contributions
 Evan+0.011
 cand+0.010
 eighty+0.010
 cash+0.010
pen+0.010
Neg logit contributions
 Judy-0.010
 Janet-0.010
arge-0.010
 Betty-0.010
imi-0.010
Token They
Token ID1119
Feature activation+2.17e-01

Pos logit contributions
iet+0.007
anne+0.007
imi+0.007
arge+0.007
inda+0.007
Neg logit contributions
 Evan-0.004
 cash-0.003
 Qu-0.003
 eighty-0.003
 himself-0.003
Token put
Token ID1234
Feature activation-7.74e-02

Pos logit contributions
 Janet+0.006
 Judy+0.006
arge+0.006
imi+0.006
 Betty+0.006
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.004
Token don
Token ID836
Feature activation+9.15e-01

Pos logit contributions
 Evan+0.005
 cand+0.004
 eighty+0.004
 cash+0.004
pen+0.004
Neg logit contributions
 Judy-0.006
 Janet-0.006
arge-0.006
imi-0.006
 Betty-0.006
Token't
Token ID470
Feature activation+4.27e-01

Pos logit contributions
 Judy+0.024
arge+0.024
 Janet+0.024
imi+0.024
 Betty+0.023
Neg logit contributions
 Evan-0.021
 cand-0.020
 eighty-0.019
 cash-0.019
pen-0.018
Token you
Token ID345
Feature activation-9.36e-02

Pos logit contributions
 Judy+0.009
 Janet+0.009
 Betty+0.009
imi+0.009
 Maria+0.009
Neg logit contributions
 Evan-0.012
 eighty-0.012
pen-0.011
 cand-0.011
 ninety-0.011
Token write
Token ID3551
Feature activation-5.14e-02

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.001
 penn+0.001
Neg logit contributions
 Janet-0.003
 Judy-0.003
arge-0.003
 Betty-0.003
imi-0.003
Token a
Token ID257
Feature activation+7.57e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
arge-0.002
 Judy-0.002
 Janet-0.002
imi-0.002
Bet-0.002
Token nice
Token ID3621
Feature activation+2.55e+00

Pos logit contributions
 Judy+0.022
arge+0.022
 Janet+0.022
imi+0.021
 Betty+0.021
Neg logit contributions
 Evan-0.016
 cand-0.016
 eighty-0.015
 cash-0.015
 penn-0.014
Token message
Token ID3275
Feature activation+6.16e-01

Pos logit contributions
 Janet+0.065
 Judy+0.065
imi+0.064
arge+0.064
 Betty+0.063
Neg logit contributions
 Evan-0.062
 eighty-0.056
 cand-0.056
pen-0.054
 cash-0.052
Token to
Token ID284
Feature activation+1.82e+00

Pos logit contributions
arge+0.019
Bet+0.019
 Judy+0.019
imi+0.019
 Janet+0.019
Neg logit contributions
 cand-0.012
 Evan-0.011
 marry-0.011
 eighty-0.010
 cash-0.010
Token each
Token ID1123
Feature activation-3.97e-01

Pos logit contributions
 Judy+0.052
 Janet+0.052
arge+0.051
imi+0.051
 Betty+0.050
Neg logit contributions
 Evan-0.039
 cand-0.037
 eighty-0.035
 cash-0.034
pen-0.033
Token other
Token ID584
Feature activation+3.14e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 cash+0.005
 eighty+0.005
 marry+0.004
Neg logit contributions
 Judy-0.014
arge-0.014
 Janet-0.014
imi-0.014
Bet-0.014
Token and
Token ID290
Feature activation+7.72e-01

Pos logit contributions
 Judy+0.009
Bet+0.009
 Janet+0.009
arge+0.009
 Betty+0.008
Neg logit contributions
 Evan-0.007
 cand-0.007
 marry-0.007
 eighty-0.006
 cash-0.006
Token "
Token ID366
Feature activation+3.24e-01

Pos logit contributions
imi+0.001
zie+0.001
arge+0.001
iet+0.001
arter+0.001
Neg logit contributions
 Evan-0.001
 cash-0.001
 Qu-0.001
 goodbye-0.001
 eighty-0.001
TokenWe
Token ID1135
Feature activation+3.14e-01

Pos logit contributions
 Judy+0.008
arge+0.008
 Janet+0.008
imi+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.009
 cand-0.008
 eighty-0.008
 cash-0.008
pen-0.008
Token tied
Token ID8165
Feature activation+4.54e-02

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.009
 Betty+0.009
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.005
 cash-0.005
pen-0.005
Token the
Token ID262
Feature activation+9.15e-01

Pos logit contributions
arge+0.001
 Judy+0.001
 Janet+0.001
imi+0.001
anne+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
 penn-0.001
Token r
Token ID374
Feature activation+4.85e-01

Pos logit contributions
 Judy+0.023
arge+0.023
 Janet+0.023
imi+0.022
 Betty+0.022
Neg logit contributions
 Evan-0.023
 cand-0.022
 eighty-0.021
 cash-0.020
pen-0.020
Tokenags
Token ID3775
Feature activation+2.50e+00

Pos logit contributions
 Judy+0.012
 Janet+0.011
 Betty+0.011
anne+0.011
Bet+0.011
Neg logit contributions
 cand-0.013
 Evan-0.013
 cash-0.012
 eighty-0.012
 penn-0.012
Token and
Token ID290
Feature activation+1.30e-02

Pos logit contributions
imi+0.096
Bet+0.094
arge+0.093
 Janet+0.093
 Judy+0.091
Neg logit contributions
 with-0.027
 himself-0.026
e-0.024
 penn-0.023
 cand-0.022
Token we
Token ID356
Feature activation+2.16e-01

Pos logit contributions
arge+0.000
 Judy+0.000
 Janet+0.000
imi+0.000
Bet+0.000
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
 cash-0.000
pen-0.000
Token were
Token ID547
Feature activation+5.18e-01

Pos logit contributions
 Judy+0.006
 Janet+0.006
arge+0.006
imi+0.006
 Betty+0.006
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.004
Token alert
Token ID7995
Feature activation-1.09e+00

Pos logit contributions
arge+0.016
 Judy+0.016
imi+0.016
 Janet+0.016
Bet+0.016
Neg logit contributions
 Evan-0.010
 cand-0.009
 eighty-0.009
 cash-0.008
 penn-0.008
Token."
Token ID526
Feature activation-2.00e-01

Pos logit contributions
 Evan+0.023
 cand+0.022
 eighty+0.021
 cash+0.020
pen+0.019
Neg logit contributions
 Janet-0.032
 Judy-0.032
arge-0.032
Bet-0.031
imi-0.031
Token beard
Token ID21213
Feature activation-4.92e-01

Pos logit contributions
 Evan+0.028
 cand+0.026
 eighty+0.024
 cash+0.024
 penn+0.023
Neg logit contributions
 Janet-0.028
 Judy-0.028
arge-0.028
iet-0.028
imi-0.027
Token.
Token ID13
Feature activation-4.05e-02

Pos logit contributions
 Evan+0.014
 eighty+0.013
 cand+0.013
 cash+0.013
 penn+0.012
Neg logit contributions
arge-0.010
 Janet-0.010
 Judy-0.010
anne-0.010
imi-0.010
Token He
Token ID679
Feature activation-6.69e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 penn+0.001
 cash+0.001
Neg logit contributions
 Judy-0.001
 Janet-0.001
arge-0.001
 Betty-0.001
imi-0.001
Token wore
Token ID12408
Feature activation+1.53e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
arge-0.002
 Janet-0.002
 Judy-0.002
imi-0.002
anne-0.002
Token a
Token ID257
Feature activation+4.02e-01

Pos logit contributions
 Janet+0.005
 Judy+0.005
arge+0.005
 Betty+0.005
imi+0.005
Neg logit contributions
 Evan-0.003
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token very
Token ID845
Feature activation+2.49e+00

Pos logit contributions
 Judy+0.012
arge+0.011
 Janet+0.011
 Betty+0.011
imi+0.011
Neg logit contributions
 Evan-0.009
 cand-0.009
 eighty-0.008
 re-0.008
 penn-0.008
Token old
Token ID1468
Feature activation-2.05e-01

Pos logit contributions
Bet+0.077
 Janet+0.076
 Judy+0.075
 Lynn+0.073
 Betty+0.073
Neg logit contributions
 cand-0.047
 Evan-0.047
 penn-0.045
 goodbye-0.045
 eighty-0.044
Token coat
Token ID13209
Feature activation-1.35e-01

Pos logit contributions
 cand+0.004
 Evan+0.004
 cash+0.004
 eighty+0.004
 penn+0.004
Neg logit contributions
 Judy-0.006
arge-0.006
imi-0.006
Bet-0.006
 Janet-0.006
Token which
Token ID543
Feature activation-9.08e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
 cash+0.003
 penn+0.003
Neg logit contributions
 Janet-0.004
arge-0.004
 Judy-0.003
imi-0.003
 Betty-0.003
Token was
Token ID373
Feature activation-5.29e-01

Pos logit contributions
 Evan+0.020
 cand+0.018
 eighty+0.018
pen+0.018
 cash+0.018
Neg logit contributions
 Judy-0.026
 Janet-0.026
 Betty-0.025
arge-0.025
 Lynn-0.024
Token thick
Token ID6546
Feature activation-1.10e+00

Pos logit contributions
 Evan+0.010
 cand+0.010
 eighty+0.010
 re+0.009
 marry+0.009
Neg logit contributions
 Judy-0.016
arge-0.016
imi-0.016
 Janet-0.016
anne-0.016
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
 cash+0.000
pen+0.000
Neg logit contributions
 Judy-0.000
arge-0.000
 Janet-0.000
imi-0.000
 Betty-0.000
Token Suddenly
Token ID24975
Feature activation+3.37e-01

Pos logit contributions
imi+0.007
iet+0.006
Bet+0.006
 Bree+0.006
 Janet+0.006
Neg logit contributions
 Evan-0.006
 eighty-0.006
 himself-0.006
 cand-0.006
 cash-0.006
Token,
Token ID11
Feature activation+5.04e-01

Pos logit contributions
arge+0.011
imi+0.011
 Janet+0.011
 Judy+0.011
Bet+0.011
Neg logit contributions
 Evan-0.006
 cand-0.005
 eighty-0.005
 cash-0.005
 penn-0.004
Token a
Token ID257
Feature activation+6.04e-01

Pos logit contributions
imi+0.013
arge+0.012
iet+0.012
 Janet+0.012
arl+0.012
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.011
 cash-0.011
 hairc-0.010
Token folder
Token ID9483
Feature activation+2.30e-02

Pos logit contributions
 Judy+0.016
arge+0.016
 Janet+0.016
imi+0.016
anne+0.015
Neg logit contributions
 Evan-0.014
 cand-0.014
 cash-0.013
 eighty-0.013
 re-0.012
Token fell
Token ID3214
Feature activation+2.48e+00

Pos logit contributions
 Judy+0.001
arge+0.001
 Janet+0.001
imi+0.001
 Betty+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token from
Token ID422
Feature activation+1.62e-01

Pos logit contributions
arge+0.086
 Judy+0.084
imi+0.080
anne+0.080
Rachel+0.079
Neg logit contributions
 Evan-0.038
 cand-0.036
 re-0.035
 eighty-0.035
 goodbye-0.034
Token the
Token ID262
Feature activation+3.19e-01

Pos logit contributions
leys+0.006
arge+0.006
imi+0.006
anne+0.006
iet+0.006
Neg logit contributions
 Evan-0.002
 him-0.002
 eighty-0.002
 himself-0.002
 re-0.002
Token sky
Token ID6766
Feature activation+2.57e-01

Pos logit contributions
 Judy+0.007
imi+0.007
 Janet+0.007
arge+0.007
anne+0.007
Neg logit contributions
 cash-0.009
 cand-0.009
 Evan-0.008
 eighty-0.008
 marry-0.008
Token.
Token ID13
Feature activation+9.53e-02

Pos logit contributions
imi+0.008
arge+0.008
 Judy+0.008
 Janet+0.008
Bet+0.008
Neg logit contributions
 Evan-0.005
 cand-0.005
pen-0.004
 cash-0.004
 eighty-0.004
Token She
Token ID1375
Feature activation+1.86e-01

Pos logit contributions
imi+0.002
iet+0.002
 Janet+0.002
arge+0.002
Bet+0.002
Neg logit contributions
 Evan-0.003
 cand-0.002
 eighty-0.002
 himself-0.002
 cash-0.002
Token,
Token ID11
Feature activation+7.32e-01

Pos logit contributions
 Judy+0.011
 Janet+0.011
arge+0.011
imi+0.011
 Betty+0.011
Neg logit contributions
 cand-0.008
 Evan-0.008
 cash-0.007
 eighty-0.007
pen-0.007
Token a
Token ID257
Feature activation+7.08e-01

Pos logit contributions
 Judy+0.021
arge+0.021
 Janet+0.021
imi+0.021
 Betty+0.021
Neg logit contributions
 Evan-0.015
 cand-0.014
 eighty-0.014
 cash-0.013
pen-0.013
Token big
Token ID1263
Feature activation+1.12e+00

Pos logit contributions
arge+0.020
 Judy+0.020
 Janet+0.020
imi+0.020
anne+0.019
Neg logit contributions
 Evan-0.016
 cand-0.014
 cash-0.014
 re-0.014
 eighty-0.013
Token canvas
Token ID21978
Feature activation+2.80e-01

Pos logit contributions
arge+0.031
leys+0.030
anne+0.030
 Janet+0.029
 Judy+0.029
Neg logit contributions
 Evan-0.025
 cand-0.024
 eighty-0.023
 re-0.023
 cash-0.023
Token sack
Token ID23704
Feature activation+2.62e-01

Pos logit contributions
 Judy+0.008
arge+0.008
imi+0.008
 Janet+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.006
 cand-0.006
pen-0.005
 eighty-0.005
 cash-0.005
Token fell
Token ID3214
Feature activation+2.47e+00

Pos logit contributions
arge+0.007
 Judy+0.007
 Janet+0.007
imi+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.006
 cash-0.005
pen-0.005
Token from
Token ID422
Feature activation+3.53e-01

Pos logit contributions
arge+0.085
 Judy+0.083
anne+0.081
imi+0.081
Rachel+0.079
Neg logit contributions
 Evan-0.039
 himself-0.036
 cand-0.036
 eighty-0.035
 goodbye-0.034
Token the
Token ID262
Feature activation+3.78e-01

Pos logit contributions
anne+0.014
arge+0.014
imi+0.014
iet+0.014
 Judy+0.014
Neg logit contributions
 Evan-0.004
 himself-0.004
 him-0.004
 eighty-0.003
 re-0.003
Token sky
Token ID6766
Feature activation+2.91e-01

Pos logit contributions
 Judy+0.009
arge+0.009
 Janet+0.009
imi+0.009
anne+0.009
Neg logit contributions
 Evan-0.010
 cand-0.010
 cash-0.010
 eighty-0.009
 penn-0.009
Token.
Token ID13
Feature activation+8.99e-02

Pos logit contributions
imi+0.009
arge+0.009
 Janet+0.009
 Judy+0.009
Bet+0.009
Neg logit contributions
 Evan-0.005
 cand-0.005
pen-0.005
 cash-0.005
 eighty-0.005
Token Jo
Token ID5302
Feature activation+4.67e-01

Pos logit contributions
 Judy+0.002
 Janet+0.002
arge+0.002
imi+0.002
Bet+0.002
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token,
Token ID11
Feature activation+6.86e-01

Pos logit contributions
arge+0.019
imi+0.019
 Judy+0.019
 Janet+0.019
Bet+0.019
Neg logit contributions
 Evan-0.009
 cand-0.009
 eighty-0.008
 cash-0.008
pen-0.008
Token Emma
Token ID18966
Feature activation+1.94e-01

Pos logit contributions
 Judy+0.019
 Janet+0.019
 Maria+0.018
arge+0.018
 Betty+0.018
Neg logit contributions
 Evan-0.015
 cand-0.015
 eighty-0.015
pen-0.014
 cash-0.014
Token could
Token ID714
Feature activation-2.88e-01

Pos logit contributions
 Judy+0.005
 Janet+0.005
arge+0.005
anne+0.005
imi+0.005
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.004
 cash-0.004
 penn-0.004
Token hear
Token ID3285
Feature activation-4.91e-01

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.008
 Janet-0.008
arge-0.008
imi-0.008
 Betty-0.008
Token a
Token ID257
Feature activation-7.45e-02

Pos logit contributions
 Evan+0.010
 cand+0.009
 eighty+0.009
 cash+0.009
pen+0.008
Neg logit contributions
 Judy-0.015
 Janet-0.014
arge-0.014
 Betty-0.014
 Maria-0.014
Token wh
Token ID348
Feature activation+2.46e+00

Pos logit contributions
 Evan+0.002
 cand+0.002
 cash+0.002
 eighty+0.002
pen+0.002
Neg logit contributions
 Judy-0.002
arge-0.002
 Janet-0.002
imi-0.002
 Betty-0.002
Tokeninn
Token ID3732
Feature activation+8.97e-01

Pos logit contributions
 Betty+0.055
 Judy+0.055
 Janet+0.054
Bet+0.052
 Lynn+0.051
Neg logit contributions
 Evan-0.067
pen-0.065
 eighty-0.062
 cand-0.061
yle-0.061
Tokenying
Token ID1112
Feature activation-5.12e-01

Pos logit contributions
 Judy+0.023
 Janet+0.022
arge+0.022
Bet+0.022
imi+0.022
Neg logit contributions
 Evan-0.022
 cand-0.021
 eighty-0.020
 cash-0.019
pen-0.019
Token sound
Token ID2128
Feature activation-5.16e-01

Pos logit contributions
 Evan+0.011
 cand+0.011
 eighty+0.010
 cash+0.010
pen+0.010
Neg logit contributions
 Judy-0.014
arge-0.014
 Janet-0.014
imi-0.014
 Betty-0.014
Token.
Token ID13
Feature activation-3.84e-02

Pos logit contributions
 Evan+0.012
 cand+0.011
 eighty+0.011
 cash+0.011
pen+0.010
Neg logit contributions
 Judy-0.014
arge-0.014
 Janet-0.014
imi-0.013
 Betty-0.013
Token She
Token ID1375
Feature activation+1.44e-01

Pos logit contributions
 Evan+0.001
 cash+0.001
 cand+0.001
 eighty+0.001
pen+0.001
Neg logit contributions
iet-0.001
imi-0.001
arge-0.001
Bet-0.001
 Janet-0.001
Token escape
Token ID6654
Feature activation+6.11e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.011
arge-0.011
 Janet-0.011
imi-0.011
 Betty-0.011
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
arge+0.021
imi+0.020
anne+0.020
 Janet+0.020
 Judy+0.020
Neg logit contributions
 Evan-0.010
 cand-0.009
 himself-0.008
 eighty-0.008
 cash-0.008
Token She
Token ID1375
Feature activation+3.00e-01

Pos logit contributions
arge+0.004
imi+0.004
iet+0.004
 Judy+0.004
 Janet+0.004
Neg logit contributions
 Evan-0.004
 cand-0.004
 cash-0.003
 eighty-0.003
pen-0.003
Token used
Token ID973
Feature activation+1.27e+00

Pos logit contributions
 Judy+0.008
arge+0.008
 Janet+0.008
imi+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.007
 cand-0.007
 eighty-0.006
 cash-0.006
pen-0.006
Token her
Token ID607
Feature activation+1.79e+00

Pos logit contributions
arge+0.040
imi+0.040
anne+0.039
 Judy+0.039
 Janet+0.039
Neg logit contributions
 Evan-0.023
 cand-0.022
 eighty-0.021
 cash-0.020
 penn-0.020
Token big
Token ID1263
Feature activation+2.43e+00

Pos logit contributions
arge+0.052
 Janet+0.052
Bet+0.051
 Judy+0.051
oky+0.049
Neg logit contributions
 cand-0.037
 re-0.037
 Evan-0.037
 penn-0.036
 eighty-0.035
Token trunk
Token ID21427
Feature activation+9.67e-01

Pos logit contributions
arge+0.065
 Janet+0.062
imi+0.062
 Judy+0.062
Bet+0.061
Neg logit contributions
 cand-0.057
 Evan-0.057
 eighty-0.054
 penn-0.053
 cash-0.051
Token to
Token ID284
Feature activation+6.79e-01

Pos logit contributions
arge+0.028
imi+0.028
 Judy+0.027
 Janet+0.027
Bet+0.027
Neg logit contributions
 Evan-0.020
 cand-0.020
 eighty-0.019
 cash-0.018
 penn-0.018
Token make
Token ID787
Feature activation+5.79e-01

Pos logit contributions
 Judy+0.020
 Janet+0.019
 Betty+0.019
arge+0.019
Bet+0.019
Neg logit contributions
 Evan-0.015
 cand-0.014
 eighty-0.013
 cash-0.013
pen-0.012
Token the
Token ID262
Feature activation+3.99e-01

Pos logit contributions
 Judy+0.017
 Janet+0.017
arge+0.017
 Betty+0.016
imi+0.016
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.011
 cash-0.011
pen-0.010
Token hole
Token ID7604
Feature activation+3.40e-01

Pos logit contributions
 Judy+0.006
 Betty+0.006
arge+0.006
imi+0.006
 Janet+0.005
Neg logit contributions
 Evan-0.014
 cand-0.014
 eighty-0.013
pen-0.013
yle-0.013
Token she
Token ID673
Feature activation-2.31e-01

Pos logit contributions
 Judy+0.015
 Janet+0.015
arge+0.015
 Betty+0.014
 Maria+0.014
Neg logit contributions
 Evan-0.009
 cand-0.009
 eighty-0.008
 cash-0.008
pen-0.008
Token spun
Token ID26843
Feature activation+3.42e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 eighty+0.005
 cash+0.004
pen+0.004
Neg logit contributions
 Judy-0.006
arge-0.006
 Janet-0.006
imi-0.006
 Betty-0.006
Token around
Token ID1088
Feature activation-7.70e-01

Pos logit contributions
 Judy+0.009
arge+0.009
 Janet+0.009
imi+0.009
 Betty+0.009
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
pen-0.007
Token in
Token ID287
Feature activation+3.44e-01

Pos logit contributions
 Evan+0.016
 cand+0.015
 eighty+0.015
 cash+0.014
pen+0.014
Neg logit contributions
 Judy-0.022
 Janet-0.022
arge-0.022
 Betty-0.022
imi-0.022
Token a
Token ID257
Feature activation-3.57e-01

Pos logit contributions
 Judy+0.009
 Janet+0.009
arge+0.009
 Betty+0.009
 Maria+0.009
Neg logit contributions
 Evan-0.008
 cand-0.008
 eighty-0.008
 cash-0.007
pen-0.007
Token wh
Token ID348
Feature activation+2.40e+00

Pos logit contributions
 Evan+0.009
 cand+0.009
 cash+0.008
 eighty+0.008
pen+0.008
Neg logit contributions
 Judy-0.009
 Janet-0.009
arge-0.009
imi-0.009
 Betty-0.009
Tokenirl
Token ID1901
Feature activation+3.71e-01

Pos logit contributions
 Betty+0.054
 Judy+0.052
 June+0.051
 Janet+0.051
 Bree+0.050
Neg logit contributions
 Evan-0.066
pen-0.064
yle-0.062
 eighty-0.062
 cand-0.060
Tokenig
Token ID328
Feature activation+4.21e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.010
 Betty+0.009
Neg logit contributions
 Evan-0.009
 cand-0.008
 eighty-0.008
 cash-0.008
pen-0.008
Tokenig
Token ID328
Feature activation+4.12e-01

Pos logit contributions
 Judy+0.011
arge+0.010
imi+0.010
 Janet+0.010
Bet+0.010
Neg logit contributions
 Evan-0.010
 cand-0.010
 eighty-0.009
pen-0.009
 cash-0.009
Token.
Token ID13
Feature activation+1.07e-01

Pos logit contributions
 Judy+0.010
arge+0.010
imi+0.010
 Janet+0.010
Bet+0.010
Neg logit contributions
 Evan-0.010
 cand-0.010
 eighty-0.009
pen-0.009
 cash-0.009
Token
Token ID220
Feature activation+9.08e-01

Pos logit contributions
imi+0.003
arge+0.003
 Janet+0.003
 Judy+0.003
iet+0.003
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token Mom
Token ID11254
Feature activation+1.88e-01

Pos logit contributions
arge+0.015
 Judy+0.015
 Janet+0.015
imi+0.015
anne+0.015
Neg logit contributions
 Evan-0.011
 cand-0.011
 eighty-0.010
 cash-0.010
pen-0.009
Token.
Token ID13
Feature activation-2.55e-01

Pos logit contributions
arge+0.006
iet+0.006
lights+0.006
Bet+0.005
eways+0.005
Neg logit contributions
 Evan-0.004
 cand-0.003
 eighty-0.003
pen-0.003
 re-0.003
Token A
Token ID317
Feature activation+2.64e-01

Pos logit contributions
 Evan+0.006
 cand+0.005
 eighty+0.005
 cash+0.005
pen+0.005
Neg logit contributions
 Judy-0.007
arge-0.007
 Janet-0.007
imi-0.007
 Betty-0.007
Token big
Token ID1263
Feature activation+9.11e-01

Pos logit contributions
 Janet+0.008
arge+0.008
 Judy+0.008
imi+0.008
zie+0.008
Neg logit contributions
 Evan-0.005
 cand-0.005
 re-0.005
 cash-0.005
 eighty-0.004
Token dog
Token ID3290
Feature activation+1.94e-01

Pos logit contributions
arge+0.028
 Janet+0.028
 Judy+0.028
anne+0.028
Bet+0.027
Neg logit contributions
 Evan-0.017
 cand-0.017
 eighty-0.016
 cash-0.016
 re-0.015
Token ruined
Token ID20484
Feature activation+2.39e+00

Pos logit contributions
arge+0.006
 Judy+0.006
 Janet+0.006
imi+0.005
Bet+0.005
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.004
pen-0.004
 cash-0.004
Token our
Token ID674
Feature activation+6.27e-01

Pos logit contributions
anne+0.074
arge+0.074
 Janet+0.072
Bet+0.072
 Judy+0.071
Neg logit contributions
 Evan-0.046
 cand-0.045
 himself-0.041
 re-0.041
 cash-0.041
Token snow
Token ID6729
Feature activation+2.38e-01

Pos logit contributions
 Janet+0.014
 Judy+0.014
arge+0.014
anne+0.013
Bet+0.013
Neg logit contributions
 Evan-0.017
 cand-0.017
 eighty-0.017
 cash-0.016
 penn-0.016
Tokenman
Token ID805
Feature activation+1.41e+00

Pos logit contributions
 Janet+0.007
 Judy+0.007
 Donna+0.007
arge+0.007
Maria+0.007
Neg logit contributions
 cand-0.005
 cash-0.005
 re-0.005
 Evan-0.005
 himself-0.005
Token.
Token ID13
Feature activation-4.90e-01

Pos logit contributions
 Judy+0.039
arge+0.039
 Janet+0.039
imi+0.038
Bet+0.037
Neg logit contributions
 Evan-0.032
 cand-0.031
 eighty-0.029
 cash-0.028
pen-0.028
Token He
Token ID679
Feature activation+5.52e-02

Pos logit contributions
 Evan+0.011
 cand+0.011
 eighty+0.010
 penn+0.010
pen+0.010
Neg logit contributions
 Judy-0.013
 Janet-0.013
 Betty-0.013
arge-0.013
imi-0.013
Token,
Token ID11
Feature activation+5.06e-01

Pos logit contributions
 Evan+0.003
 cand+0.002
 eighty+0.002
pen+0.002
 cash+0.002
Neg logit contributions
arge-0.003
 Judy-0.003
 Janet-0.003
imi-0.003
 Betty-0.003
Token who
Token ID508
Feature activation-1.15e-01

Pos logit contributions
arge+0.017
imi+0.017
 Judy+0.017
anne+0.017
 Janet+0.017
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.006
pen-0.006
Token was
Token ID373
Feature activation-9.47e-02

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.002
pen+0.002
Neg logit contributions
 Judy-0.004
 Janet-0.003
arge-0.003
imi-0.003
 Betty-0.003
Token wearing
Token ID5762
Feature activation-2.05e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 cash+0.002
 eighty+0.002
pen+0.002
Neg logit contributions
 Judy-0.002
 Janet-0.002
arge-0.002
imi-0.002
 Betty-0.002
Token a
Token ID257
Feature activation-2.45e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.003
pen+0.003
Neg logit contributions
 Judy-0.006
 Janet-0.006
arge-0.006
 Betty-0.006
imi-0.006
Token very
Token ID845
Feature activation+2.38e+00

Pos logit contributions
 cand+0.005
 Evan+0.005
 eighty+0.005
 marry+0.005
 re+0.005
Neg logit contributions
arge-0.007
 Judy-0.007
 Janet-0.007
imi-0.007
 Betty-0.007
Token fine
Token ID3734
Feature activation+9.47e-01

Pos logit contributions
Bet+0.084
 Janet+0.081
arge+0.079
 Judy+0.079
 Betty+0.078
Neg logit contributions
 cand-0.036
 Evan-0.034
 penn-0.033
 goodbye-0.033
 marry-0.033
Token dress
Token ID6576
Feature activation-1.92e-01

Pos logit contributions
arge+0.028
 Judy+0.028
 Janet+0.028
imi+0.027
Bet+0.027
Neg logit contributions
 Evan-0.019
 cand-0.019
 eighty-0.018
 marry-0.017
 cash-0.017
Token.
Token ID13
Feature activation+5.58e-02

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.004
pen+0.004
Neg logit contributions
 Judy-0.006
arge-0.006
 Janet-0.005
imi-0.005
Bet-0.005
Token
Token ID198
Feature activation+4.95e-02

Pos logit contributions
iet+0.002
arge+0.002
imi+0.002
lights+0.002
anne+0.002
Neg logit contributions
 Evan-0.001
 cand-0.001
 cash-0.001
 eighty-0.001
 Qu-0.001
Token
Token ID198
Feature activation+2.91e-01

Pos logit contributions
arge+0.002
 Janet+0.002
imi+0.002
lights+0.002
 Judy+0.002
Neg logit contributions
 Evan-0.001
pen-0.001
 eighty-0.001
 cand-0.001
 Mont-0.001
Token lies
Token ID7363
Feature activation-2.79e-02

Pos logit contributions
 Evan+0.012
 cand+0.011
 eighty+0.010
 cash+0.010
yle+0.010
Neg logit contributions
 Judy-0.009
 Betty-0.009
anne-0.009
imi-0.009
arge-0.009
Token on
Token ID319
Feature activation+9.05e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
 penn+0.001
Neg logit contributions
arge-0.001
 Janet-0.001
 Judy-0.001
imi-0.001
Bet-0.001
Token his
Token ID465
Feature activation-1.89e-01

Pos logit contributions
 Judy+0.003
arge+0.003
 Janet+0.003
imi+0.003
 Betty+0.003
Neg logit contributions
 Evan-0.002
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token bed
Token ID3996
Feature activation-9.79e-02

Pos logit contributions
 Evan+0.005
 eighty+0.005
pen+0.005
 cand+0.004
 cash+0.004
Neg logit contributions
imi-0.004
arge-0.004
 Judy-0.004
 Betty-0.004
anne-0.004
Token and
Token ID290
Feature activation-3.83e-02

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.002
pen+0.002
Neg logit contributions
 Judy-0.003
 Janet-0.003
arge-0.003
imi-0.003
 Betty-0.003
Token wh
Token ID348
Feature activation+2.37e+00

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
pen+0.001
 cash+0.001
Neg logit contributions
 Judy-0.001
arge-0.001
 Janet-0.001
imi-0.001
 Betty-0.001
Tokenines
Token ID1127
Feature activation+1.59e+00

Pos logit contributions
 Betty+0.042
 Judy+0.042
 Janet+0.040
Bet+0.039
 Bree+0.038
Neg logit contributions
 Evan-0.076
pen-0.073
 eighty-0.072
 penn-0.071
 cand-0.070
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
 Judy+0.039
arge+0.039
 Janet+0.038
imi+0.038
 Betty+0.038
Neg logit contributions
 Evan-0.040
 eighty-0.037
 cand-0.037
 cash-0.035
 penn-0.034
Token Anna
Token ID11735
Feature activation+4.45e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
 cash+0.003
pen+0.003
Neg logit contributions
 Judy-0.003
arge-0.003
 Janet-0.003
imi-0.003
 Betty-0.003
Token is
Token ID318
Feature activation-1.47e-01

Pos logit contributions
imi+0.010
 Lynn+0.009
iet+0.009
 Judy+0.009
anne+0.009
Neg logit contributions
 Evan-0.012
 cand-0.012
 eighty-0.011
 penn-0.011
 cash-0.011
Token worried
Token ID7960
Feature activation-1.42e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 cash+0.004
pen+0.004
 eighty+0.003
Neg logit contributions
 Judy-0.003
 Janet-0.003
arge-0.003
 Betty-0.003
imi-0.003
Token him
Token ID683
Feature activation-4.38e-01

Pos logit contributions
 Evan+0.005
 eighty+0.004
 cand+0.004
pen+0.004
 cash+0.004
Neg logit contributions
 Judy-0.009
 Janet-0.009
arge-0.009
 Betty-0.009
imi-0.008
Token.
Token ID13
Feature activation-1.57e-01

Pos logit contributions
 Evan+0.009
 cand+0.009
 eighty+0.009
 cash+0.008
 penn+0.008
Neg logit contributions
 Janet-0.012
 Judy-0.012
 Betty-0.012
arge-0.012
imi-0.012
Token He
Token ID679
Feature activation-2.30e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 cash+0.003
 eighty+0.002
 traded+0.002
Neg logit contributions
iet-0.005
arge-0.005
imi-0.005
 Judy-0.005
 Janet-0.005
Token used
Token ID973
Feature activation+1.21e+00

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.005
pen+0.005
 penn+0.005
Neg logit contributions
 Janet-0.006
 Judy-0.005
arge-0.005
 Betty-0.005
imi-0.005
Token a
Token ID257
Feature activation+1.42e+00

Pos logit contributions
 Janet+0.040
 Judy+0.040
arge+0.039
 Betty+0.039
imi+0.039
Neg logit contributions
 Evan-0.021
 cand-0.019
 eighty-0.018
 cash-0.017
pen-0.017
Token big
Token ID1263
Feature activation+2.36e+00

Pos logit contributions
arge+0.038
 Judy+0.037
imi+0.037
 Janet+0.036
anne+0.036
Neg logit contributions
 Evan-0.034
 cand-0.034
 cash-0.032
 penn-0.032
 eighty-0.032
Token truck
Token ID7779
Feature activation+4.04e-01

Pos logit contributions
 Judy+0.050
arge+0.050
 Janet+0.050
imi+0.049
 Betty+0.048
Neg logit contributions
 Evan-0.068
 cand-0.065
 eighty-0.063
 cash-0.062
pen-0.060
Token to
Token ID284
Feature activation+7.65e-01

Pos logit contributions
 Janet+0.009
 Judy+0.009
 Betty+0.009
arge+0.009
Bet+0.008
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.011
yle-0.010
 penn-0.010
Token reverse
Token ID9575
Feature activation+5.14e-01

Pos logit contributions
 Judy+0.024
arge+0.024
 Janet+0.024
imi+0.024
 Betty+0.024
Neg logit contributions
 Evan-0.014
 cand-0.013
 eighty-0.012
 cash-0.012
pen-0.012
Token the
Token ID262
Feature activation+8.56e-01

Pos logit contributions
arge+0.016
 Judy+0.016
imi+0.016
 Janet+0.015
Bet+0.015
Neg logit contributions
 Evan-0.010
 cand-0.010
 eighty-0.009
 cash-0.009
pen-0.009
Token car
Token ID1097
Feature activation+8.64e-01

Pos logit contributions
 Judy+0.022
 Janet+0.021
arge+0.021
imi+0.021
anne+0.021
Neg logit contributions
 Evan-0.022
 cand-0.021
 cash-0.020
 eighty-0.020
 penn-0.019
Tokenay
Token ID323
Feature activation-1.09e-01

Pos logit contributions
 Evan+0.026
 cand+0.026
 eighty+0.025
pen+0.025
 cash+0.024
Neg logit contributions
 Judy-0.017
arge-0.017
 Janet-0.016
 Betty-0.016
imi-0.016
Tokenons
Token ID684
Feature activation-4.26e-02

Pos logit contributions
 cand+0.003
 Evan+0.002
pen+0.002
 penn+0.002
 eighty+0.002
Neg logit contributions
 Judy-0.003
Bet-0.003
arge-0.003
imi-0.003
 Janet-0.003
Token and
Token ID290
Feature activation-3.54e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.001
 Janet-0.001
arge-0.001
imi-0.001
 Betty-0.001
Token write
Token ID3551
Feature activation+2.04e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
arge-0.001
 Judy-0.001
imi-0.001
 Janet-0.001
 Betty-0.001
Token a
Token ID257
Feature activation+1.11e+00

Pos logit contributions
imi+0.006
arge+0.006
Bet+0.006
 Judy+0.006
 Janet+0.006
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.004
 cash-0.003
pen-0.003
Token nice
Token ID3621
Feature activation+2.36e+00

Pos logit contributions
zie+0.033
imi+0.032
 Betty+0.032
 Judy+0.032
anne+0.032
Neg logit contributions
 cand-0.024
 marry-0.022
 cash-0.022
 trade-0.021
 eighty-0.021
Token message
Token ID3275
Feature activation+5.35e-01

Pos logit contributions
arge+0.058
imi+0.057
Bet+0.057
 Judy+0.057
 Janet+0.056
Neg logit contributions
 cand-0.060
 Evan-0.057
 cash-0.056
 eighty-0.053
 marry-0.053
Token to
Token ID284
Feature activation+1.48e+00

Pos logit contributions
imi+0.017
arge+0.017
Bet+0.017
 Judy+0.017
 Janet+0.017
Neg logit contributions
 cand-0.009
 Evan-0.009
 marry-0.008
 eighty-0.008
 cash-0.008
Token each
Token ID1123
Feature activation-5.05e-01

Pos logit contributions
arge+0.043
 Judy+0.043
 Janet+0.043
imi+0.043
Bet+0.043
Neg logit contributions
 Evan-0.030
 cand-0.028
 eighty-0.027
 cash-0.026
pen-0.025
Token other
Token ID584
Feature activation-2.89e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 cash+0.006
 eighty+0.006
pen+0.006
Neg logit contributions
arge-0.018
imi-0.018
 Judy-0.018
 Janet-0.018
Bet-0.018
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.007
 Janet-0.007
arge-0.007
imi-0.007
 Betty-0.007
Token farm
Token ID5318
Feature activation+6.48e-01

Pos logit contributions
 Janet+0.018
 Judy+0.017
imi+0.017
anne+0.017
arge+0.017
Neg logit contributions
 cand-0.017
 Evan-0.017
 cash-0.017
 re-0.016
 eighty-0.016
Token.
Token ID13
Feature activation+6.66e-02

Pos logit contributions
imi+0.020
arge+0.019
 Janet+0.019
 Judy+0.019
Bet+0.019
Neg logit contributions
 Evan-0.013
 cand-0.012
 cash-0.012
pen-0.011
 eighty-0.011
Token He
Token ID679
Feature activation-1.78e-01

Pos logit contributions
 Judy+0.002
arge+0.002
 Janet+0.002
imi+0.002
 Betty+0.002
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token used
Token ID973
Feature activation+1.20e+00

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.004
pen+0.004
Neg logit contributions
 Judy-0.005
arge-0.005
 Janet-0.005
imi-0.005
 Betty-0.005
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
arge+0.040
 Judy+0.040
 Janet+0.040
imi+0.040
anne+0.039
Neg logit contributions
 Evan-0.020
 cand-0.018
 eighty-0.017
 cash-0.016
pen-0.016
Token big
Token ID1263
Feature activation+2.36e+00

Pos logit contributions
arge+0.048
 Janet+0.047
 Judy+0.046
imi+0.046
lights+0.046
Neg logit contributions
 cand-0.030
 re-0.030
 penn-0.030
 coin-0.029
 Evan-0.029
Token rake
Token ID47885
Feature activation+8.63e-01

Pos logit contributions
arge+0.068
 Janet+0.066
 Judy+0.065
anne+0.064
Maria+0.064
Neg logit contributions
 cand-0.050
 eighty-0.048
 Evan-0.048
 penn-0.047
 re-0.046
Token to
Token ID284
Feature activation+9.86e-01

Pos logit contributions
 Judy+0.023
arge+0.023
 Janet+0.023
imi+0.022
 Betty+0.022
Neg logit contributions
 Evan-0.020
 cand-0.019
 eighty-0.018
 cash-0.018
pen-0.018
Token scrape
Token ID42778
Feature activation+7.48e-01

Pos logit contributions
arge+0.031
imi+0.031
 Judy+0.031
 Janet+0.031
anne+0.031
Neg logit contributions
 Evan-0.018
 cand-0.017
 cash-0.016
 eighty-0.015
pen-0.015
Token all
Token ID477
Feature activation+3.41e-01

Pos logit contributions
 Judy+0.023
arge+0.023
 Janet+0.023
imi+0.023
anne+0.022
Neg logit contributions
 Evan-0.014
 cand-0.013
 eighty-0.013
 cash-0.012
pen-0.012
Token the
Token ID262
Feature activation+5.61e-02

Pos logit contributions
arge+0.011
 Judy+0.011
 Janet+0.011
imi+0.011
Bet+0.011
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.005
 cash-0.005
pen-0.005
Token listened
Token ID16399
Feature activation-9.82e-01

Pos logit contributions
arge+0.027
 Judy+0.027
imi+0.027
 Janet+0.027
Bet+0.026
Neg logit contributions
 Evan-0.019
 cand-0.018
 eighty-0.017
pen-0.016
 cash-0.016
Token carefully
Token ID7773
Feature activation-5.30e-02

Pos logit contributions
 Evan+0.018
 cand+0.017
 eighty+0.016
 cash+0.016
pen+0.015
Neg logit contributions
imi-0.031
arge-0.031
 Janet-0.031
 Judy-0.031
Bet-0.030
Token and
Token ID290
Feature activation-4.50e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.002
arge-0.002
 Janet-0.002
imi-0.002
 Betty-0.001
Token heard
Token ID2982
Feature activation-1.56e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.001
 Janet-0.001
 Betty-0.001
arge-0.001
 Maria-0.001
Token the
Token ID262
Feature activation+1.52e-02

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
 cash+0.003
pen+0.003
Neg logit contributions
 Judy-0.005
 Janet-0.005
arge-0.005
imi-0.005
 Betty-0.005
Token wh
Token ID348
Feature activation+2.35e+00

Pos logit contributions
arge+0.000
 Janet+0.000
imi+0.000
 Judy+0.000
anne+0.000
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
pen-0.000
 cash-0.000
Tokenizzy
Token ID40593
Feature activation+1.91e-01

Pos logit contributions
 Betty+0.053
 Judy+0.052
 Janet+0.050
 June+0.050
 Lynn+0.049
Neg logit contributions
 Evan-0.063
pen-0.061
yle-0.059
 eighty-0.059
 penn-0.058
Token sound
Token ID2128
Feature activation-5.48e-01

Pos logit contributions
 Judy+0.006
arge+0.006
 Janet+0.006
imi+0.006
anne+0.006
Neg logit contributions
 Evan-0.004
 cand-0.003
 eighty-0.003
 cash-0.003
pen-0.003
Token until
Token ID1566
Feature activation+6.33e-01

Pos logit contributions
 Evan+0.013
 cand+0.013
 eighty+0.012
 cash+0.012
 penn+0.011
Neg logit contributions
 Judy-0.014
 Janet-0.014
arge-0.014
anne-0.014
 Betty-0.014
Token it
Token ID340
Feature activation-1.67e-01

Pos logit contributions
 Judy+0.018
arge+0.018
 Janet+0.018
imi+0.018
 Betty+0.018
Neg logit contributions
 Evan-0.013
 cand-0.013
 eighty-0.012
 cash-0.012
pen-0.011
Token went
Token ID1816
Feature activation+3.47e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
pen+0.003
 cash+0.003
Neg logit contributions
arge-0.005
imi-0.005
 Janet-0.005
 Judy-0.005
 Betty-0.005
Token and
Token ID290
Feature activation-4.00e-02

Pos logit contributions
 Evan+0.012
 cand+0.011
 eighty+0.010
 cash+0.010
pen+0.010
Neg logit contributions
arge-0.020
 Judy-0.020
imi-0.020
 Janet-0.020
Bet-0.019
Token the
Token ID262
Feature activation+2.23e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.001
 Janet-0.001
arge-0.001
 Betty-0.001
imi-0.001
Token printer
Token ID20632
Feature activation+2.84e-02

Pos logit contributions
 Judy+0.001
arge+0.001
 Janet+0.001
imi+0.001
Bet+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 cash-0.001
 eighty-0.001
 penn-0.000
Token began
Token ID2540
Feature activation+1.10e-01

Pos logit contributions
 Judy+0.001
 Janet+0.001
arge+0.001
imi+0.001
 Betty+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token to
Token ID284
Feature activation-6.73e-01

Pos logit contributions
imi+0.003
arge+0.003
 Judy+0.003
 Janet+0.003
anne+0.003
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token wh
Token ID348
Feature activation+2.34e+00

Pos logit contributions
 Evan+0.015
 cand+0.014
 eighty+0.013
 cash+0.013
pen+0.013
Neg logit contributions
imi-0.019
arge-0.019
 Judy-0.019
anne-0.019
 Janet-0.019
Tokenir
Token ID343
Feature activation+5.34e-01

Pos logit contributions
 Betty+0.054
 Judy+0.052
 Janet+0.050
 June+0.050
Bet+0.050
Neg logit contributions
 Evan-0.063
pen-0.063
yle-0.059
 eighty-0.059
 penn-0.058
Tokenr
Token ID81
Feature activation+8.96e-01

Pos logit contributions
 Judy+0.015
arge+0.014
 Janet+0.014
imi+0.014
anne+0.014
Neg logit contributions
 Evan-0.012
 cand-0.012
 eighty-0.011
 cash-0.011
 penn-0.010
Token and
Token ID290
Feature activation-7.91e-02

Pos logit contributions
 Judy+0.024
arge+0.024
 Janet+0.024
imi+0.024
 Betty+0.023
Neg logit contributions
 Evan-0.021
 cand-0.019
 eighty-0.019
 cash-0.018
pen-0.018
Token print
Token ID3601
Feature activation+1.75e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
imi-0.002
arge-0.002
iet-0.002
 Judy-0.002
Bet-0.002
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
arge+0.005
 Judy+0.005
imi+0.005
 Janet+0.005
Bet+0.005
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.003
 cash-0.003
pen-0.003
Token faster
Token ID5443
Feature activation-3.15e-01

Pos logit contributions
arge+0.012
 Judy+0.012
 Janet+0.012
imi+0.012
anne+0.011
Neg logit contributions
 Evan-0.011
 cand-0.011
 eighty-0.010
 cash-0.010
pen-0.010
Token than
Token ID621
Feature activation-3.44e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 cash+0.006
 eighty+0.006
pen+0.006
Neg logit contributions
 Judy-0.008
 Janet-0.008
arge-0.008
imi-0.008
 Betty-0.008
Token the
Token ID262
Feature activation-4.56e-01

Pos logit contributions
 Evan+0.007
 cash+0.007
 cand+0.007
 eighty+0.006
pen+0.006
Neg logit contributions
 Judy-0.010
 Janet-0.010
 Betty-0.010
 Maria-0.010
arge-0.010
Token clouds
Token ID15114
Feature activation+2.48e-01

Pos logit contributions
 Evan+0.011
 cand+0.010
 eighty+0.009
 cash+0.009
pen+0.009
Neg logit contributions
arge-0.012
 Judy-0.012
 Janet-0.011
imi-0.011
 Betty-0.011
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
 Judy+0.006
 Janet+0.006
 Betty+0.006
anne+0.006
 Maria+0.006
Neg logit contributions
 Evan-0.006
 cash-0.006
 cand-0.006
 eighty-0.006
 penn-0.005
Token wh
Token ID348
Feature activation+2.34e+00

Pos logit contributions
 Evan+0.000
 cand+0.000
 cash+0.000
 eighty+0.000
pen+0.000
Neg logit contributions
 Judy-0.000
 Janet-0.000
 Betty-0.000
arge-0.000
 Lynn-0.000
Tokenizz
Token ID6457
Feature activation-9.16e-02

Pos logit contributions
 Judy+0.051
 Betty+0.051
 Janet+0.050
 Lynn+0.048
Bet+0.048
Neg logit contributions
 Evan-0.066
pen-0.062
 cand-0.061
 eighty-0.061
yle-0.060
Tokened
Token ID276
Feature activation-2.86e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.002
pen+0.002
Neg logit contributions
 Judy-0.002
arge-0.002
 Janet-0.002
imi-0.002
anne-0.002
Token past
Token ID1613
Feature activation-1.68e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 eighty+0.007
 cash+0.007
yle+0.006
Neg logit contributions
 Judy-0.007
 Janet-0.007
 Betty-0.007
 Maria-0.007
arge-0.007
Token the
Token ID262
Feature activation+1.88e-01

Pos logit contributions
 Evan+0.003
 eighty+0.003
 cash+0.003
 cand+0.003
 marry+0.002
Neg logit contributions
 Judy-0.005
arge-0.005
imi-0.005
 Betty-0.005
 Janet-0.005
Token trees
Token ID7150
Feature activation+6.54e-01

Pos logit contributions
arge+0.004
 Judy+0.004
imi+0.004
 Janet+0.004
iet+0.004
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.005
 cash-0.005
pen-0.004
Tokenicked
Token ID9484
Feature activation+1.75e+00

Pos logit contributions
 Evan+0.019
 cand+0.018
 cash+0.018
 eighty+0.018
 hairc+0.017
Neg logit contributions
 Judy-0.014
 Janet-0.014
imi-0.014
arge-0.014
 Betty-0.014
Token Anna
Token ID11735
Feature activation+3.63e-01

Pos logit contributions
 Judy+0.049
 Janet+0.047
arge+0.047
imi+0.047
 Betty+0.047
Neg logit contributions
 Evan-0.040
 cand-0.038
 eighty-0.036
 cash-0.035
pen-0.035
Token and
Token ID290
Feature activation-3.55e-01

Pos logit contributions
anne+0.008
iet+0.007
 Judy+0.007
 June+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.010
 eighty-0.009
yle-0.009
 cash-0.008
 cand-0.008
Token Ben
Token ID3932
Feature activation+1.47e-01

Pos logit contributions
 Evan+0.009
 cand+0.008
 eighty+0.008
 cash+0.008
pen+0.008
Neg logit contributions
 Judy-0.009
arge-0.009
 Janet-0.009
imi-0.009
 Betty-0.009
Token and
Token ID290
Feature activation-5.56e-01

Pos logit contributions
 Judy+0.003
 June+0.003
anne+0.003
 Betty+0.003
 Maria+0.003
Neg logit contributions
 Evan-0.004
 eighty-0.003
 cash-0.003
yle-0.003
 ninety-0.003
Token wh
Token ID348
Feature activation+2.34e+00

Pos logit contributions
 Evan+0.012
 cand+0.011
 eighty+0.011
 cash+0.010
 penn+0.010
Neg logit contributions
arge-0.016
imi-0.016
 Janet-0.016
 Judy-0.016
Bet-0.015
Tokenined
Token ID1389
Feature activation+1.25e+00

Pos logit contributions
 Judy+0.053
 Betty+0.053
 Janet+0.051
 Lynn+0.050
arge+0.050
Neg logit contributions
 Evan-0.062
 cand-0.059
 eighty-0.058
pen-0.058
 penn-0.058
Token.
Token ID13
Feature activation-3.57e-02

Pos logit contributions
 Judy+0.033
 Janet+0.033
arge+0.033
imi+0.032
 Betty+0.032
Neg logit contributions
 Evan-0.029
 cand-0.028
 eighty-0.027
 cash-0.026
pen-0.025
Token
Token ID198
Feature activation-1.25e-02

Pos logit contributions
 Evan+0.001
 eighty+0.000
 Qu+0.000
 himself+0.000
 cand+0.000
Neg logit contributions
arge-0.001
 Janet-0.001
iet-0.001
imi-0.001
anne-0.001
Token
Token ID198
Feature activation+3.79e-03

Pos logit contributions
 Evan+0.000
 himself+0.000
 eighty+0.000
 cand+0.000
 Qu+0.000
Neg logit contributions
arge-0.000
 Janet-0.000
 Judy-0.000
iet-0.000
anne-0.000
Token"
Token ID1
Feature activation+5.22e-02

Pos logit contributions
 Janet+0.000
arge+0.000
 Judy+0.000
imi+0.000
anne+0.000
Neg logit contributions
 Evan-0.000
 eighty-0.000
 cand-0.000
 cash-0.000
pen-0.000
Tokenround
Token ID744
Feature activation-4.39e-01

Pos logit contributions
 Evan+0.038
 cand+0.036
 cash+0.035
 eighty+0.034
 penn+0.033
Neg logit contributions
anne-0.037
 Judy-0.035
arge-0.035
 Janet-0.034
Bet-0.034
Token.
Token ID13
Feature activation-3.04e-01

Pos logit contributions
 Evan+0.011
 cand+0.010
 eighty+0.010
 cash+0.009
pen+0.009
Neg logit contributions
 Judy-0.011
arge-0.011
 Janet-0.011
imi-0.011
 Betty-0.011
Token
Token ID198
Feature activation-5.72e-01

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.005
Neg logit contributions
imi-0.009
arge-0.009
 Janet-0.009
 Judy-0.009
Bet-0.008
Token
Token ID198
Feature activation-5.47e-01

Pos logit contributions
 Evan+0.013
 cand+0.012
 eighty+0.011
 cash+0.011
pen+0.011
Neg logit contributions
 Janet-0.016
 Judy-0.016
arge-0.016
imi-0.016
 Betty-0.015
TokenS
Token ID50
Feature activation-1.19e+00

Pos logit contributions
 Evan+0.016
 cand+0.015
 eighty+0.015
 cash+0.014
pen+0.014
Neg logit contributions
 Judy-0.012
arge-0.012
iet-0.011
Bet-0.011
 Janet-0.011
Tokenoph
Token ID2522
Feature activation-2.86e+00

Pos logit contributions
 Evan+0.033
 cand+0.030
 eighty+0.030
 cash+0.029
 penn+0.028
Neg logit contributions
 Judy-0.028
arge-0.028
 Janet-0.028
imi-0.028
anne-0.027
Tokenie
Token ID494
Feature activation-1.07e-01

Pos logit contributions
 Evan+0.078
 cand+0.077
 eighty+0.073
 penn+0.070
 cash+0.070
Neg logit contributions
 Janet-0.064
 Judy-0.062
Bet-0.062
 Betty-0.061
arge-0.061
Token had
Token ID550
Feature activation+2.47e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 cash+0.002
 eighty+0.002
 penn+0.002
Neg logit contributions
 Judy-0.003
arge-0.003
 Janet-0.003
anne-0.003
imi-0.003
Token had
Token ID550
Feature activation+3.62e-02

Pos logit contributions
 Judy+0.007
arge+0.007
 Janet+0.007
imi+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.004
 cash-0.004
pen-0.004
Token a
Token ID257
Feature activation-5.04e-01

Pos logit contributions
 Judy+0.001
arge+0.001
 Janet+0.001
imi+0.001
 Betty+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token very
Token ID845
Feature activation+1.35e+00

Pos logit contributions
 Evan+0.012
 cand+0.011
 eighty+0.011
 cash+0.010
 penn+0.010
Neg logit contributions
 Judy-0.014
 Janet-0.014
arge-0.014
imi-0.013
 Betty-0.013
Token so
Token ID523
Feature activation-2.21e-01

Pos logit contributions
 Judy+0.014
 Janet+0.014
arge+0.014
imi+0.013
 Betty+0.013
Neg logit contributions
 Evan-0.009
 cand-0.008
 eighty-0.008
 cash-0.007
pen-0.007
Token much
Token ID881
Feature activation+4.79e-01

Pos logit contributions
 Evan+0.007
 cash+0.007
 eighty+0.006
pen+0.006
etr+0.006
Neg logit contributions
anne-0.004
arge-0.004
 Judy-0.004
 Maria-0.004
 Janet-0.004
Token fun
Token ID1257
Feature activation+2.30e-01

Pos logit contributions
 Judy+0.006
 Janet+0.006
arge+0.006
imi+0.006
 Betty+0.006
Neg logit contributions
 Evan-0.018
 eighty-0.017
 cash-0.016
 cand-0.016
yle-0.016
Token.
Token ID13
Feature activation+4.04e-01

Pos logit contributions
 Judy+0.006
arge+0.006
 Janet+0.006
Bet+0.006
imi+0.006
Neg logit contributions
 Evan-0.005
 cand-0.005
pen-0.005
 eighty-0.005
 penn-0.005
Token K
Token ID509
Feature activation-7.70e-01

Pos logit contributions
 Judy+0.009
arge+0.009
 Janet+0.009
imi+0.009
 Betty+0.009
Neg logit contributions
 Evan-0.011
 cand-0.010
 eighty-0.010
 cash-0.010
pen-0.010
Tokenait
Token ID4548
Feature activation-2.83e+00

Pos logit contributions
 Evan+0.021
 cand+0.020
 eighty+0.019
 cash+0.018
 penn+0.018
Neg logit contributions
 Janet-0.018
 Judy-0.018
arge-0.017
 Betty-0.017
Bet-0.017
Tokenlyn
Token ID6213
Feature activation+1.05e-01

Pos logit contributions
 Evan+0.084
 cand+0.080
 eighty+0.078
 cash+0.076
pen+0.075
Neg logit contributions
 Judy-0.057
 Janet-0.057
arge-0.057
imi-0.056
 Betty-0.054
Token was
Token ID373
Feature activation-2.09e-01

Pos logit contributions
 Judy+0.003
 Janet+0.003
arge+0.003
anne+0.003
imi+0.003
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
 penn-0.002
Token so
Token ID523
Feature activation-1.98e-01

Pos logit contributions
 cand+0.006
 Evan+0.005
pen+0.005
 cash+0.005
 penn+0.005
Neg logit contributions
 Janet-0.005
 Judy-0.005
arge-0.005
 Maria-0.005
 Betty-0.005
Token happy
Token ID3772
Feature activation-1.41e-01

Pos logit contributions
 cand+0.006
 Evan+0.006
 cash+0.005
pen+0.005
 eighty+0.005
Neg logit contributions
 Judy-0.004
 Janet-0.004
arge-0.004
 Maria-0.004
 Betty-0.004
Token to
Token ID284
Feature activation+2.65e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.002
 cash+0.002
pen+0.002
Neg logit contributions
arge-0.004
 Judy-0.004
 Janet-0.004
imi-0.004
Bet-0.004
TokenIt
Token ID1026
Feature activation-1.04e-02

Pos logit contributions
 Judy+0.011
Bet+0.011
arge+0.011
 Janet+0.011
oky+0.010
Neg logit contributions
 Evan-0.015
 cand-0.015
 cash-0.014
 eighty-0.014
 penn-0.014
Token is
Token ID318
Feature activation-7.18e-03

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
 cash+0.000
pen+0.000
Neg logit contributions
 Judy-0.000
 Janet-0.000
arge-0.000
imi-0.000
 Betty-0.000
Token the
Token ID262
Feature activation-7.68e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
 re+0.000
 himself+0.000
Neg logit contributions
anne-0.000
arge-0.000
imi-0.000
Bet-0.000
iet-0.000
Token rh
Token ID9529
Feature activation-1.41e+00

Pos logit contributions
 Evan+0.018
pen+0.017
 cand+0.017
 eighty+0.015
yle+0.015
Neg logit contributions
arge-0.019
imi-0.019
 Judy-0.019
 Janet-0.019
 Betty-0.019
Tokenin
Token ID259
Feature activation+6.14e-02

Pos logit contributions
 Evan+0.043
 goodbye+0.041
 cash+0.040
 cand+0.038
 eighty+0.038
Neg logit contributions
imi-0.028
oky-0.027
iet-0.025
web-0.025
iders-0.025
Tokenoc
Token ID420
Feature activation-2.77e+00

Pos logit contributions
 Betty+0.002
imi+0.002
arge+0.002
oky+0.002
 Judy+0.002
Neg logit contributions
 Evan-0.001
 cash-0.001
 cand-0.001
pen-0.001
 eighty-0.001
Tokeneros
Token ID27498
Feature activation+2.46e-01

Pos logit contributions
 Evan+0.096
My+0.087
 marry+0.084
 rejuven+0.084
 traded+0.083
Neg logit contributions
oky-0.041
imi-0.040
arge-0.037
ower-0.036
eds-0.035
Token!"
Token ID2474
Feature activation-6.98e-01

Pos logit contributions
 Judy+0.006
arge+0.005
imi+0.005
 Janet+0.005
 Betty+0.005
Neg logit contributions
 Evan-0.007
 cand-0.006
 cash-0.006
 eighty-0.006
pen-0.006
Token
Token ID198
Feature activation-3.70e-01

Pos logit contributions
 Evan+0.011
 himself+0.009
 cand+0.009
 eighty+0.008
 Qu+0.008
Neg logit contributions
imi-0.025
arge-0.025
zie-0.025
anne-0.024
 Janet-0.024
Token
Token ID198
Feature activation-2.16e-01

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
arge-0.012
 Janet-0.012
 Judy-0.012
anne-0.011
imi-0.011
TokenThe
Token ID464
Feature activation+3.64e-01

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.005
Neg logit contributions
 Janet-0.005
 Judy-0.005
arge-0.005
imi-0.005
 Betty-0.005
Token It
Token ID632
Feature activation-5.40e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
arge-0.011
 Janet-0.011
imi-0.011
 Judy-0.011
anne-0.011
Token was
Token ID373
Feature activation+1.29e-01

Pos logit contributions
 Evan+0.010
 cand+0.009
 eighty+0.009
 cash+0.008
pen+0.008
Neg logit contributions
 Judy-0.017
 Janet-0.017
arge-0.017
imi-0.017
 Betty-0.017
Token the
Token ID262
Feature activation-1.07e+00

Pos logit contributions
anne+0.004
arge+0.004
imi+0.004
Bet+0.004
 Janet+0.004
Neg logit contributions
 Evan-0.002
 eighty-0.002
 re-0.002
 cand-0.002
 himself-0.002
Token rh
Token ID9529
Feature activation-1.34e+00

Pos logit contributions
 Evan+0.026
 cand+0.025
 eighty+0.024
 cash+0.023
pen+0.023
Neg logit contributions
 Judy-0.027
arge-0.027
 Janet-0.027
imi-0.027
 Betty-0.026
Tokenin
Token ID259
Feature activation-1.02e-01

Pos logit contributions
 Evan+0.039
 cash+0.036
 goodbye+0.036
 eighty+0.035
 cand+0.035
Neg logit contributions
imi-0.029
oky-0.028
iet-0.027
arge-0.026
lights-0.026
Tokenoc
Token ID420
Feature activation-2.74e+00

Pos logit contributions
 Evan+0.002
 eighty+0.002
 cash+0.002
 cand+0.002
pen+0.002
Neg logit contributions
arge-0.003
imi-0.003
 Judy-0.003
anne-0.003
oky-0.003
Tokeneros
Token ID27498
Feature activation+2.38e-01

Pos logit contributions
 Evan+0.093
My+0.085
 marry+0.083
 rejuven+0.079
 eighty+0.079
Neg logit contributions
oky-0.046
arge-0.042
imi-0.041
lights-0.040
zie-0.038
Token.
Token ID13
Feature activation-2.24e-01

Pos logit contributions
 Judy+0.006
anne+0.005
imi+0.005
 Betty+0.005
arge+0.005
Neg logit contributions
 Evan-0.006
 cash-0.006
 eighty-0.006
 cand-0.006
 penn-0.005
Token It
Token ID632
Feature activation-4.43e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.003
 Qu+0.003
Neg logit contributions
arge-0.007
imi-0.007
 Janet-0.007
anne-0.007
 Judy-0.007
Token lifted
Token ID13663
Feature activation+2.54e-01

Pos logit contributions
 Evan+0.010
 cand+0.009
 eighty+0.009
 cash+0.009
pen+0.009
Neg logit contributions
 Judy-0.012
arge-0.012
 Janet-0.012
imi-0.012
 Betty-0.012
Token its
Token ID663
Feature activation+5.86e-01

Pos logit contributions
 Judy+0.007
 Janet+0.007
arge+0.007
imi+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.006
 cand-0.005
 eighty-0.005
 cash-0.005
pen-0.005
Token have
Token ID423
Feature activation-3.38e-02

Pos logit contributions
 Judy+0.003
 Janet+0.003
arge+0.003
imi+0.003
 Betty+0.002
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token stopped
Token ID5025
Feature activation+1.73e+00

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.001
arge-0.001
 Janet-0.001
imi-0.001
 Betty-0.001
Token the
Token ID262
Feature activation+2.88e-01

Pos logit contributions
anne+0.051
arge+0.051
 Janet+0.051
 Judy+0.051
Bet+0.050
Neg logit contributions
 Evan-0.035
 cand-0.032
 eighty-0.031
 re-0.030
 marry-0.030
Token rh
Token ID9529
Feature activation-1.28e+00

Pos logit contributions
arge+0.008
 Judy+0.008
 Janet+0.008
imi+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.006
 cand-0.005
 eighty-0.005
pen-0.005
 cash-0.005
Tokenin
Token ID259
Feature activation+3.85e-01

Pos logit contributions
 Evan+0.036
 goodbye+0.032
 eighty+0.032
 cand+0.031
 himself+0.030
Neg logit contributions
oky-0.028
imi-0.028
arge-0.026
iet-0.026
iders-0.025
Tokenoc
Token ID420
Feature activation-2.70e+00

Pos logit contributions
arge+0.013
 Judy+0.013
imi+0.013
 Janet+0.012
 Betty+0.012
Neg logit contributions
 Evan-0.007
 cand-0.006
 eighty-0.006
 penn-0.005
pen-0.005
Tokeneros
Token ID27498
Feature activation+6.35e-01

Pos logit contributions
 Evan+0.089
My+0.080
 rejuven+0.077
 eighty+0.076
 marry+0.075
Neg logit contributions
oky-0.047
arge-0.044
imi-0.043
arl-0.039
eds-0.038
Token.
Token ID13
Feature activation-6.49e-01

Pos logit contributions
 Judy+0.017
arge+0.017
 Janet+0.017
imi+0.016
 Betty+0.016
Neg logit contributions
 Evan-0.015
 cand-0.014
 eighty-0.014
 cash-0.013
pen-0.013
Token He
Token ID679
Feature activation-2.36e-01

Pos logit contributions
 Evan+0.017
 cand+0.016
 eighty+0.016
pen+0.015
 cash+0.015
Neg logit contributions
 Judy-0.016
 Janet-0.015
arge-0.015
 Betty-0.015
imi-0.015
Token is
Token ID318
Feature activation+2.02e-01

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.005
 Janet-0.005
arge-0.005
imi-0.005
 Betty-0.005
Token sleeping
Token ID11029
Feature activation-1.87e-01

Pos logit contributions
arge+0.006
 Judy+0.006
imi+0.005
 Janet+0.005
Bet+0.005
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
 marry-0.004
TokenIn
Token ID818
Feature activation+8.14e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.010
anne+0.009
Neg logit contributions
 Evan-0.013
 cand-0.012
 eighty-0.012
 cash-0.011
pen-0.011
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
 Judy+0.026
 Janet+0.026
arge+0.026
imi+0.026
 Betty+0.025
Neg logit contributions
 Evan-0.015
 cand-0.014
 eighty-0.013
 cash-0.013
pen-0.012
Token end
Token ID886
Feature activation+6.25e-01

Pos logit contributions
 Evan+0.009
 eighty+0.008
 cand+0.008
yle+0.008
pen+0.008
Neg logit contributions
 Janet-0.014
arge-0.013
 Judy-0.013
iet-0.013
imi-0.013
Token,
Token ID11
Feature activation+5.40e-01

Pos logit contributions
arge+0.022
 Judy+0.022
 Janet+0.021
imi+0.021
anne+0.021
Neg logit contributions
 Evan-0.010
 cand-0.009
 eighty-0.008
 cash-0.008
 penn-0.007
Token K
Token ID509
Feature activation-2.67e-01

Pos logit contributions
arge+0.013
anne+0.013
oky+0.013
iet+0.013
imi+0.013
Neg logit contributions
 Evan-0.014
 cand-0.013
 cash-0.012
 penn-0.012
 hairc-0.011
Tokenait
Token ID4548
Feature activation-2.67e+00

Pos logit contributions
 Evan+0.007
 eighty+0.006
 cand+0.006
 cash+0.006
 penn+0.006
Neg logit contributions
 Janet-0.007
 Judy-0.007
Bet-0.006
 Betty-0.006
arge-0.006
Tokenlyn
Token ID6213
Feature activation+2.36e-01

Pos logit contributions
 Evan+0.078
 cand+0.073
 eighty+0.072
 cash+0.070
pen+0.068
Neg logit contributions
 Janet-0.056
 Judy-0.056
arge-0.055
imi-0.054
 Betty-0.053
Token picked
Token ID6497
Feature activation+1.34e-01

Pos logit contributions
 Judy+0.007
arge+0.007
 Janet+0.007
anne+0.007
imi+0.006
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.005
 cash-0.004
 penn-0.004
Token a
Token ID257
Feature activation+1.22e-01

Pos logit contributions
arge+0.004
 Judy+0.004
imi+0.004
 Janet+0.004
Bet+0.004
Neg logit contributions
 Evan-0.003
 cand-0.003
 eighty-0.003
 cash-0.003
pen-0.002
Token spark
Token ID9009
Feature activation+3.32e-01

Pos logit contributions
imi+0.004
Bet+0.003
arge+0.003
 Judy+0.003
 Betty+0.003
Neg logit contributions
 Evan-0.003
 cand-0.003
 eighty-0.003
 cash-0.002
pen-0.002
Tokenly
Token ID306
Feature activation+1.16e+00

Pos logit contributions
 Janet+0.009
 Judy+0.009
arge+0.009
anne+0.009
imi+0.009
Neg logit contributions
 Evan-0.007
 eighty-0.007
 cand-0.006
 cash-0.006
pen-0.006
Token
Token ID198
Feature activation-3.70e-01

Pos logit contributions
 Evan+0.011
 himself+0.009
 cand+0.009
 eighty+0.008
 Qu+0.008
Neg logit contributions
imi-0.025
arge-0.025
zie-0.025
anne-0.024
 Janet-0.024
Token
Token ID198
Feature activation-2.16e-01

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
arge-0.012
 Janet-0.012
 Judy-0.012
anne-0.011
imi-0.011
TokenThe
Token ID464
Feature activation+3.64e-01

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.005
Neg logit contributions
 Janet-0.005
 Judy-0.005
arge-0.005
imi-0.005
 Betty-0.005
Token rh
Token ID9529
Feature activation-1.34e+00

Pos logit contributions
imi+0.011
 window+0.010
 mist+0.010
 vine+0.010
arl+0.010
Neg logit contributions
pen-0.006
 Evan-0.006
yle-0.005
etr-0.005
hop-0.005
Tokenin
Token ID259
Feature activation+1.02e-01

Pos logit contributions
 Evan+0.040
 goodbye+0.037
 cand+0.035
 cash+0.035
 eighty+0.035
Neg logit contributions
imi-0.027
iet-0.025
oky-0.025
web-0.024
iders-0.023
Tokenoc
Token ID420
Feature activation-2.66e+00

Pos logit contributions
anne+0.003
imi+0.003
arge+0.003
 Judy+0.003
iet+0.003
Neg logit contributions
 Evan-0.002
 cand-0.002
yle-0.002
pen-0.002
 penn-0.002
Tokeneros
Token ID27498
Feature activation+1.94e-01

Pos logit contributions
 Evan+0.092
My+0.086
 contain+0.084
pen+0.084
 rejuven+0.084
Neg logit contributions
imi-0.035
oky-0.033
arge-0.031
eds-0.031
arl-0.029
Token walked
Token ID6807
Feature activation-6.03e-01

Pos logit contributions
anne+0.004
 Judy+0.004
iet+0.004
arge+0.004
 Betty+0.004
Neg logit contributions
 Evan-0.005
 cand-0.005
 penn-0.005
yle-0.005
pen-0.005
Token to
Token ID284
Feature activation-5.15e-01

Pos logit contributions
 Evan+0.018
 cand+0.017
 eighty+0.016
pen+0.016
 cash+0.016
Neg logit contributions
 Judy-0.013
 Janet-0.013
arge-0.012
 Betty-0.012
Bet-0.012
Token the
Token ID262
Feature activation+2.42e-01

Pos logit contributions
 cand+0.011
 Evan+0.011
 eighty+0.010
 penn+0.010
pen+0.010
Neg logit contributions
 Judy-0.014
 Janet-0.014
arge-0.014
 Betty-0.014
imi-0.014
Token fence
Token ID13990
Feature activation-2.38e-01

Pos logit contributions
arge+0.005
 window+0.005
 vine+0.005
imi+0.005
oky+0.005
Neg logit contributions
 Evan-0.006
pen-0.006
 cand-0.006
yle-0.006
 eighty-0.006
Token had
Token ID550
Feature activation+5.03e-01

Pos logit contributions
anne+0.002
 Janet+0.002
 Judy+0.002
 Betty+0.002
Bet+0.002
Neg logit contributions
 Evan-0.003
 cand-0.003
 cash-0.003
 eighty-0.003
pen-0.003
Token never
Token ID1239
Feature activation+1.79e-01

Pos logit contributions
 Judy+0.013
 Janet+0.013
 Betty+0.013
arge+0.012
Bet+0.012
Neg logit contributions
 Evan-0.012
pen-0.011
 cand-0.011
 eighty-0.011
 cash-0.011
Token seen
Token ID1775
Feature activation-4.33e-01

Pos logit contributions
 Janet+0.004
 Judy+0.004
 Betty+0.004
 Maria+0.004
Bet+0.004
Neg logit contributions
 Evan-0.005
 cash-0.004
 eighty-0.004
yle-0.004
 penn-0.004
Token the
Token ID262
Feature activation-3.25e-01

Pos logit contributions
 Evan+0.008
 cand+0.008
 eighty+0.007
 cash+0.007
pen+0.007
Neg logit contributions
 Judy-0.013
 Janet-0.013
 Betty-0.013
arge-0.013
imi-0.013
Token av
Token ID1196
Feature activation-1.11e+00

Pos logit contributions
 Evan+0.007
 cand+0.007
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.009
arge-0.009
 Janet-0.009
imi-0.009
 Betty-0.009
Tokenoc
Token ID420
Feature activation-2.65e+00

Pos logit contributions
 Evan+0.020
 cand+0.016
 eighty+0.015
 cash+0.015
yle+0.015
Neg logit contributions
Bet-0.036
 Janet-0.036
 Judy-0.036
 Betty-0.035
arge-0.035
Tokenados
Token ID22484
Feature activation+6.43e-01

Pos logit contributions
 Evan+0.082
 Qu+0.070
 eighty+0.070
yle+0.068
 marry+0.068
Neg logit contributions
 Betty-0.051
 Judy-0.051
arge-0.050
 Janet-0.050
oky-0.049
Token.
Token ID13
Feature activation-2.08e-01

Pos logit contributions
 Judy+0.014
arge+0.013
 Betty+0.013
 Janet+0.013
 Maria+0.013
Neg logit contributions
 Evan-0.017
 cand-0.015
 cash-0.015
 eighty-0.015
 penn-0.014
Token They
Token ID1119
Feature activation+8.36e-02

Pos logit contributions
 Evan+0.005
 cand+0.004
 cash+0.004
 Qu+0.004
 eighty+0.004
Neg logit contributions
imi-0.006
arge-0.006
iet-0.005
 Judy-0.005
 Janet-0.005
Token wished
Token ID16555
Feature activation+1.20e+00

Pos logit contributions
 Janet+0.002
 Judy+0.002
Bet+0.002
 Betty+0.002
arge+0.002
Neg logit contributions
 Evan-0.002
 eighty-0.002
 cand-0.002
pen-0.002
 cash-0.002
Token they
Token ID484
Feature activation+2.87e-02

Pos logit contributions
 Judy+0.024
 Janet+0.024
 Betty+0.023
arge+0.023
imi+0.022
Neg logit contributions
 Evan-0.036
 cand-0.035
pen-0.034
 eighty-0.034
 cash-0.033
Token careful
Token ID8161
Feature activation-6.90e-01

Pos logit contributions
imi+0.015
arge+0.015
 Janet+0.015
anne+0.015
 Judy+0.015
Neg logit contributions
 Evan-0.009
 eighty-0.009
 cand-0.008
 himself-0.008
pen-0.008
Token."
Token ID526
Feature activation-6.29e-01

Pos logit contributions
 Evan+0.014
 cand+0.013
 eighty+0.012
 himself+0.011
pen+0.011
Neg logit contributions
arge-0.021
 Janet-0.021
 Judy-0.020
Bet-0.020
imi-0.020
Token
Token ID198
Feature activation-6.68e-02

Pos logit contributions
 Evan+0.016
 cand+0.015
 eighty+0.015
 marry+0.014
 re+0.014
Neg logit contributions
 Judy-0.016
 Janet-0.015
 Betty-0.015
arge-0.015
Bet-0.014
Token
Token ID198
Feature activation-7.31e-02

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.002
arge-0.002
 Janet-0.002
imi-0.002
Bet-0.002
TokenS
Token ID50
Feature activation-1.06e+00

Pos logit contributions
 Evan+0.002
 cand+0.002
 hairc+0.002
 eighty+0.002
 re+0.002
Neg logit contributions
 Judy-0.001
iet-0.001
Bet-0.001
arge-0.001
 Janet-0.001
Tokenoph
Token ID2522
Feature activation-2.64e+00

Pos logit contributions
 Evan+0.026
 cand+0.024
 eighty+0.024
 cash+0.023
pen+0.022
Neg logit contributions
 Judy-0.027
arge-0.027
 Janet-0.027
imi-0.027
 Betty-0.026
Tokenie
Token ID494
Feature activation+5.05e-02

Pos logit contributions
 Evan+0.082
 cand+0.078
 eighty+0.076
 cash+0.075
pen+0.073
Neg logit contributions
 Judy-0.050
arge-0.050
 Janet-0.050
imi-0.049
 Betty-0.047
Token thanked
Token ID26280
Feature activation+1.61e-01

Pos logit contributions
 Judy+0.001
 Janet+0.001
 Betty+0.001
anne+0.001
arge+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token him
Token ID683
Feature activation-1.08e+00

Pos logit contributions
 Judy+0.005
 Janet+0.005
 Betty+0.004
 Maria+0.004
arge+0.004
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.003
pen-0.003
 penn-0.003
Token and
Token ID290
Feature activation-3.48e-01

Pos logit contributions
 Evan+0.028
 cand+0.027
 eighty+0.025
 penn+0.024
 cash+0.024
Neg logit contributions
 Judy-0.026
 Janet-0.026
 Betty-0.025
arge-0.025
 Lynn-0.025
Token gave
Token ID2921
Feature activation+3.29e-01

Pos logit contributions
 Evan+0.009
 cand+0.008
 eighty+0.008
pen+0.008
 hairc+0.008
Neg logit contributions
 Judy-0.009
 Janet-0.009
 Betty-0.009
 Maria-0.008
 Lynn-0.008
Token pushed
Token ID7121
Feature activation+3.25e-01

Pos logit contributions
 Evan+0.009
 cand+0.008
 eighty+0.008
 cash+0.008
 hairc+0.008
Neg logit contributions
 Judy-0.011
 Betty-0.011
 Janet-0.011
arge-0.011
Bet-0.011
Token and
Token ID290
Feature activation-3.05e-01

Pos logit contributions
 Judy+0.010
 Janet+0.010
 Betty+0.010
Bet+0.009
arge+0.009
Neg logit contributions
 Evan-0.007
 cand-0.007
 eighty-0.006
 cash-0.006
pen-0.006
Token pulled
Token ID5954
Feature activation+3.46e-01

Pos logit contributions
 Evan+0.007
 cand+0.007
 eighty+0.007
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.008
 Betty-0.008
 Janet-0.008
Bet-0.008
 Maria-0.008
Token on
Token ID319
Feature activation-2.45e-01

Pos logit contributions
 Judy+0.009
 Janet+0.009
 Betty+0.009
arge+0.009
Bet+0.009
Neg logit contributions
 Evan-0.008
 cand-0.008
 eighty-0.007
 cash-0.007
yle-0.007
Token the
Token ID262
Feature activation+5.67e-02

Pos logit contributions
 Evan+0.006
 cand+0.005
 eighty+0.005
 cash+0.005
yle+0.005
Neg logit contributions
 Judy-0.007
 Betty-0.007
 Janet-0.007
 Maria-0.006
arge-0.006
Token seaw
Token ID32085
Feature activation-2.62e+00

Pos logit contributions
 Judy+0.001
arge+0.001
 Janet+0.001
imi+0.001
 Betty+0.001
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Tokeneed
Token ID2308
Feature activation-9.49e-01

Pos logit contributions
 Evan+0.059
 cand+0.054
 eighty+0.052
 cash+0.051
 hairc+0.048
Neg logit contributions
arge-0.072
imi-0.071
iet-0.071
 Judy-0.071
anne-0.069
Token until
Token ID1566
Feature activation+3.28e-01

Pos logit contributions
 Evan+0.023
 cand+0.021
 eighty+0.021
 cash+0.020
pen+0.019
Neg logit contributions
 Judy-0.025
 Janet-0.024
arge-0.024
 Betty-0.024
imi-0.023
Token finally
Token ID3443
Feature activation+2.98e-01

Pos logit contributions
 Judy+0.009
 Betty+0.009
 Janet+0.009
 Maria+0.008
arge+0.008
Neg logit contributions
 Evan-0.007
 cand-0.007
 eighty-0.007
 cash-0.007
pen-0.007
Token,
Token ID11
Feature activation+1.40e-01

Pos logit contributions
 Judy+0.008
 Betty+0.008
 Janet+0.008
 Maria+0.007
 Donna+0.007
Neg logit contributions
 cash-0.007
 cand-0.007
 Evan-0.007
 eighty-0.007
 hairc-0.007
Token the
Token ID262
Feature activation-4.69e-01

Pos logit contributions
 Judy+0.004
 Janet+0.004
 Betty+0.004
arge+0.004
Bet+0.004
Neg logit contributions
 Evan-0.003
 cand-0.003
 eighty-0.003
 cash-0.003
pen-0.003
Token hair
Token ID4190
Feature activation-9.36e-02

Pos logit contributions
arge+0.003
imi+0.003
 Judy+0.003
 Janet+0.003
anne+0.003
Neg logit contributions
 Evan-0.002
 eighty-0.002
 cand-0.002
pen-0.002
 cash-0.002
Token!
Token ID0
Feature activation-1.57e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.002
pen+0.002
Neg logit contributions
 Judy-0.003
arge-0.003
 Janet-0.003
imi-0.003
 Betty-0.003
Token
Token ID198
Feature activation-3.69e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.003
pen+0.003
Neg logit contributions
 Judy-0.004
 Janet-0.004
arge-0.004
imi-0.004
 Betty-0.004
Token
Token ID198
Feature activation-3.43e-01

Pos logit contributions
 Evan+0.010
 cand+0.010
 eighty+0.010
 cash+0.010
pen+0.009
Neg logit contributions
 Judy-0.008
arge-0.008
imi-0.008
iet-0.008
 Janet-0.008
TokenS
Token ID50
Feature activation-1.03e+00

Pos logit contributions
 Evan+0.009
 cand+0.009
 eighty+0.009
 hairc+0.009
 ninety+0.008
Neg logit contributions
iet-0.008
Bet-0.008
arge-0.007
 Judy-0.007
 Janet-0.007
Tokenoph
Token ID2522
Feature activation-2.62e+00

Pos logit contributions
 Evan+0.028
 cand+0.026
 eighty+0.026
 cash+0.025
pen+0.024
Neg logit contributions
 Judy-0.024
arge-0.024
 Janet-0.024
imi-0.024
iet-0.023
Tokenie
Token ID494
Feature activation-5.07e-01

Pos logit contributions
 Evan+0.083
 cand+0.079
 eighty+0.077
 cash+0.076
pen+0.075
Neg logit contributions
 Judy-0.049
arge-0.049
imi-0.048
 Janet-0.048
anne-0.046
Token smiled
Token ID13541
Feature activation+2.28e-01

Pos logit contributions
 Evan+0.011
 cand+0.010
 eighty+0.009
 cash+0.009
pen+0.009
Neg logit contributions
 Judy-0.015
arge-0.014
 Janet-0.014
imi-0.014
anne-0.014
Token.
Token ID13
Feature activation-5.86e-01

Pos logit contributions
 Judy+0.005
 Janet+0.005
arge+0.005
 Maria+0.005
 Betty+0.005
Neg logit contributions
 cand-0.006
 Evan-0.006
 cash-0.005
 eighty-0.005
pen-0.005
Token She
Token ID1375
Feature activation+2.19e-01

Pos logit contributions
 Evan+0.016
 cand+0.015
 eighty+0.015
 cash+0.014
pen+0.014
Neg logit contributions
arge-0.013
 Judy-0.013
 Janet-0.013
imi-0.013
 Betty-0.013
Token knew
Token ID2993
Feature activation+6.18e-01

Pos logit contributions
 Judy+0.006
 Janet+0.006
arge+0.006
imi+0.006
 Betty+0.006
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.004
Token.
Token ID13
Feature activation+2.89e-01

Pos logit contributions
arge+0.008
 Judy+0.008
imi+0.008
 Janet+0.008
Bet+0.008
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.006
pen-0.005
 cash-0.005
Token
Token ID220
Feature activation+5.82e-01

Pos logit contributions
arge+0.008
 Judy+0.008
 Janet+0.008
imi+0.008
iet+0.008
Neg logit contributions
 Evan-0.007
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.005
Token
Token ID198
Feature activation-4.79e-02

Pos logit contributions
arge+0.018
 Janet+0.017
 Judy+0.017
imi+0.017
iet+0.017
Neg logit contributions
 Evan-0.012
 cand-0.010
 eighty-0.010
pen-0.009
 cash-0.009
Token
Token ID198
Feature activation+4.03e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.001
arge-0.001
 Janet-0.001
imi-0.001
anne-0.001
TokenK
Token ID42
Feature activation-6.13e-02

Pos logit contributions
arge+0.009
 Judy+0.009
 Janet+0.009
imi+0.008
Bet+0.008
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.011
 cash-0.010
pen-0.010
Tokenait
Token ID4548
Feature activation-2.62e+00

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.001
 cash+0.001
 penn+0.001
Neg logit contributions
 Janet-0.001
 Judy-0.001
 Betty-0.001
arge-0.001
Bet-0.001
Tokenlyn
Token ID6213
Feature activation+3.52e-01

Pos logit contributions
 Evan+0.080
 cand+0.077
 eighty+0.074
 cash+0.073
pen+0.072
Neg logit contributions
 Judy-0.051
arge-0.051
 Janet-0.051
imi-0.050
 Betty-0.049
Token had
Token ID550
Feature activation+2.74e-01

Pos logit contributions
 Judy+0.010
 Janet+0.009
arge+0.009
anne+0.009
 Lynn+0.009
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
pen-0.007
Token so
Token ID523
Feature activation-2.34e-01

Pos logit contributions
 Judy+0.008
arge+0.008
 Janet+0.008
imi+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.005
 cash-0.005
pen-0.004
Token much
Token ID881
Feature activation+5.77e-01

Pos logit contributions
 cash+0.007
 Evan+0.007
 cand+0.007
 eighty+0.007
pen+0.007
Neg logit contributions
 Judy-0.004
 Janet-0.004
arge-0.004
 Betty-0.004
anne-0.004
Token fun
Token ID1257
Feature activation+5.76e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.019
 cand-0.018
 eighty-0.017
 cash-0.017
pen-0.017
Token agreed
Token ID4987
Feature activation-2.79e-01

Pos logit contributions
 Judy+0.005
 Janet+0.005
 Betty+0.005
arge+0.004
 Lynn+0.004
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.004
pen-0.004
 cash-0.004
Token.
Token ID13
Feature activation+2.74e-01

Pos logit contributions
 Evan+0.008
 eighty+0.008
 cand+0.008
pen+0.007
 cash+0.007
Neg logit contributions
 Judy-0.006
 Maria-0.006
 Janet-0.006
 Betty-0.006
anne-0.005
Token
Token ID198
Feature activation+7.59e-02

Pos logit contributions
iet+0.009
arge+0.008
imi+0.008
 Janet+0.008
anne+0.008
Neg logit contributions
 Evan-0.006
 Qu-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
Token
Token ID198
Feature activation+4.10e-01

Pos logit contributions
arge+0.002
 Janet+0.002
 Judy+0.002
oky+0.002
imi+0.002
Neg logit contributions
 Evan-0.002
 cand-0.001
 eighty-0.001
pen-0.001
 himself-0.001
TokenK
Token ID42
Feature activation-2.00e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.010
 cand-0.010
 eighty-0.009
 cash-0.009
pen-0.009
Tokenait
Token ID4548
Feature activation-2.62e+00

Pos logit contributions
 Evan+0.005
 eighty+0.005
 cand+0.005
pen+0.005
 cash+0.005
Neg logit contributions
 Janet-0.005
 Judy-0.005
 Betty-0.005
Bet-0.004
arge-0.004
Tokenlyn
Token ID6213
Feature activation+3.01e-01

Pos logit contributions
 Evan+0.078
 cand+0.075
 eighty+0.073
 cash+0.071
pen+0.069
Neg logit contributions
 Judy-0.053
arge-0.052
 Janet-0.052
imi-0.051
 Betty-0.050
Token and
Token ID290
Feature activation-1.47e-01

Pos logit contributions
 Judy+0.008
anne+0.008
 Janet+0.008
arge+0.008
 Lynn+0.008
Neg logit contributions
 Evan-0.007
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.006
Token Alex
Token ID4422
Feature activation-6.81e-03

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.004
pen+0.004
Neg logit contributions
 Judy-0.003
 Janet-0.003
arge-0.003
imi-0.003
 Betty-0.003
Token showed
Token ID3751
Feature activation-4.99e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
 cash+0.000
pen+0.000
Neg logit contributions
anne-0.000
 Judy-0.000
 Janet-0.000
iet-0.000
arge-0.000
Token that
Token ID326
Feature activation-1.34e-01

Pos logit contributions
 eighty+0.013
 Evan+0.013
 cand+0.012
pen+0.012
 ninety+0.012
Neg logit contributions
 Judy-0.012
 Betty-0.012
 Janet-0.012
imi-0.012
arge-0.012
Token Ben
Token ID3932
Feature activation+1.17e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
pen+0.002
 penn+0.002
Neg logit contributions
 Judy-0.002
 Janet-0.002
arge-0.002
 Betty-0.002
imi-0.002
Token say
Token ID910
Feature activation-8.01e-01

Pos logit contributions
 Judy+0.003
 Janet+0.002
 Betty+0.002
arge+0.002
 June+0.002
Neg logit contributions
 Evan-0.003
 cand-0.003
 eighty-0.003
 penn-0.003
yle-0.003
Token.
Token ID13
Feature activation+7.71e-02

Pos logit contributions
 Evan+0.025
 cand+0.024
 cash+0.023
 eighty+0.023
pen+0.022
Neg logit contributions
 Judy-0.015
 Janet-0.014
 Maria-0.014
anne-0.014
 Betty-0.014
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
imi+0.003
iet+0.003
arge+0.003
zie+0.003
 Janet+0.003
Neg logit contributions
 Evan-0.001
 eighty-0.001
 cash-0.001
 Qu-0.001
 cand-0.001
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
 Evan+0.002
 eighty+0.002
 himself+0.002
 cand+0.002
 cash+0.002
Neg logit contributions
arge-0.004
 Janet-0.004
 Judy-0.004
anne-0.004
iet-0.004
TokenOffic
Token ID12710
Feature activation-2.61e+00

Pos logit contributions
 Janet+0.003
imi+0.003
 Judy+0.003
arge+0.003
anne+0.003
Neg logit contributions
 Evan-0.004
 eighty-0.003
 cash-0.003
 cand-0.003
pen-0.003
Tokener
Token ID263
Feature activation-1.08e+00

Pos logit contributions
 Evan+0.056
 cand+0.053
 eighty+0.051
 cash+0.049
pen+0.048
Neg logit contributions
 Judy-0.075
arge-0.074
 Janet-0.074
imi-0.074
 Betty-0.072
Token Mike
Token ID4995
Feature activation+8.23e-01

Pos logit contributions
 Evan+0.029
 cand+0.027
 eighty+0.027
 cash+0.027
pen+0.025
Neg logit contributions
arge-0.024
 Judy-0.024
Bet-0.024
 Janet-0.024
imi-0.024
Token shows
Token ID2523
Feature activation-1.31e+00

Pos logit contributions
imi+0.019
 Judy+0.019
arge+0.018
 Lynn+0.018
anne+0.018
Neg logit contributions
 Evan-0.022
 cand-0.020
 cash-0.019
 eighty-0.019
yle-0.019
Token them
Token ID606
Feature activation-3.37e-01

Pos logit contributions
 Evan+0.031
 cand+0.030
 eighty+0.030
pen+0.028
 cash+0.027
Neg logit contributions
 Judy-0.034
 Janet-0.034
arge-0.034
imi-0.033
 Betty-0.033
Token his
Token ID465
Feature activation+3.27e-01

Pos logit contributions
 Evan+0.008
 eighty+0.008
 cand+0.008
pen+0.007
 cash+0.007
Neg logit contributions
 Judy-0.009
 Janet-0.009
 Betty-0.008
arge-0.008
 Maria-0.008
TokenThe
Token ID464
Feature activation-5.15e-02

Pos logit contributions
 Judy+0.004
 Janet+0.004
arge+0.004
imi+0.004
 Betty+0.004
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.003
Token little
Token ID1310
Feature activation-5.07e-03

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.002
arge-0.002
 Janet-0.002
imi-0.002
 Betty-0.002
Token girl
Token ID2576
Feature activation+9.08e-03

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
 cash+0.000
pen+0.000
Neg logit contributions
arge-0.000
 Judy-0.000
 Janet-0.000
imi-0.000
Bet-0.000
Token eagerly
Token ID30130
Feature activation-3.43e-01

Pos logit contributions
 Judy+0.000
 Janet+0.000
arge+0.000
 Maria+0.000
anne+0.000
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
 cash-0.000
pen-0.000
Token helped
Token ID4193
Feature activation-4.08e-01

Pos logit contributions
 Evan+0.009
 cand+0.009
 eighty+0.008
 penn+0.008
yle+0.008
Neg logit contributions
 Judy-0.008
 Janet-0.008
 Betty-0.008
arge-0.008
anne-0.008
Token mom
Token ID1995
Feature activation-2.60e+00

Pos logit contributions
 Evan+0.010
 eighty+0.010
 cand+0.010
pen+0.009
 ninety+0.009
Neg logit contributions
 Judy-0.010
 Janet-0.010
arge-0.010
imi-0.010
 Betty-0.010
Tokenmy
Token ID1820
Feature activation-9.09e-01

Pos logit contributions
 Evan+0.067
 cand+0.066
 cash+0.063
 eighty+0.063
pen+0.062
Neg logit contributions
 Judy-0.061
Bet-0.060
arge-0.060
 Janet-0.059
imi-0.059
Token open
Token ID1280
Feature activation+1.17e-01

Pos logit contributions
 Evan+0.019
 cand+0.018
 eighty+0.017
 cash+0.017
pen+0.016
Neg logit contributions
 Judy-0.026
arge-0.026
 Janet-0.026
imi-0.026
 Betty-0.025
Token the
Token ID262
Feature activation+8.68e-01

Pos logit contributions
arge+0.004
 Judy+0.004
imi+0.004
 Janet+0.004
Bet+0.004
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token box
Token ID3091
Feature activation+3.26e-03

Pos logit contributions
 Judy+0.018
arge+0.018
 Janet+0.018
imi+0.018
Bet+0.017
Neg logit contributions
 Evan-0.026
 cand-0.025
 eighty-0.024
 cash-0.023
pen-0.023
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
imi+0.000
Bet+0.000
arge+0.000
 Janet+0.000
 Judy+0.000
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
pen-0.000
 cash-0.000
Tokenmy
Token ID1820
Feature activation-2.05e-01

Pos logit contributions
 Evan+0.015
 cand+0.014
 eighty+0.014
 cash+0.014
pen+0.013
Neg logit contributions
 Judy-0.008
arge-0.008
 Janet-0.008
imi-0.008
 Betty-0.008
Token see
Token ID766
Feature activation-9.15e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.003
 penn+0.003
Neg logit contributions
 Judy-0.006
 Janet-0.006
arge-0.006
 Betty-0.006
 Maria-0.006
Token the
Token ID262
Feature activation-1.61e-02

Pos logit contributions
 Evan+0.018
 cand+0.017
 eighty+0.016
 cash+0.016
pen+0.015
Neg logit contributions
 Judy-0.028
arge-0.028
 Janet-0.028
imi-0.027
 Betty-0.027
Token rh
Token ID9529
Feature activation-1.28e+00

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
pen+0.000
 cash+0.000
Neg logit contributions
arge-0.000
 Judy-0.000
 Janet-0.000
imi-0.000
 Betty-0.000
Tokenin
Token ID259
Feature activation-5.85e-02

Pos logit contributions
 Evan+0.035
 goodbye+0.032
 eighty+0.032
 cand+0.032
 cash+0.029
Neg logit contributions
imi-0.028
arge-0.028
oky-0.027
iders-0.026
iet-0.026
Tokenoc
Token ID420
Feature activation-2.59e+00

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 penn+0.001
yle+0.001
Neg logit contributions
arge-0.002
 Judy-0.002
 Betty-0.002
 Janet-0.002
Bet-0.002
Tokeneros
Token ID27498
Feature activation+3.75e-01

Pos logit contributions
 Evan+0.084
My+0.073
 rejuven+0.073
 marry+0.072
 eighty+0.071
Neg logit contributions
arge-0.045
oky-0.043
imi-0.041
uana-0.038
 Betty-0.038
Token up
Token ID510
Feature activation-2.32e-01

Pos logit contributions
 Judy+0.010
 Janet+0.010
 Betty+0.009
arge+0.009
imi+0.009
Neg logit contributions
 Evan-0.009
 cand-0.008
 eighty-0.008
 cash-0.008
 penn-0.008
Token close
Token ID1969
Feature activation-3.99e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
pen+0.004
 eighty+0.004
 penn+0.004
Neg logit contributions
imi-0.007
arge-0.007
 Janet-0.007
 Lynn-0.007
 Judy-0.007
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
 Evan+0.009
 cand+0.008
 eighty+0.008
 cash+0.007
pen+0.007
Neg logit contributions
arge-0.011
imi-0.011
 Janet-0.011
 Judy-0.011
Bet-0.011
Token Tim
Token ID5045
Feature activation-3.81e-02

Pos logit contributions
 Evan+0.004
 cand+0.004
 cash+0.004
 eighty+0.004
 traded+0.003
Neg logit contributions
iet-0.007
imi-0.007
arge-0.007
anne-0.007
 Judy-0.006
Token mom
Token ID1995
Feature activation+4.48e-03

Pos logit contributions
 Evan+0.003
 cand+0.003
 cash+0.003
 penn+0.003
 eighty+0.003
Neg logit contributions
Bet-0.005
 Judy-0.005
 Janet-0.005
arge-0.004
iet-0.004
Token.
Token ID13
Feature activation-5.61e-01

Pos logit contributions
arge+0.000
iet+0.000
imi+0.000
 Judy+0.000
Bet+0.000
Neg logit contributions
 cand-0.000
 Evan-0.000
 eighty-0.000
 cash-0.000
pen-0.000
Token
Token ID198
Feature activation-6.23e-01

Pos logit contributions
 Evan+0.013
 cand+0.012
 cash+0.011
 eighty+0.011
pen+0.011
Neg logit contributions
arge-0.015
 Judy-0.015
 Janet-0.015
imi-0.015
iet-0.015
Token
Token ID198
Feature activation-4.38e-01

Pos logit contributions
 Evan+0.012
 cand+0.011
 cash+0.010
 eighty+0.010
pen+0.009
Neg logit contributions
 Janet-0.019
 Judy-0.019
arge-0.019
iet-0.019
anne-0.019
TokenS
Token ID50
Feature activation-1.03e+00

Pos logit contributions
 Evan+0.013
 cand+0.012
 eighty+0.012
pen+0.011
 penn+0.011
Neg logit contributions
arge-0.009
 Judy-0.009
imi-0.009
 Janet-0.009
Bet-0.009
Tokenoph
Token ID2522
Feature activation-2.59e+00

Pos logit contributions
 Evan+0.027
 cand+0.025
 eighty+0.025
 cash+0.024
pen+0.023
Neg logit contributions
 Judy-0.025
arge-0.024
 Janet-0.024
imi-0.024
anne-0.023
Tokenie
Token ID494
Feature activation+2.18e-01

Pos logit contributions
 Evan+0.075
 cand+0.073
 eighty+0.069
 cash+0.068
 penn+0.066
Neg logit contributions
 Janet-0.054
 Judy-0.054
arge-0.054
Bet-0.053
 Betty-0.052
Token began
Token ID2540
Feature activation-6.83e-01

Pos logit contributions
 Judy+0.006
arge+0.006
 Janet+0.006
imi+0.006
anne+0.006
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.004
Token to
Token ID284
Feature activation-1.17e+00

Pos logit contributions
 Evan+0.019
 cand+0.018
 eighty+0.018
 cash+0.017
pen+0.016
Neg logit contributions
arge-0.015
 Judy-0.015
 Janet-0.015
imi-0.015
 Lynn-0.015
Token feel
Token ID1254
Feature activation-8.30e-02

Pos logit contributions
 Evan+0.025
 cand+0.025
 eighty+0.023
 penn+0.022
pen+0.022
Neg logit contributions
 Judy-0.033
arge-0.032
 Janet-0.032
imi-0.032
 Betty-0.032
Token frustrated
Token ID14718
Feature activation-6.16e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 ninety+0.002
pen+0.002
Neg logit contributions
 Judy-0.002
 Betty-0.002
 Janet-0.002
arge-0.002
 Lynn-0.002
Token than
Token ID621
Feature activation-2.00e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 himself+0.004
 penn+0.004
 eighty+0.004
Neg logit contributions
Bet-0.009
imi-0.009
arge-0.009
 Janet-0.009
 Lynn-0.009
Token the
Token ID262
Feature activation-6.41e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.003
 cash+0.003
pen+0.003
Neg logit contributions
arge-0.006
 Judy-0.006
 Janet-0.006
imi-0.006
Bet-0.006
Token park
Token ID3952
Feature activation+1.47e-01

Pos logit contributions
 Evan+0.016
 cand+0.015
 eighty+0.014
 cash+0.014
 penn+0.013
Neg logit contributions
 Judy-0.017
 Janet-0.016
arge-0.016
imi-0.016
 Betty-0.016
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
imi+0.004
arge+0.004
 Judy+0.004
 Janet+0.004
Bet+0.004
Neg logit contributions
 Evan-0.003
 cand-0.003
 cash-0.003
 eighty-0.003
pen-0.002
Token K
Token ID509
Feature activation-3.55e-01

Pos logit contributions
arge+0.007
imi+0.007
 Judy+0.007
 Janet+0.007
iet+0.007
Neg logit contributions
 Evan-0.008
 cand-0.008
 cash-0.007
 eighty-0.007
 penn-0.007
Tokenait
Token ID4548
Feature activation-2.59e+00

Pos logit contributions
 Evan+0.009
 cand+0.008
 eighty+0.008
 cash+0.008
 penn+0.008
Neg logit contributions
 Janet-0.009
 Judy-0.009
 Betty-0.008
Bet-0.008
arge-0.008
Tokenlyn
Token ID6213
Feature activation+3.27e-01

Pos logit contributions
 Evan+0.075
 cand+0.070
 eighty+0.069
 cash+0.067
pen+0.065
Neg logit contributions
 Janet-0.055
 Judy-0.055
arge-0.054
imi-0.053
 Betty-0.053
Token ran
Token ID4966
Feature activation-4.32e-01

Pos logit contributions
 Judy+0.009
arge+0.009
 Janet+0.009
anne+0.009
imi+0.008
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
pen-0.007
Token over
Token ID625
Feature activation-1.15e+00

Pos logit contributions
 Evan+0.010
 cand+0.010
 eighty+0.009
 cash+0.009
pen+0.009
Neg logit contributions
 Judy-0.011
 Janet-0.011
arge-0.011
imi-0.011
 Betty-0.011
Token to
Token ID284
Feature activation-5.07e-01

Pos logit contributions
 Evan+0.025
 cand+0.023
 eighty+0.022
 cash+0.022
pen+0.021
Neg logit contributions
arge-0.032
imi-0.032
 Janet-0.032
 Judy-0.032
anne-0.031
Token the
Token ID262
Feature activation-2.17e-01

Pos logit contributions
 Evan+0.010
 cand+0.010
 eighty+0.009
 cash+0.009
pen+0.008
Neg logit contributions
 Judy-0.016
 Janet-0.016
arge-0.015
 Betty-0.015
imi-0.015
Token happy
Token ID3772
Feature activation-3.43e-01

Pos logit contributions
imi+0.015
arge+0.015
anne+0.014
 Janet+0.014
 Judy+0.014
Neg logit contributions
 Evan-0.008
 eighty-0.008
 cand-0.008
 cash-0.007
 penn-0.007
Token to
Token ID284
Feature activation+2.71e-01

Pos logit contributions
 cand+0.006
 Evan+0.005
 eighty+0.005
 penn+0.005
 marry+0.005
Neg logit contributions
 Janet-0.012
arge-0.012
anne-0.011
 Judy-0.011
Bet-0.011
Token see
Token ID766
Feature activation-1.29e+00

Pos logit contributions
lights+0.010
arge+0.009
anne+0.009
imi+0.009
 Janet+0.009
Neg logit contributions
 Evan-0.004
 cand-0.004
 marry-0.004
 eighty-0.004
 cash-0.003
Token our
Token ID674
Feature activation-1.66e-01

Pos logit contributions
 Evan+0.025
 cand+0.024
 eighty+0.022
 cash+0.021
 penn+0.021
Neg logit contributions
arge-0.040
 Janet-0.040
 Judy-0.039
anne-0.039
imi-0.039
Token big
Token ID1263
Feature activation-1.89e-02

Pos logit contributions
 Evan+0.004
 cand+0.004
 cash+0.003
 eighty+0.003
 penn+0.003
Neg logit contributions
 Janet-0.004
 Judy-0.004
arge-0.004
imi-0.004
anne-0.004
Token cuc
Token ID38421
Feature activation-2.58e+00

Pos logit contributions
 cand+0.000
 Evan+0.000
 cash+0.000
 penn+0.000
 eighty+0.000
Neg logit contributions
arge-0.001
 Janet-0.001
anne-0.001
Bet-0.000
 Judy-0.000
Tokenumber
Token ID4494
Feature activation+3.90e-01

Pos logit contributions
 Evan+0.065
 cand+0.057
 eighty+0.055
 goodbye+0.055
 hairc+0.054
Neg logit contributions
arge-0.065
imi-0.064
 Judy-0.062
oky-0.061
iet-0.061
Token."
Token ID526
Feature activation-2.80e-01

Pos logit contributions
arge+0.011
 Judy+0.011
 Janet+0.011
imi+0.011
Bet+0.011
Neg logit contributions
 Evan-0.008
 cand-0.008
 eighty-0.008
 cash-0.008
pen-0.007
Token Lily
Token ID20037
Feature activation+5.57e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 cash+0.005
 Qu+0.005
 eighty+0.004
Neg logit contributions
anne-0.009
iders-0.009
iet-0.009
eways-0.009
leys-0.009
Token says
Token ID1139
Feature activation-5.71e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.018
 cand-0.017
 eighty-0.017
 cash-0.016
pen-0.016
Token.
Token ID13
Feature activation+8.78e-02

Pos logit contributions
 Evan+0.017
 cand+0.016
 cash+0.015
 eighty+0.015
pen+0.015
Neg logit contributions
 Judy-0.012
anne-0.011
 Janet-0.011
arge-0.011
imi-0.011
Tokenâ
Token ID22940
Feature activation+4.76e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
pen+0.000
 cash+0.000
Neg logit contributions
arge-0.001
imi-0.001
 Judy-0.001
 Janet-0.001
Bet-0.001
Token
Token ID26391
Feature activation+1.48e-01

Pos logit contributions
 Judy+0.010
 Janet+0.010
arge+0.010
anne+0.010
imi+0.009
Neg logit contributions
 Evan-0.014
 cand-0.014
 eighty-0.013
 penn-0.013
 cash-0.013
Token
Token ID447
Feature activation-9.84e-01

Pos logit contributions
arge+0.004
 Judy+0.004
imi+0.004
 Janet+0.004
 Betty+0.004
Neg logit contributions
 Evan-0.004
 cand-0.003
 eighty-0.003
pen-0.003
 cash-0.003
Token
Token ID251
Feature activation-5.88e-01

Pos logit contributions
 Evan+0.027
 cand+0.025
pen+0.024
 cash+0.024
 eighty+0.023
Neg logit contributions
arge-0.023
 Judy-0.023
imi-0.023
 Janet-0.023
 Betty-0.022
TokenS
Token ID50
Feature activation-8.59e-01

Pos logit contributions
 Evan+0.013
 cand+0.013
 eighty+0.012
 cash+0.012
pen+0.011
Neg logit contributions
arge-0.016
 Judy-0.016
 Janet-0.016
imi-0.016
anne-0.016
Tokenoph
Token ID2522
Feature activation-2.58e+00

Pos logit contributions
 Evan+0.020
 cand+0.019
 eighty+0.018
 cash+0.018
pen+0.017
Neg logit contributions
 Janet-0.023
 Judy-0.023
arge-0.023
imi-0.023
 Betty-0.022
Tokenie
Token ID494
Feature activation-1.20e-01

Pos logit contributions
 Evan+0.074
 cand+0.071
 eighty+0.068
 cash+0.066
pen+0.065
Neg logit contributions
 Janet-0.055
arge-0.054
 Judy-0.054
Bet-0.053
 Betty-0.052
Token used
Token ID973
Feature activation+8.77e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.002
pen+0.002
Neg logit contributions
arge-0.004
 Judy-0.004
 Janet-0.004
imi-0.004
Bet-0.003
Token her
Token ID607
Feature activation+5.03e-01

Pos logit contributions
 Judy+0.026
 Janet+0.026
arge+0.026
imi+0.025
 Betty+0.025
Neg logit contributions
 Evan-0.018
 cand-0.017
 eighty-0.016
 cash-0.016
pen-0.015
Token hands
Token ID2832
Feature activation-2.68e-01

Pos logit contributions
arge+0.016
Bet+0.016
 Janet+0.016
 Judy+0.016
imi+0.016
Neg logit contributions
 Evan-0.009
 cand-0.009
 eighty-0.009
 penn-0.008
 cash-0.008
Token and
Token ID290
Feature activation-1.47e-01

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.005
 cash+0.005
pen+0.005
Neg logit contributions
arge-0.007
 Judy-0.007
 Janet-0.007
imi-0.007
 Betty-0.007
TokenBut
Token ID1537
Feature activation-2.51e-01

Pos logit contributions
 Judy+0.001
arge+0.001
 Janet+0.001
imi+0.001
 Betty+0.001
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.001
 cash-0.001
pen-0.001
Token then
Token ID788
Feature activation+3.89e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 eighty+0.005
pen+0.005
 cash+0.005
Neg logit contributions
 Judy-0.007
 Janet-0.007
arge-0.007
imi-0.007
 Betty-0.007
Token,
Token ID11
Feature activation+4.55e-01

Pos logit contributions
 Judy+0.012
 Betty+0.012
 Janet+0.012
imi+0.011
 Maria+0.011
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
pen-0.007
Token the
Token ID262
Feature activation+3.28e-02

Pos logit contributions
 Judy+0.013
arge+0.013
 Janet+0.013
imi+0.013
 Betty+0.013
Neg logit contributions
 Evan-0.009
 cand-0.009
 eighty-0.008
 cash-0.008
pen-0.008
Token door
Token ID3420
Feature activation+5.99e-01

Pos logit contributions
 Judy+0.001
 Janet+0.001
Bet+0.001
imi+0.001
arge+0.001
Neg logit contributions
 cand-0.001
 cash-0.001
 Evan-0.001
 penn-0.001
 marry-0.001
Token fell
Token ID3214
Feature activation+2.08e+00

Pos logit contributions
 Judy+0.019
arge+0.019
imi+0.018
Bet+0.018
 Janet+0.018
Neg logit contributions
 cand-0.011
 Evan-0.011
 cash-0.010
 traded-0.009
pen-0.009
Token down
Token ID866
Feature activation+1.30e-01

Pos logit contributions
arge+0.073
 Judy+0.073
anne+0.070
imi+0.069
 Janet+0.068
Neg logit contributions
 Evan-0.031
 cand-0.031
 eighty-0.028
 himself-0.027
 goodbye-0.027
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
imi+0.005
arge+0.005
 Judy+0.005
anne+0.005
iet+0.005
Neg logit contributions
 Evan-0.002
 cand-0.002
 himself-0.002
 cash-0.002
 marry-0.001
Token It
Token ID632
Feature activation-7.15e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
 cash+0.003
pen+0.002
Neg logit contributions
 Judy-0.003
arge-0.003
 Janet-0.003
imi-0.003
 Betty-0.003
Token made
Token ID925
Feature activation+5.10e-01

Pos logit contributions
 Evan+0.010
 cand+0.010
 cash+0.009
 re+0.009
 marry+0.009
Neg logit contributions
arge-0.025
 Judy-0.025
 Janet-0.025
imi-0.024
Bet-0.024
Token a
Token ID257
Feature activation-6.96e-02

Pos logit contributions
arge+0.016
 Janet+0.016
 Judy+0.016
imi+0.016
anne+0.015
Neg logit contributions
 Evan-0.010
 cand-0.009
 cash-0.008
 eighty-0.008
 penn-0.008
Token keep
Token ID1394
Feature activation+2.44e-01

Pos logit contributions
 eighty+0.007
 cand+0.007
 Evan+0.007
 penn+0.007
 ninety+0.007
Neg logit contributions
 Janet-0.007
 Betty-0.007
 Judy-0.007
 Maria-0.007
Bet-0.007
Token the
Token ID262
Feature activation-2.97e-01

Pos logit contributions
 Janet+0.007
 Judy+0.007
arge+0.007
 Betty+0.007
imi+0.007
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.005
 cash-0.004
pen-0.004
Token bone
Token ID9970
Feature activation+2.26e-02

Pos logit contributions
 Evan+0.008
 eighty+0.007
yle+0.007
 cand+0.007
 marry+0.007
Neg logit contributions
imi-0.007
 Betty-0.006
 Janet-0.006
 Bree-0.006
 Judy-0.006
Token.
Token ID13
Feature activation+4.44e-02

Pos logit contributions
 Betty+0.001
 Janet+0.001
 Judy+0.000
 Maria+0.000
imi+0.000
Neg logit contributions
 Evan-0.001
 eighty-0.001
 cand-0.001
 cash-0.001
 hairc-0.001
Token Max
Token ID5436
Feature activation-1.59e-01

Pos logit contributions
arge+0.001
 Judy+0.001
iet+0.001
imi+0.001
anne+0.001
Neg logit contributions
 Evan-0.001
 cash-0.001
 cand-0.001
 traded-0.001
 himself-0.001
Token wh
Token ID348
Feature activation+2.09e+00

Pos logit contributions
 Evan+0.004
 eighty+0.004
 cand+0.003
 penn+0.003
yle+0.003
Neg logit contributions
 Judy-0.004
 Janet-0.004
 Betty-0.004
 Lynn-0.004
imi-0.004
Tokenined
Token ID1389
Feature activation+1.29e+00

Pos logit contributions
 Judy+0.046
 Betty+0.045
arge+0.044
 Janet+0.044
Bet+0.043
Neg logit contributions
 Evan-0.058
 cand-0.055
 eighty-0.055
pen-0.054
 penn-0.052
Token and
Token ID290
Feature activation-1.39e-01

Pos logit contributions
 Judy+0.037
 Janet+0.037
arge+0.037
imi+0.036
 Betty+0.036
Neg logit contributions
 Evan-0.028
 cand-0.026
 eighty-0.025
 cash-0.024
pen-0.023
Token bark
Token ID21405
Feature activation-3.46e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
 cash+0.003
pen+0.002
Neg logit contributions
arge-0.004
 Judy-0.004
imi-0.004
 Janet-0.004
anne-0.004
Tokened
Token ID276
Feature activation-3.67e-01

Pos logit contributions
 eighty+0.009
 Evan+0.009
 cash+0.008
 cand+0.008
 hairc+0.008
Neg logit contributions
anne-0.008
 Betty-0.008
 Janet-0.008
 Judy-0.008
Bet-0.008
Token until
Token ID1566
Feature activation+4.27e-01

Pos logit contributions
 Evan+0.009
 eighty+0.009
 cand+0.009
yle+0.008
 cash+0.008
Neg logit contributions
 Judy-0.009
 Betty-0.009
 Janet-0.009
 Maria-0.009
 June-0.008
Token the
Token ID262
Feature activation-6.83e-01

Pos logit contributions
 Evan+0.025
 cand+0.024
 eighty+0.023
 cash+0.022
 penn+0.021
Neg logit contributions
 Judy-0.032
 Janet-0.032
arge-0.032
 Maria-0.032
 Betty-0.031
Token old
Token ID1468
Feature activation-1.25e+00

Pos logit contributions
 Evan+0.020
 cand+0.019
 cash+0.018
 eighty+0.018
pen+0.018
Neg logit contributions
 Janet-0.014
 Judy-0.014
arge-0.014
imi-0.014
 Betty-0.014
Token lady
Token ID10846
Feature activation-2.84e-01

Pos logit contributions
 Evan+0.029
 cand+0.028
 eighty+0.027
 cash+0.026
pen+0.025
Neg logit contributions
 Judy-0.033
arge-0.033
 Janet-0.033
imi-0.033
 Betty-0.032
Token like
Token ID588
Feature activation+1.25e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.003
pen+0.003
Neg logit contributions
 Judy-0.010
arge-0.010
 Janet-0.010
imi-0.010
 Betty-0.010
Token a
Token ID257
Feature activation-7.02e-01

Pos logit contributions
 Judy+0.004
 Janet+0.004
arge+0.004
imi+0.004
 Betty+0.004
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token wh
Token ID348
Feature activation+2.18e+00

Pos logit contributions
 Evan+0.016
 cand+0.014
 eighty+0.014
 cash+0.014
pen+0.013
Neg logit contributions
 Judy-0.020
 Janet-0.020
arge-0.020
imi-0.020
 Betty-0.019
Tokenirl
Token ID1901
Feature activation+1.27e-01

Pos logit contributions
 Betty+0.048
 Judy+0.048
 Janet+0.047
 June+0.046
Bet+0.045
Neg logit contributions
 Evan-0.060
pen-0.058
 eighty-0.056
yle-0.055
 cand-0.055
Tokenig
Token ID328
Feature activation+4.46e-01

Pos logit contributions
 Judy+0.003
 Janet+0.003
arge+0.003
anne+0.003
imi+0.003
Neg logit contributions
 Evan-0.003
 cand-0.003
 eighty-0.003
 cash-0.003
 penn-0.003
Tokenig
Token ID328
Feature activation+4.52e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.011
pen-0.011
 marry-0.011
Token.
Token ID13
Feature activation-2.27e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.009
 Betty+0.009
Neg logit contributions
 Evan-0.012
 cand-0.012
 eighty-0.012
pen-0.012
 cash-0.011
Token His
Token ID2399
Feature activation-2.32e-01

Pos logit contributions
 Evan+0.004
 himself+0.003
 cash+0.003
 Qu+0.003
pen+0.003
Neg logit contributions
imi-0.008
iet-0.007
anne-0.007
 outage-0.007
arge-0.007
Token day
Token ID1110
Feature activation+1.04e-01

Pos logit contributions
 Janet+0.013
 Judy+0.013
arge+0.013
imi+0.013
Bet+0.012
Neg logit contributions
 Evan-0.013
 cand-0.012
 eighty-0.012
 cash-0.011
 marry-0.011
Token,
Token ID11
Feature activation+4.25e-01

Pos logit contributions
imi+0.003
 Betty+0.003
 Janet+0.003
 Judy+0.003
 June+0.003
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
yle-0.002
Token he
Token ID339
Feature activation-2.11e-01

Pos logit contributions
arge+0.011
 Judy+0.011
 Janet+0.011
imi+0.011
anne+0.011
Neg logit contributions
 Evan-0.010
 cand-0.009
 eighty-0.009
 cash-0.009
pen-0.009
Token dug
Token ID18735
Feature activation+3.20e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 eighty+0.005
 cash+0.005
pen+0.004
Neg logit contributions
 Judy-0.005
 Janet-0.005
arge-0.005
imi-0.005
 Betty-0.005
Token a
Token ID257
Feature activation+2.18e-01

Pos logit contributions
 Judy+0.008
 Betty+0.008
iet+0.008
Bet+0.008
 Janet+0.008
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
yle-0.007
Token very
Token ID845
Feature activation+2.12e+00

Pos logit contributions
 Janet+0.005
arge+0.005
 Judy+0.005
anne+0.004
imi+0.004
Neg logit contributions
 cand-0.006
 Evan-0.006
 cash-0.006
 penn-0.006
 eighty-0.006
Token big
Token ID1263
Feature activation+9.39e-01

Pos logit contributions
 Janet+0.055
arge+0.053
Bet+0.053
 Judy+0.053
 Lynn+0.052
Neg logit contributions
 Evan-0.051
 cand-0.051
 penn-0.048
 eighty-0.047
 cash-0.046
Token hole
Token ID7604
Feature activation+4.89e-01

Pos logit contributions
arge+0.016
 Judy+0.016
 Janet+0.016
imi+0.016
anne+0.015
Neg logit contributions
 Evan-0.031
 cand-0.031
 eighty-0.029
 cash-0.029
 penn-0.028
Token.
Token ID13
Feature activation+3.99e-01

Pos logit contributions
 Janet+0.018
arge+0.018
imi+0.018
 Judy+0.018
Bet+0.018
Neg logit contributions
 Evan-0.006
 eighty-0.005
 cand-0.005
 himself-0.005
pen-0.005
Token
Token ID198
Feature activation-6.89e-03

Pos logit contributions
arge+0.013
 Judy+0.012
 Janet+0.012
imi+0.012
anne+0.012
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.006
pen-0.006
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
pen+0.000
 eighty+0.000
 himself+0.000
Neg logit contributions
arge-0.000
 Janet-0.000
 Judy-0.000
imi-0.000
iet-0.000
Token hello
Token ID23748
Feature activation-3.67e-01

Pos logit contributions
 Judy+0.018
 Betty+0.017
 Janet+0.017
 June+0.017
 Bree+0.017
Neg logit contributions
 Evan-0.014
pen-0.014
 cash-0.014
 cand-0.013
yle-0.013
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
 Evan+0.010
 cand+0.009
 eighty+0.009
 cash+0.009
pen+0.009
Neg logit contributions
 Judy-0.008
 Janet-0.008
arge-0.008
 Betty-0.008
imi-0.008
Token The
Token ID383
Feature activation+5.58e-01

Pos logit contributions
arge+0.006
imi+0.006
 Janet+0.006
 Judy+0.006
anne+0.006
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.004
 cash-0.004
 Qu-0.003
Token dog
Token ID3290
Feature activation-1.29e-02

Pos logit contributions
 Judy+0.014
imi+0.014
 Janet+0.014
arge+0.014
 Betty+0.014
Neg logit contributions
 Evan-0.013
 cand-0.012
 eighty-0.012
pen-0.012
 cash-0.012
Token w
Token ID266
Feature activation+9.21e-01

Pos logit contributions
 Evan+0.000
yle+0.000
pen+0.000
 cand+0.000
 eighty+0.000
Neg logit contributions
imi-0.000
 Lynn-0.000
iet-0.000
 Judy-0.000
 Betty-0.000
Tokenags
Token ID3775
Feature activation+2.00e+00

Pos logit contributions
imi+0.012
arge+0.012
 Judy+0.012
 Janet+0.012
iet+0.011
Neg logit contributions
 Evan-0.034
 cand-0.033
 eighty-0.032
 cash-0.032
pen-0.031
Token its
Token ID663
Feature activation-1.48e+00

Pos logit contributions
arge+0.063
imi+0.063
 Judy+0.062
 Janet+0.062
Bet+0.062
Neg logit contributions
 Evan-0.037
 cand-0.033
 eighty-0.033
 cash-0.030
 himself-0.030
Token tail
Token ID7894
Feature activation-4.74e-01

Pos logit contributions
 Evan+0.043
 cand+0.041
 eighty+0.039
 cash+0.039
pen+0.039
Neg logit contributions
 Judy-0.031
 Janet-0.031
arge-0.031
imi-0.030
 Betty-0.030
Token and
Token ID290
Feature activation+3.40e-01

Pos logit contributions
 Evan+0.014
 cand+0.013
yle+0.012
 cash+0.012
 penn+0.012
Neg logit contributions
 Judy-0.009
anne-0.009
imi-0.009
iet-0.009
 Betty-0.009
Token l
Token ID300
Feature activation-4.86e-01

Pos logit contributions
 Judy+0.010
 Janet+0.010
 Betty+0.010
imi+0.010
 Lynn+0.010
Neg logit contributions
 Evan-0.007
 cand-0.006
pen-0.006
 eighty-0.006
 cash-0.005
Tokenicks
Token ID3378
Feature activation+1.76e+00

Pos logit contributions
 Evan+0.018
 cash+0.017
 cand+0.017
 hairc+0.016
 eighty+0.016
Neg logit contributions
 Judy-0.007
imi-0.007
arl-0.006
oky-0.006
arge-0.006
Token her
Token ID607
Feature activation-4.01e-01

Pos logit contributions
 Judy+0.008
arge+0.008
 Janet+0.008
imi+0.008
anne+0.008
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.005
Token mom
Token ID1995
Feature activation-1.29e+00

Pos logit contributions
 Evan+0.009
 cand+0.008
 cash+0.008
 eighty+0.008
 marry+0.007
Neg logit contributions
Bet-0.012
 Judy-0.012
 Janet-0.012
arge-0.011
anne-0.011
Token.
Token ID13
Feature activation-4.19e-02

Pos logit contributions
 Evan+0.025
 cand+0.025
 eighty+0.023
 cash+0.023
pen+0.022
Neg logit contributions
arge-0.038
 Judy-0.038
 Janet-0.038
Bet-0.038
imi-0.038
Token Her
Token ID2332
Feature activation+5.22e-02

Pos logit contributions
 Evan+0.001
 cand+0.001
 cash+0.001
 Qu+0.001
 marry+0.001
Neg logit contributions
iet-0.001
anne-0.001
arge-0.001
zie-0.001
imi-0.001
Token mom
Token ID1995
Feature activation-3.10e-01

Pos logit contributions
 Judy+0.002
 Janet+0.002
Bet+0.001
arge+0.001
anne+0.001
Neg logit contributions
 cand-0.001
 Evan-0.001
 cash-0.001
 eighty-0.001
 penn-0.001
Token hugged
Token ID41130
Feature activation+9.30e-01

Pos logit contributions
 Evan+0.009
 penn+0.008
 eighty+0.008
 Mont+0.007
 cand+0.007
Neg logit contributions
imi-0.006
 Lynn-0.006
arge-0.006
 Janet-0.006
 Judy-0.006
Token her
Token ID607
Feature activation-5.56e-01

Pos logit contributions
 Judy+0.024
 Janet+0.024
imi+0.023
 Betty+0.023
arge+0.023
Neg logit contributions
 Evan-0.023
 cand-0.022
 eighty-0.021
pen-0.020
 cash-0.020
Token and
Token ID290
Feature activation-3.25e-01

Pos logit contributions
 Evan+0.015
 cand+0.014
pen+0.013
 penn+0.013
 eighty+0.013
Neg logit contributions
 Judy-0.013
arge-0.012
 Janet-0.012
imi-0.012
iet-0.012
Token said
Token ID531
Feature activation+2.91e-01

Pos logit contributions
 Evan+0.009
 cand+0.009
 eighty+0.008
pen+0.008
 cash+0.008
Neg logit contributions
 Judy-0.007
 Janet-0.007
arge-0.007
imi-0.007
 Betty-0.007
Token she
Token ID673
Feature activation+5.30e-01

Pos logit contributions
imi+0.007
 Judy+0.007
 Betty+0.006
 Janet+0.006
 Maria+0.006
Neg logit contributions
 Evan-0.007
pen-0.007
 cash-0.007
 eighty-0.007
hop-0.007
Token was
Token ID373
Feature activation+4.17e-01

Pos logit contributions
arge+0.013
imi+0.013
 Janet+0.013
anne+0.013
 Judy+0.013
Neg logit contributions
 Evan-0.013
 eighty-0.012
 cand-0.011
 penn-0.011
 cash-0.011
Token and
Token ID290
Feature activation-2.28e-01

Pos logit contributions
 Evan+0.018
 eighty+0.017
 cash+0.016
yle+0.016
 cand+0.016
Neg logit contributions
 Judy-0.016
 Betty-0.016
arge-0.016
 Janet-0.015
 Maria-0.015
Token could
Token ID714
Feature activation-1.06e+00

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 cash+0.004
 penn+0.004
Neg logit contributions
arge-0.007
imi-0.007
 Janet-0.007
 Judy-0.007
Bet-0.007
Token never
Token ID1239
Feature activation+1.04e-01

Pos logit contributions
 Evan+0.021
 cand+0.020
 eighty+0.020
 cash+0.019
 marry+0.018
Neg logit contributions
arge-0.031
 Janet-0.031
imi-0.031
 Judy-0.031
anne-0.031
Token get
Token ID651
Feature activation+2.88e-01

Pos logit contributions
 Judy+0.003
 Betty+0.003
 Janet+0.003
anne+0.002
 Maria+0.002
Neg logit contributions
 Evan-0.003
 cand-0.002
 eighty-0.002
 cash-0.002
 penn-0.002
Token enough
Token ID1576
Feature activation+1.03e-01

Pos logit contributions
 Judy+0.008
 Janet+0.008
arge+0.008
imi+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.007
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.006
Token to
Token ID284
Feature activation+4.41e-01

Pos logit contributions
arge+0.003
 Janet+0.003
 Judy+0.003
imi+0.003
Bet+0.003
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
 penn-0.002
Token eat
Token ID4483
Feature activation+8.36e-01

Pos logit contributions
 Judy+0.014
arge+0.014
 Janet+0.014
 Betty+0.014
imi+0.013
Neg logit contributions
 Evan-0.008
 cand-0.008
 eighty-0.007
 cash-0.007
pen-0.007
Token.
Token ID13
Feature activation+2.77e-01

Pos logit contributions
arge+0.024
 Janet+0.024
 Judy+0.024
imi+0.024
anne+0.023
Neg logit contributions
 Evan-0.018
 cand-0.017
 eighty-0.016
 cash-0.016
pen-0.015
Token She
Token ID1375
Feature activation+2.52e-01

Pos logit contributions
iet+0.009
arge+0.009
lights+0.009
 Janet+0.009
 Judy+0.009
Neg logit contributions
 Evan-0.005
 cand-0.004
 cash-0.004
 eighty-0.004
 Qu-0.003
Token would
Token ID561
Feature activation-5.63e-01

Pos logit contributions
arge+0.006
 Judy+0.006
anne+0.006
imi+0.006
 Janet+0.006
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.006
pen-0.006
 cash-0.005
Token go
Token ID467
Feature activation-1.10e+00

Pos logit contributions
 Evan+0.010
 cand+0.010
 eighty+0.009
 cash+0.009
pen+0.009
Neg logit contributions
 Judy-0.018
arge-0.018
 Janet-0.018
imi-0.017
 Betty-0.017
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
arge+0.019
imi+0.019
 Janet+0.019
 Judy+0.019
anne+0.019
Neg logit contributions
 Evan-0.010
 cand-0.010
 himself-0.009
pen-0.009
 eighty-0.009
Token
Token ID220
Feature activation+7.43e-01

Pos logit contributions
 Judy+0.007
 Janet+0.007
arge+0.007
 Betty+0.007
imi+0.007
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.004
 cash-0.004
 penn-0.004
Token
Token ID198
Feature activation-1.77e-01

Pos logit contributions
arge+0.025
 Janet+0.024
iet+0.024
 Judy+0.024
imi+0.024
Neg logit contributions
 Evan-0.013
 himself-0.011
pen-0.010
 cand-0.010
 eighty-0.010
Token
Token ID198
Feature activation+3.62e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
pen+0.003
 cash+0.003
Neg logit contributions
arge-0.006
 Judy-0.006
 Janet-0.006
imi-0.006
iet-0.005
TokenThe
Token ID464
Feature activation+2.50e-01

Pos logit contributions
 Judy+0.010
arge+0.010
 Janet+0.010
imi+0.009
Bet+0.009
Neg logit contributions
 Evan-0.009
 cand-0.008
 eighty-0.008
 cash-0.008
 penn-0.007
Token bear
Token ID6842
Feature activation+3.60e-01

Pos logit contributions
imi+0.007
arge+0.007
 Judy+0.006
 Betty+0.006
 Janet+0.006
Neg logit contributions
 Evan-0.006
 cand-0.005
 eighty-0.005
pen-0.005
 cash-0.005
Token was
Token ID373
Feature activation-3.29e-01

Pos logit contributions
arge+0.011
 Judy+0.011
 Janet+0.011
imi+0.011
 Betty+0.011
Neg logit contributions
 Evan-0.007
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.006
Token looking
Token ID2045
Feature activation-2.13e-02

Pos logit contributions
 Evan+0.008
 cand+0.007
 eighty+0.007
 cash+0.007
pen+0.006
Neg logit contributions
 Judy-0.009
arge-0.009
 Janet-0.009
imi-0.009
 Betty-0.009
Token for
Token ID329
Feature activation-4.58e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
 cash+0.000
 penn+0.000
Neg logit contributions
arge-0.001
 Janet-0.001
 Judy-0.001
imi-0.001
Bet-0.001
Token honey
Token ID12498
Feature activation+2.46e-01

Pos logit contributions
 Evan+0.011
 eighty+0.011
yle+0.010
pen+0.010
 cand+0.010
Neg logit contributions
 Betty-0.013
 Judy-0.013
 Maria-0.012
 Janet-0.012
 Bree-0.012
Token near
Token ID1474
Feature activation+9.45e-01

Pos logit contributions
arge+0.007
 Janet+0.007
 Judy+0.007
imi+0.007
anne+0.007
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.004
 cash-0.004
pen-0.004
Token.
Token ID13
Feature activation+3.43e-01

Pos logit contributions
 cand+0.002
 Evan+0.002
 marry+0.001
 penn+0.001
 himself+0.001
Neg logit contributions
Bet-0.003
arge-0.003
 Janet-0.003
imi-0.003
 Judy-0.003
Token So
Token ID1406
Feature activation+4.21e-01

Pos logit contributions
iet+0.010
arge+0.010
imi+0.010
 Janet+0.010
 Judy+0.010
Neg logit contributions
 Evan-0.008
 eighty-0.006
 cand-0.006
 cash-0.006
 Qu-0.006
Token,
Token ID11
Feature activation+2.39e-01

Pos logit contributions
arge+0.013
imi+0.013
 Janet+0.013
 Judy+0.013
anne+0.013
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
 penn-0.006
Token the
Token ID262
Feature activation+1.20e-01

Pos logit contributions
arge+0.007
 Judy+0.007
imi+0.007
 Janet+0.007
anne+0.007
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.004
 cash-0.004
pen-0.004
Token family
Token ID1641
Feature activation-8.46e-01

Pos logit contributions
 Judy+0.003
 Janet+0.003
arge+0.003
imi+0.003
Bet+0.003
Neg logit contributions
 Evan-0.003
 cand-0.002
 cash-0.002
 eighty-0.002
 penn-0.002
Token shared
Token ID4888
Feature activation+5.89e-01

Pos logit contributions
 Evan+0.019
 cand+0.018
 eighty+0.017
 cash+0.017
pen+0.016
Neg logit contributions
 Judy-0.023
 Janet-0.023
arge-0.023
 Betty-0.022
anne-0.022
Token their
Token ID511
Feature activation+6.85e-01

Pos logit contributions
 Judy+0.018
arge+0.018
 Janet+0.018
imi+0.018
 Betty+0.017
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.010
 cash-0.010
pen-0.010
Token spray
Token ID11662
Feature activation+1.80e-01

Pos logit contributions
 Judy+0.018
arge+0.018
 Janet+0.018
imi+0.018
 Betty+0.017
Neg logit contributions
 Evan-0.016
 eighty-0.015
 cand-0.015
 cash-0.014
pen-0.014
Token and
Token ID290
Feature activation+2.54e-01

Pos logit contributions
arge+0.005
 Judy+0.005
 Janet+0.005
imi+0.005
anne+0.005
Neg logit contributions
 Evan-0.004
 cand-0.003
 cash-0.003
 eighty-0.003
pen-0.003
Token gave
Token ID2921
Feature activation+6.38e-01

Pos logit contributions
 Judy+0.007
 Janet+0.007
arge+0.007
imi+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.005
 cash-0.005
pen-0.004
Token some
Token ID617
Feature activation-1.32e-01

Pos logit contributions
 Judy+0.019
 Janet+0.018
arge+0.018
 Betty+0.018
imi+0.018
Neg logit contributions
 Evan-0.014
 cand-0.013
 eighty-0.012
 cash-0.012
pen-0.012
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
arge-0.002
 Judy-0.002
 Janet-0.002
imi-0.002
Bet-0.002
Token it
Token ID340
Feature activation-1.11e-01

Pos logit contributions
arge+0.007
imi+0.007
 Judy+0.007
 Janet+0.007
anne+0.007
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.004
Token's
Token ID338
Feature activation+8.51e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.001
 cash+0.001
pen+0.001
Neg logit contributions
 Judy-0.004
arge-0.004
 Janet-0.004
imi-0.004
 Betty-0.004
Token easy
Token ID2562
Feature activation-4.15e-01

Pos logit contributions
arge+0.032
anne+0.030
oky+0.030
 Judy+0.030
iet+0.030
Neg logit contributions
 Evan-0.012
 cand-0.011
 eighty-0.011
 himself-0.011
 marry-0.010
Token."
Token ID526
Feature activation+8.05e-02

Pos logit contributions
 cand+0.007
 Evan+0.006
 himself+0.006
 hairc+0.006
 marry+0.006
Neg logit contributions
Bet-0.015
arge-0.014
iet-0.014
 Janet-0.014
imi-0.014
Token
Token ID220
Feature activation+1.02e+00

Pos logit contributions
iet+0.002
arge+0.002
imi+0.002
lights+0.002
oky+0.002
Neg logit contributions
 Evan-0.002
 cand-0.001
 cash-0.001
pen-0.001
 himself-0.001
Token
Token ID198
Feature activation+1.36e-01

Pos logit contributions
iet+0.036
arge+0.036
 Janet+0.034
lights+0.034
anne+0.034
Neg logit contributions
 Evan-0.015
 himself-0.012
pen-0.012
 eighty-0.011
 Qu-0.011
Token
Token ID198
Feature activation+5.17e-01

Pos logit contributions
lights+0.005
arge+0.004
iet+0.004
oky+0.004
imi+0.004
Neg logit contributions
 Evan-0.002
 himself-0.002
pen-0.002
 cash-0.002
 eighty-0.002
TokenThe
Token ID464
Feature activation+2.83e-01

Pos logit contributions
arge+0.014
imi+0.014
 Judy+0.014
 Janet+0.014
lights+0.014
Neg logit contributions
 Evan-0.012
 cand-0.010
 cash-0.010
 eighty-0.010
pen-0.010
Token little
Token ID1310
Feature activation+4.10e-01

Pos logit contributions
 Judy+0.008
 Janet+0.008
arge+0.008
anne+0.008
imi+0.008
Neg logit contributions
 Evan-0.006
 cand-0.006
 cash-0.005
 eighty-0.005
 penn-0.005
Token boy
Token ID2933
Feature activation-1.32e-02

Pos logit contributions
arge+0.012
 Judy+0.012
 Janet+0.012
imi+0.011
Bet+0.011
Neg logit contributions
 Evan-0.009
 cand-0.008
 eighty-0.008
 cash-0.008
 penn-0.008
Token "
Token ID366
Feature activation+3.67e-01

Pos logit contributions
 Evan+0.003
 cash+0.002
 eighty+0.002
 cand+0.002
 Qu+0.002
Neg logit contributions
arge-0.004
iet-0.004
imi-0.004
anne-0.004
 Janet-0.004
TokenThose
Token ID9627
Feature activation-7.49e-01

Pos logit contributions
Bet+0.008
arge+0.008
 Judy+0.008
oky+0.008
iet+0.007
Neg logit contributions
 Evan-0.010
 cand-0.010
 eighty-0.009
 penn-0.009
pen-0.009
Token are
Token ID389
Feature activation-1.71e-01

Pos logit contributions
 Evan+0.013
 eighty+0.012
 cand+0.011
 cash+0.011
pen+0.011
Neg logit contributions
 Judy-0.024
arge-0.024
 Janet-0.024
imi-0.024
 Betty-0.024
Token Mom
Token ID11254
Feature activation+6.70e-02

Pos logit contributions
 cand+0.004
 Evan+0.004
 eighty+0.004
 penn+0.003
 cash+0.003
Neg logit contributions
anne-0.005
 Janet-0.005
arge-0.005
 Judy-0.005
iet-0.005
Tokenmy
Token ID1820
Feature activation+1.93e-01

Pos logit contributions
arge+0.002
 Janet+0.002
 Judy+0.002
Bet+0.002
iet+0.002
Neg logit contributions
 cand-0.001
 Evan-0.001
 eighty-0.001
pen-0.001
's-0.001
Token's
Token ID338
Feature activation-5.75e-01

Pos logit contributions
 Judy+0.005
arge+0.005
 Janet+0.005
imi+0.005
Bet+0.005
Neg logit contributions
 Evan-0.005
 cand-0.004
 eighty-0.004
 cash-0.004
pen-0.004
Token flowers
Token ID12734
Feature activation-2.32e-01

Pos logit contributions
 cand+0.012
 marry+0.011
 penn+0.011
 re+0.011
 cash+0.011
Neg logit contributions
 Janet-0.017
Maria-0.017
Bet-0.017
 Judy-0.017
 Lynn-0.017
Token.
Token ID13
Feature activation-5.05e-01

Pos logit contributions
 cand+0.005
 Evan+0.005
 eighty+0.004
 marry+0.004
pen+0.004
Neg logit contributions
 Janet-0.007
arge-0.007
 Judy-0.007
Bet-0.007
imi-0.007
Token You
Token ID921
Feature activation-3.15e-01

Pos logit contributions
 Evan+0.013
 cand+0.012
 eighty+0.012
 cash+0.011
 marry+0.011
Neg logit contributions
arge-0.012
 Janet-0.012
 Judy-0.012
imi-0.012
anne-0.012
Token can
Token ID460
Feature activation-1.20e+00

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
 Judy-0.009
 Janet-0.009
arge-0.009
imi-0.009
 Betty-0.009
Token't
Token ID470
Feature activation+1.98e-01

Pos logit contributions
 Evan+0.026
 cand+0.024
 eighty+0.023
 cash+0.022
 penn+0.022
Neg logit contributions
imi-0.034
 Judy-0.034
arge-0.034
 Janet-0.033
 Betty-0.033
Token to
Token ID284
Feature activation+5.00e-01

Pos logit contributions
arge+0.000
 Judy+0.000
 Janet+0.000
imi+0.000
anne+0.000
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
 cash-0.000
pen-0.000
Token be
Token ID307
Feature activation+5.96e-01

Pos logit contributions
 Judy+0.014
 Janet+0.014
imi+0.014
 Betty+0.014
arge+0.014
Neg logit contributions
 Evan-0.010
 cand-0.010
 eighty-0.009
yle-0.009
 penn-0.009
Token honest
Token ID5508
Feature activation-7.52e-01

Pos logit contributions
 Judy+0.017
 Janet+0.017
arge+0.016
 Betty+0.016
imi+0.016
Neg logit contributions
 Evan-0.013
 cand-0.012
 eighty-0.012
 cash-0.011
pen-0.011
Token and
Token ID290
Feature activation+2.13e-02

Pos logit contributions
 Evan+0.016
 cand+0.015
 eighty+0.015
 cash+0.014
pen+0.014
Neg logit contributions
 Judy-0.021
arge-0.021
 Janet-0.021
imi-0.021
 Betty-0.021
Token kind
Token ID1611
Feature activation-5.90e-01

Pos logit contributions
 Judy+0.001
 Janet+0.001
arge+0.001
 Betty+0.001
imi+0.001
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
pen-0.000
 cash-0.000
Token.
Token ID13
Feature activation+3.70e-03

Pos logit contributions
 Evan+0.014
 cand+0.014
 eighty+0.013
 cash+0.013
pen+0.012
Neg logit contributions
 Judy-0.015
arge-0.015
 Janet-0.015
imi-0.015
 Betty-0.015
Token Do
Token ID2141
Feature activation+1.76e-01

Pos logit contributions
 Judy+0.000
 Janet+0.000
arge+0.000
imi+0.000
 Betty+0.000
Neg logit contributions
 Evan-0.000
 cand-0.000
 eighty-0.000
 cash-0.000
pen-0.000
Token you
Token ID345
Feature activation+3.15e-01

Pos logit contributions
imi+0.005
 Janet+0.004
 Judy+0.004
arge+0.004
 Betty+0.004
Neg logit contributions
 Evan-0.004
 eighty-0.004
pen-0.004
 cand-0.004
 cash-0.004
Token understand
Token ID1833
Feature activation-6.62e-01

Pos logit contributions
 Judy+0.011
 Janet+0.011
arge+0.011
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.005
 cand-0.005
 eighty-0.004
 cash-0.004
pen-0.004
Token?"
Token ID1701
Feature activation-1.15e-02

Pos logit contributions
 Evan+0.021
 cand+0.021
 cash+0.020
 eighty+0.020
 marry+0.020
Neg logit contributions
anne-0.012
Bet-0.012
 Judy-0.012
 Janet-0.011
arge-0.011
Token
Token ID198
Feature activation+2.83e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
pen+0.000
 cash+0.000
Neg logit contributions
 Judy-0.000
 Janet-0.000
arge-0.000
imi-0.000
 Betty-0.000
Token,
Token ID11
Feature activation+2.66e-01

Pos logit contributions
 Judy+0.032
arge+0.032
 Janet+0.032
imi+0.031
 Betty+0.031
Neg logit contributions
 Evan-0.019
 cand-0.018
 eighty-0.017
 cash-0.016
pen-0.016
Token stop
Token ID2245
Feature activation-3.16e-01

Pos logit contributions
imi+0.007
 Judy+0.007
 Janet+0.007
arge+0.006
 Betty+0.006
Neg logit contributions
 Evan-0.006
 cand-0.006
pen-0.006
 eighty-0.006
 cash-0.006
Token it
Token ID340
Feature activation-1.72e-02

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.006
Neg logit contributions
anne-0.009
Bet-0.009
 Judy-0.009
arge-0.009
 Janet-0.009
Token!"
Token ID2474
Feature activation-5.96e-01

Pos logit contributions
 Evan+0.000
 cand+0.000
 eighty+0.000
pen+0.000
 cash+0.000
Neg logit contributions
 Judy-0.000
arge-0.000
 Janet-0.000
Bet-0.000
anne-0.000
Token Sara
Token ID24799
Feature activation+7.27e-01

Pos logit contributions
pen+0.015
 eighty+0.015
 cand+0.014
 Evan+0.014
 ninety+0.013
Neg logit contributions
 Judy-0.014
 Betty-0.013
arge-0.013
imi-0.013
 Lynn-0.013
Token said
Token ID531
Feature activation-3.20e-01

Pos logit contributions
 Judy+0.016
arge+0.016
 Janet+0.016
imi+0.016
 Betty+0.016
Neg logit contributions
 Evan-0.020
 cand-0.019
 eighty-0.019
 cash-0.018
pen-0.017
Token.
Token ID13
Feature activation-2.47e-01

Pos logit contributions
 Evan+0.009
 cand+0.009
 eighty+0.009
 cash+0.009
 ninety+0.008
Neg logit contributions
 Judy-0.007
 Maria-0.007
 Janet-0.006
anne-0.006
 Betty-0.006
Token "
Token ID366
Feature activation+3.24e-01

Pos logit contributions
 Evan+0.006
 cand+0.006
 eighty+0.006
 cash+0.006
pen+0.005
Neg logit contributions
arge-0.006
 Janet-0.006
imi-0.006
 Judy-0.006
anne-0.006
TokenYou
Token ID1639
Feature activation-2.88e-02

Pos logit contributions
arge+0.007
Bet+0.006
oky+0.006
iet+0.006
 Judy+0.006
Neg logit contributions
 Evan-0.010
 cand-0.010
 penn-0.009
 eighty-0.009
 cash-0.008
Token are
Token ID389
Feature activation+3.91e-01

Pos logit contributions
 Evan+0.001
 cand+0.001
 eighty+0.001
 cash+0.001
 ninety+0.001
Neg logit contributions
 Janet-0.001
 Judy-0.001
imi-0.001
arge-0.001
 Betty-0.001
Token making
Token ID1642
Feature activation+2.38e-01

Pos logit contributions
 Janet+0.008
arge+0.008
 Judy+0.008
 Betty+0.008
 June+0.008
Neg logit contributions
 Evan-0.011
 cand-0.010
 eighty-0.010
pen-0.010
hop-0.010
Token and
Token ID290
Feature activation+1.42e-01

Pos logit contributions
 Judy+0.011
 Janet+0.010
arge+0.010
imi+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.012
 cand-0.011
 cash-0.010
 eighty-0.010
pen-0.010
Token thanked
Token ID26280
Feature activation+6.54e-01

Pos logit contributions
 Judy+0.004
 Janet+0.004
 Betty+0.003
 Lynn+0.003
 Bree+0.003
Neg logit contributions
 Evan-0.004
pen-0.003
 eighty-0.003
 cand-0.003
yle-0.003
Token Mama
Token ID40084
Feature activation-1.20e+00

Pos logit contributions
 Judy+0.019
 Janet+0.019
arge+0.019
imi+0.018
 Betty+0.018
Neg logit contributions
 Evan-0.014
 cand-0.013
 eighty-0.013
 cash-0.012
pen-0.012
Token.
Token ID13
Feature activation+2.89e-01

Pos logit contributions
 Evan+0.027
 cand+0.026
 eighty+0.025
 cash+0.024
pen+0.023
Neg logit contributions
 Judy-0.033
arge-0.033
 Janet-0.033
imi-0.032
Bet-0.031
Token They
Token ID1119
Feature activation+3.45e-01

Pos logit contributions
anne+0.010
iet+0.010
arge+0.009
 outage+0.009
iders+0.009
Neg logit contributions
 Evan-0.005
 Qu-0.004
 Pe-0.004
 cash-0.004
 eighty-0.004
Token put
Token ID1234
Feature activation-4.38e-01

Pos logit contributions
 Janet+0.009
 Judy+0.009
Bet+0.008
iet+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.008
 hairc-0.008
 eighty-0.007
 cand-0.007
yle-0.007
Token their
Token ID511
Feature activation+3.54e-01

Pos logit contributions
 Evan+0.009
 cand+0.008
 eighty+0.008
pen+0.007
 cash+0.007
Neg logit contributions
 Judy-0.013
 Janet-0.013
arge-0.013
 Betty-0.013
imi-0.013
Token pieces
Token ID5207
Feature activation-3.22e-01

Pos logit contributions
imi+0.007
arge+0.007
 Judy+0.007
 Janet+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.011
pen-0.009
etr-0.009
 eighty-0.009
hop-0.009
Token of
Token ID286
Feature activation+7.19e-01

Pos logit contributions
 Evan+0.008
 cash+0.007
 cand+0.007
 eighty+0.007
pen+0.007
Neg logit contributions
 Judy-0.008
 Janet-0.008
lights-0.008
iet-0.008
 Betty-0.008
Token the
Token ID262
Feature activation+1.41e-01

Pos logit contributions
 Judy+0.016
 Betty+0.015
 Maria+0.015
imi+0.015
 Janet+0.015
Neg logit contributions
 Evan-0.020
 eighty-0.017
pen-0.017
etr-0.017
yle-0.017
Token magnet
Token ID19972
Feature activation+1.09e+00

Pos logit contributions
imi+0.003
 window+0.003
 vine+0.003
 hose+0.003
 blender+0.003
Neg logit contributions
 Evan-0.004
hop-0.003
yle-0.003
pen-0.003
 Mont-0.003
Token Max
Token ID5436
Feature activation+1.82e-01

Pos logit contributions
 Judy+0.014
 Janet+0.014
arge+0.014
imi+0.014
 Betty+0.014
Neg logit contributions
 Evan-0.012
 cand-0.012
 eighty-0.011
 cash-0.011
 penn-0.011
Token and
Token ID290
Feature activation-3.12e-01

Pos logit contributions
 June+0.003
imi+0.003
 Betty+0.003
 Judy+0.003
 Lynn+0.003
Neg logit contributions
 Evan-0.006
yle-0.005
 cand-0.005
 cash-0.005
 marry-0.005
Token play
Token ID711
Feature activation-3.81e-01

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
pen+0.006
 cash+0.006
Neg logit contributions
 Judy-0.009
 Janet-0.009
arge-0.009
imi-0.009
 Betty-0.009
Token with
Token ID351
Feature activation-1.66e-01

Pos logit contributions
 Evan+0.007
 cand+0.006
 eighty+0.006
 penn+0.006
 cash+0.006
Neg logit contributions
 Judy-0.012
 Janet-0.012
 June-0.012
 Betty-0.011
 Lynn-0.011
Token him
Token ID683
Feature activation-4.21e-01

Pos logit contributions
 Evan+0.003
 cand+0.002
 eighty+0.002
 cash+0.002
 penn+0.002
Neg logit contributions
 Judy-0.006
 Janet-0.006
arge-0.006
imi-0.006
 Betty-0.006
Token.
Token ID13
Feature activation+9.89e-02

Pos logit contributions
 Evan+0.012
 eighty+0.011
 cand+0.011
 cash+0.011
pen+0.010
Neg logit contributions
imi-0.008
 Betty-0.008
 Judy-0.008
 Janet-0.008
 June-0.008
Token They
Token ID1119
Feature activation+5.94e-02

Pos logit contributions
arge+0.003
imi+0.003
iet+0.003
anne+0.003
 Judy+0.003
Neg logit contributions
 Evan-0.002
 Qu-0.002
 eighty-0.002
 cand-0.002
 himself-0.002
Token wait
Token ID4043
Feature activation-7.24e-01

Pos logit contributions
 Judy+0.002
 Janet+0.002
Bet+0.002
 Betty+0.002
arge+0.002
Neg logit contributions
 Evan-0.001
 cand-0.001
 eighty-0.001
 cash-0.001
pen-0.001
Token for
Token ID329
Feature activation-3.85e-01

Pos logit contributions
 Evan+0.014
 eighty+0.013
 cand+0.013
 goodbye+0.012
 cash+0.012
Neg logit contributions
 Janet-0.023
Bet-0.022
 Judy-0.022
imi-0.022
arge-0.022
Token the
Token ID262
Feature activation+2.97e-01

Pos logit contributions
 Evan+0.008
 cand+0.007
 eighty+0.007
 cash+0.007
pen+0.007
Neg logit contributions
 Judy-0.011
arge-0.011
 Janet-0.011
imi-0.011
 Betty-0.011
Token woman
Token ID2415
Feature activation+2.68e-02

Pos logit contributions
 Judy+0.008
 Janet+0.008
arge+0.008
imi+0.008
 Betty+0.008
Neg logit contributions
 Evan-0.007
 cand-0.007
 cash-0.007
 eighty-0.006
 penn-0.006
Token,
Token ID11
Feature activation-4.34e-01

Pos logit contributions
 Judy+0.002
 Betty+0.002
 Janet+0.002
 Maria+0.002
 June+0.002
Neg logit contributions
 Evan-0.002
pen-0.002
 cash-0.002
 cand-0.002
 eighty-0.002
Token "
Token ID366
Feature activation+2.52e-01

Pos logit contributions
 Evan+0.010
 cand+0.009
 eighty+0.009
 cash+0.009
 ninety+0.008
Neg logit contributions
arge-0.012
imi-0.012
 Judy-0.011
 Janet-0.011
iet-0.011
TokenThat
Token ID2504
Feature activation-2.52e-01

Pos logit contributions
 Judy+0.006
imi+0.006
arge+0.006
 Janet+0.006
 Betty+0.006
Neg logit contributions
 Evan-0.006
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.005
Token is
Token ID318
Feature activation-3.24e-01

Pos logit contributions
 Evan+0.005
 cand+0.005
 eighty+0.005
 cash+0.005
pen+0.004
Neg logit contributions
 Janet-0.007
 Judy-0.007
arge-0.007
imi-0.007
 Betty-0.007
Token an
Token ID281
Feature activation-4.37e-01

Pos logit contributions
 Evan+0.004
 cand+0.004
 eighty+0.004
 marry+0.003
 re+0.003
Neg logit contributions
anne-0.012
arge-0.012
imi-0.012
iet-0.012
Bet-0.011
Token aer
Token ID9551
Feature activation-1.44e+00

Pos logit contributions
 Evan+0.010
 cand+0.010
pen+0.009
 cash+0.009
 eighty+0.009
Neg logit contributions
arge-0.012
 Janet-0.012
 Judy-0.012
imi-0.011
 Betty-0.011
Tokenopl
Token ID20106
Feature activation-1.21e+00

Pos logit contributions
 Evan+0.041
 cand+0.039
 eighty+0.038
pen+0.037
 cash+0.037
Neg logit contributions
 Judy-0.030
 Janet-0.030
arge-0.029
imi-0.029
 Betty-0.029
Tokenane
Token ID1531
Feature activation+4.61e-01

Pos logit contributions
 Evan+0.032
 cand+0.031
 cash+0.029
 eighty+0.028
 penn+0.027
Neg logit contributions
arge-0.030
 Janet-0.030
imi-0.029
 Judy-0.029
oky-0.028
Token!
Token ID0
Feature activation-2.56e-01

Pos logit contributions
arge+0.014
 Judy+0.013
 Janet+0.013
imi+0.013
Bet+0.013
Neg logit contributions
 Evan-0.009
 cand-0.009
 eighty-0.008
 marry-0.008
pen-0.008
Token It
Token ID632
Feature activation-7.79e-01

Pos logit contributions
 Evan+0.006
 cand+0.005
 eighty+0.005
 cash+0.005
pen+0.005
Neg logit contributions
arge-0.007
 Judy-0.007
imi-0.007
 Janet-0.007
anne-0.007
Token's
Token ID338
Feature activation+6.88e-01

Pos logit contributions
 Evan+0.015
 cand+0.014
 cash+0.013
 eighty+0.013
pen+0.013
Neg logit contributions
 Judy-0.024
 Janet-0.024
arge-0.023
imi-0.023
 Betty-0.023
Token,
Token ID11
Feature activation+3.64e-01

Pos logit contributions
arge+0.018
lights+0.018
leys+0.017
oky+0.017
iet+0.017
Neg logit contributions
 Evan-0.005
 cand-0.004
pen-0.004
 eighty-0.004
 cash-0.003
Token I
Token ID314
Feature activation+1.06e+00

Pos logit contributions
 Judy+0.010
 Janet+0.010
imi+0.010
 Betty+0.010
arge+0.010
Neg logit contributions
 Evan-0.008
 cand-0.008
 eighty-0.008
 cash-0.007
pen-0.007
Token'm
Token ID1101
Feature activation+5.50e-01

Pos logit contributions
arge+0.032
 Judy+0.032
 Janet+0.032
imi+0.031
anne+0.031
Neg logit contributions
 Evan-0.021
 cand-0.019
 eighty-0.018
pen-0.018
 cash-0.017
Token scared
Token ID12008
Feature activation+5.18e-01

Pos logit contributions
arge+0.014
anne+0.014
lights+0.014
iet+0.014
imi+0.014
Neg logit contributions
 Evan-0.013
 eighty-0.012
 cand-0.012
 Qu-0.011
 re-0.011
Token of
Token ID286
Feature activation-1.17e-01

Pos logit contributions
 Janet+0.018
 Judy+0.018
arge+0.018
anne+0.018
Bet+0.018
Neg logit contributions
 Evan-0.007
 himself-0.006
 cand-0.006
 re-0.006
 Qu-0.005
Token that
Token ID326
Feature activation-1.42e+00

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 cash+0.002
 penn+0.002
Neg logit contributions
anne-0.004
arge-0.004
 Janet-0.004
 Judy-0.004
iet-0.004
Token gate
Token ID8946
Feature activation+2.22e-02

Pos logit contributions
 Evan+0.032
's+0.031
 hairc+0.030
 re+0.029
 goodbye+0.029
Neg logit contributions
anne-0.035
 Janet-0.035
arl-0.034
Bet-0.034
lights-0.034
Token.
Token ID13
Feature activation-8.60e-02

Pos logit contributions
arge+0.001
Jud+0.001
 Judy+0.001
Bet+0.001
Rachel+0.001
Neg logit contributions
 cand-0.000
 Evan-0.000
's-0.000
 himself-0.000
 re-0.000
Token Can
Token ID1680
Feature activation+7.23e-02

Pos logit contributions
 Evan+0.002
 eighty+0.001
 cash+0.001
 cand+0.001
 Qu+0.001
Neg logit contributions
arge-0.003
iet-0.003
 Judy-0.003
anne-0.003
imi-0.003
Token you
Token ID345
Feature activation+2.19e-01

Pos logit contributions
imi+0.002
 Janet+0.002
 Betty+0.002
 Judy+0.002
 June+0.002
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
pen-0.002
 cash-0.002
Token help
Token ID1037
Feature activation-4.57e-01

Pos logit contributions
 Judy+0.007
 Janet+0.007
imi+0.007
arge+0.007
 Betty+0.007
Neg logit contributions
 Evan-0.004
 cand-0.004
 eighty-0.003
 cash-0.003
 penn-0.003
Tokenay
Token ID323
Feature activation-6.71e-01

Pos logit contributions
 Evan+0.012
 cand+0.011
 eighty+0.011
 cash+0.011
pen+0.011
Neg logit contributions
arge-0.006
imi-0.006
 Janet-0.006
 Judy-0.006
 Betty-0.006
Token,
Token ID11
Feature activation+3.11e-01

Pos logit contributions
 Evan+0.020
 cand+0.019
 eighty+0.018
 cash+0.018
pen+0.017
Neg logit contributions
 Judy-0.014
 Janet-0.014
arge-0.014
imi-0.014
 Betty-0.013
Token let
Token ID1309
Feature activation-2.53e-01

Pos logit contributions
 Judy+0.009
 Janet+0.009
arge+0.009
imi+0.009
 Betty+0.009
Neg logit contributions
 Evan-0.007
 cand-0.006
 eighty-0.006
 cash-0.006
pen-0.006
Tokenâ
Token ID22940
Feature activation+4.18e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 eighty+0.003
 cash+0.003
pen+0.003
Neg logit contributions
 Judy-0.009
 Janet-0.009
imi-0.009
arge-0.009
 Betty-0.009
Token
Token ID26391
Feature activation+4.31e-01

Pos logit contributions
 Janet+0.009
 Judy+0.009
arge+0.009
anne+0.009
imi+0.009
Neg logit contributions
 cand-0.012
 Evan-0.011
 eighty-0.011
 penn-0.011
 cash-0.011
Token
Token ID8151
Feature activation-1.60e+00

Pos logit contributions
 Judy+0.011
arge+0.011
 Janet+0.011
imi+0.011
 Betty+0.010
Neg logit contributions
 Evan-0.011
 cand-0.010
 eighty-0.010
 cash-0.009
pen-0.009
Tokens
Token ID82
Feature activation-4.56e-01

Pos logit contributions
 Evan+0.040
 cand+0.038
 eighty+0.036
 cash+0.035
pen+0.035
Neg logit contributions
 Judy-0.040
 Janet-0.040
arge-0.040
imi-0.039
 Betty-0.038
Token buy
Token ID2822
Feature activation+2.06e-01

Pos logit contributions
 Evan+0.008
 cand+0.007
 eighty+0.007
 cash+0.007
pen+0.006
Neg logit contributions
 Judy-0.015
 Janet-0.015
arge-0.015
imi-0.015
 Betty-0.014
Token it
Token ID340
Feature activation+3.32e-01

Pos logit contributions
 Judy+0.005
arge+0.005
 Janet+0.005
 Betty+0.005
imi+0.005
Neg logit contributions
 Evan-0.004
 eighty-0.004
pen-0.004
 cand-0.004
etr-0.004
Token!
Token ID0
Feature activation+4.41e-01

Pos logit contributions
arge+0.009
 Judy+0.009
 Janet+0.009
imi+0.009
Bet+0.009
Neg logit contributions
 Evan-0.008
 cand-0.007
 eighty-0.007
 cash-0.007
 penn-0.006
Tokenâ
Token ID22940
Feature activation+5.38e-01

Pos logit contributions
arge+0.013
imi+0.013
iet+0.013
 Judy+0.013
anne+0.013
Neg logit contributions
 Evan-0.010
 eighty-0.008
 cand-0.008
 cash-0.008
pen-0.007
Token lived
Token ID5615
Feature activation-1.42e-01

Pos logit contributions
imi+0.001
 Maria+0.001
 Judy+0.001
 Betty+0.001
 Janet+0.001
Neg logit contributions
 eighty-0.002
 cash-0.002
 cand-0.002
 Evan-0.001
 penn-0.001
Token a
Token ID257
Feature activation-4.86e-01

Pos logit contributions
 cand+0.004
 Evan+0.003
 cash+0.003
 hairc+0.003
 penn+0.003
Neg logit contributions
Bet-0.003
 Judy-0.003
 Betty-0.003
imi-0.003
 Maria-0.003
Token little
Token ID1310
Feature activation+6.27e-01

Pos logit contributions
 Evan+0.011
 cand+0.011
 eighty+0.010
 cash+0.010
pen+0.010
Neg logit contributions
 Judy-0.013
arge-0.013
imi-0.013
 Janet-0.013
 Betty-0.013
Token girl
Token ID2576
Feature activation+6.82e-02

Pos logit contributions
imi+0.016
 Judy+0.016
arge+0.016
 Janet+0.016
 Betty+0.016
Neg logit contributions
 Evan-0.015
 cand-0.014
 eighty-0.014
 cash-0.013
pen-0.013
Token named
Token ID3706
Feature activation+1.38e-01

Pos logit contributions
 Judy+0.002
arge+0.002
 Janet+0.002
imi+0.002
 Betty+0.002
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.001
 cash-0.001
pen-0.001
Token Gab
Token ID12300
Feature activation-1.36e+00

Pos logit contributions
lights+0.004
arge+0.004
iet+0.004
puters+0.004
 Janet+0.004
Neg logit contributions
 Evan-0.003
 cand-0.002
 Qu-0.002
 marry-0.002
 cash-0.002
Tokenby
Token ID1525
Feature activation+7.69e-02

Pos logit contributions
 Evan+0.038
 cand+0.035
 cash+0.033
 eighty+0.033
 penn+0.032
Neg logit contributions
imi-0.031
arge-0.030
 Judy-0.030
iet-0.030
 Janet-0.030
Token.
Token ID13
Feature activation-9.39e-02

Pos logit contributions
 Judy+0.002
arge+0.002
 Janet+0.002
imi+0.002
 Betty+0.002
Neg logit contributions
 Evan-0.002
 cand-0.002
 eighty-0.002
 cash-0.002
pen-0.002
Token She
Token ID1375
Feature activation-2.10e-02

Pos logit contributions
 Evan+0.003
 cand+0.003
etr+0.003
 hairc+0.003
pen+0.003
Neg logit contributions
 Judy-0.002
 Janet-0.002
 Betty-0.002
Bet-0.002
 Donna-0.002
Token woke
Token ID19092
Feature activation+4.94e-01

Pos logit contributions
 Evan+0.001
 cash+0.001
 eighty+0.001
 cand+0.001
pen+0.001
Neg logit contributions
imi-0.000
iet-0.000
arge-0.000
anne-0.000
 Janet-0.000
Token up
Token ID510
Feature activation-1.20e+00

Pos logit contributions
imi+0.011
arge+0.011
 Judy+0.011
 Janet+0.011
 Betty+0.011
Neg logit contributions
 Evan-0.013
 cand-0.013
 eighty-0.013
 cash-0.012
pen-0.012
Token Ben
Token ID3932
Feature activation+6.39e-01

Pos logit contributions
 Judy+0.017
 Betty+0.016
 Janet+0.016
 Maria+0.015
 June+0.015
Neg logit contributions
 cand-0.016
 Evan-0.016
pen-0.016
 cash-0.015
 eighty-0.015
Token were
Token ID547
Feature activation-2.37e-01

Pos logit contributions
 Judy+0.015
iet+0.014
 Janet+0.014
 Betty+0.013
Bet+0.013
Neg logit contributions
 cand-0.015
 Evan-0.015
 cash-0.015
 hairc-0.015
 penn-0.015
Token twins
Token ID20345
Feature activation-7.05e-02

Pos logit contributions
 Evan+0.005
 cand+0.004
 eighty+0.004
 cash+0.004
 penn+0.004
Neg logit contributions
 Judy-0.007
 Janet-0.007
arge-0.007
imi-0.007
anne-0.007
Token who
Token ID508
Feature activation+5.64e-01

Pos logit contributions
 Evan+0.002
 cand+0.002
 eighty+0.002
 ninety+0.002
 cash+0.002
Neg logit contributions
arge-0.001
anne-0.001
imi-0.001
 Maria-0.001
 Judy-0.001
Token loved
Token ID6151
Feature activation+1.43e+00

Pos logit contributions
anne+0.013
 Judy+0.013
 Janet+0.013
arge+0.013
 Betty+0.012
Neg logit contributions
 eighty-0.014
 cand-0.014
 Evan-0.014
 penn-0.013
 cash-0.013
Token to
Token ID284
Feature activation-1.42e+00

Pos logit contributions
arge+0.034
 Judy+0.034
 Janet+0.034
 Betty+0.033
imi+0.033
Neg logit contributions
 Evan-0.037
 eighty-0.034
pen-0.033
 cand-0.033
 cash-0.032
Token play
Token ID711
Feature activation-3.31e-01

Pos logit contributions
 Evan+0.025
 cand+0.023
 eighty+0.022
 cash+0.021
pen+0.020
Neg logit contributions
arge-0.046
 Judy-0.046
imi-0.045
 Janet-0.045
Bet-0.045
Token with
Token ID351
Feature activation-5.96e-02

Pos logit contributions
 Evan+0.007
 eighty+0.007
 cand+0.007
 ninety+0.007
 seventy+0.006
Neg logit contributions
imi-0.009
 Janet-0.009
iet-0.008
arge-0.008
 Judy-0.008
Token their
Token ID511
Feature activation-1.36e-01

Pos logit contributions
 Evan+0.002
 eighty+0.002
 cand+0.001
pen+0.001
 cash+0.001
Neg logit contributions
imi-0.001
arge-0.001
 Janet-0.001
 Judy-0.001
 Betty-0.001
Token toys
Token ID14958
Feature activation+4.35e-01

Pos logit contributions
 Evan+0.003
 cand+0.003
 cash+0.003
 eighty+0.003
 penn+0.002
Neg logit contributions
 Judy-0.004
 Janet-0.004
arge-0.004
imi-0.004
Bet-0.004
Token.
Token ID13
Feature activation+1.39e-01

Pos logit contributions
arge+0.010
imi+0.010
 Janet+0.010
 Judy+0.010
 Betty+0.010
Neg logit contributions
 Evan-0.011
 eighty-0.010
 cand-0.010
 cash-0.010
pen-0.010