INDEX
Explanations
references to a person named "Adams" with various contexts and actions
mentions of the name "Adams."
New Auto-Interp
Negative Logits
bered
-0.77
ozyg
-0.70
urrent
-0.67
SIGN
-0.65
Canaver
-0.63
ipped
-0.62
entrants
-0.61
oiler
-0.59
ebin
-0.58
paragraph
-0.56
POSITIVE LOGITS
Adams
0.85
olini
0.79
men
0.78
aic
0.77
sov
0.77
kins
0.76
agher
0.75
mond
0.75
man
0.75
nect
0.74
Activations Density 0.013%