INDEX
Explanations
mentions of the word "hammer" and related terms
the term "hammer" and its variations in various contexts
New Auto-Interp
Negative Logits
ected
-0.74
cript
-0.72
Leone
-0.68
ceed
-0.68
uce
-0.68
RIP
-0.67
ocard
-0.65
lus
-0.65
cius
-0.65
yon
-0.64
POSITIVE LOGITS
sonian
1.09
heads
1.04
head
1.01
hammer
0.96
bats
0.96
hammer
0.86
lock
0.82
hamm
0.82
mann
0.76
stone
0.76
Activations Density 0.047%