INDEX
Explanations
mentions of the name "Fisher"
mentions of the name "Fisher."
New Auto-Interp
Negative Logits
crawl
-0.82
Nazi
-0.67
terday
-0.66
sight
-0.65
dism
-0.64
ablishment
-0.62
contempt
-0.62
Dear
-0.61
denial
-0.58
OPS
-0.58
POSITIVE LOGITS
Fisher
1.14
isher
0.93
bage
0.90
sonian
0.88
strom
0.86
berg
0.85
folk
0.85
aldi
0.83
ota
0.79
pige
0.79
Activations Density 0.008%