INDEX
Explanations
mentions of a specific name "Matthews."
repeated mentions of the name "Matthews."
New Auto-Interp
Negative Logits
emort
-1.01
gling
-0.89
izations
-0.86
anguage
-0.86
odor
-0.83
isations
-0.82
ition
-0.81
ation
-0.79
theless
-0.77
ogy
-0.77
POSITIVE LOGITS
'
0.90
bury
0.76
boro
0.76
andra
0.75
hews
0.73
hew
0.73
pora
0.72
hip
0.72
Done
0.71
hiba
0.71
Activations Density 0.088%