INDEX
Explanations
references to the name "Jerry" specifically
references to the name "Jerry" in various contexts
New Auto-Interp
Negative Logits
arin
-0.80
ngth
-0.77
yrim
-0.73
alid
-0.72
awaru
-0.69
uyomi
-0.68
hips
-0.68
acle
-0.66
yrinth
-0.65
arent
-0.64
POSITIVE LOGITS
Springer
0.92
Kramer
0.88
stein
0.78
Garcia
0.76
Jerry
0.69
ono
0.69
spective
0.69
Lee
0.68
Pie
0.68
mA
0.67
Activations Density 0.007%