INDEX
Explanations
personal reflections, metaphorical reflections, and literal mirrors in a document
references to mirrors and the concept of reflection
New Auto-Interp
Negative Logits
--------------------------------------------------------
-0.81
ensable
-0.77
stant
-0.73
iott
-0.73
Reserve
-0.70
wav
-0.70
cific
-0.70
CVE
-0.70
artney
-0.68
estern
-0.66
POSITIVE LOGITS
ror
0.96
neuron
0.90
mirror
0.90
image
0.84
pane
0.81
reflection
0.81
ocular
0.79
shine
0.77
gazing
0.76
angelo
0.76
Activations Density 0.036%