Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords related to programming or database structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Majefty
    -1.20
     myſelf
    -1.15
     itſelf
    -1.11
     himſelf
    -1.09
     Jefus
    -1.08
     ſever
    -1.06
     purpoſe
    -1.06
     pleaſure
    -1.06
     themſelves
    -1.05
     ſeveral
    -1.05
    POSITIVE LOGITS
     (
    0.51
    ...
    0.51
     x
    0.50
     
    0.49
    g
    0.49
     .
    0.45
     g
    0.45
     h
    0.42
     -
    0.42
     p
    0.41
    Act Density 0.238%

    No Known Activations