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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending with "self"

    np_acts-logits-general · gemini-2.0-flash

    s Encyclopedia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.55
     b
    -0.53
     ne
    -0.53
     k
    -0.52
     Hall
    -0.51
     g
    -0.51
     never
    -0.51
     tri
    -0.51
     for
    -0.50
     ro
    -0.50
    POSITIVE LOGITS
     myſelf
    1.09
    AndEndTag
    0.99
    ViewImports
    0.96
     itſelf
    0.95
     pleaſure
    0.92
     crdi
    0.90
     ſeveral
    0.85
     purpoſe
    0.85
     themſelves
    0.85
     himſelf
    0.84
    Act Density 0.032%

    No Known Activations