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

    Neuronpedia

    INDEX
    Explanations

    mention of a specific name ("Mark Townsend") alongside surrounding text

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.70
    ften
    -0.64
     whipping
    -0.58
    BALL
    -0.58
     whip
    -0.58
     miscarriage
    -0.58
     gag
    -0.57
     artificially
    -0.57
     brewer
    -0.57
     disproportion
    -0.56
    POSITIVE LOGITS
    auri
    0.73
     Chapters
    0.70
     denotes
    0.67
    --------------------
    0.65
     Credits
    0.63
    redits
    0.62
    -+-+
    0.61
    adoes
    0.60
    )=(
    0.60
    =~=~
    0.60
    Act Density 0.076%

    No Known Activations