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

    Neuronpedia

    INDEX
    Explanations

    mentions of cats or similar words related to cats

    oai_token-act-pair · gpt-3.5-turbo

    references to cats or cat-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OND
    -0.71
    FontSize
    -0.70
    hower
    -0.66
    mble
    -0.66
     Seym
    -0.65
     Fellowship
    -0.63
    ij士
    -0.63
     Impossible
    -0.61
    assetsadobe
    -0.61
    èĢħ
    -0.61
    POSITIVE LOGITS
    aclysm
    1.62
    heter
    1.38
    apult
    1.33
    chers
    1.30
    cher
    1.24
    alogue
    1.19
    alyst
    1.19
    hedral
    1.14
    alog
    1.14
    fish
    1.08
    Act Density 0.025%

    No Known Activations