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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cats

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.71
     Seym
    -0.71
    indal
    -0.68
     htt
    -0.68
    gur
    -0.68
     enriched
    -0.63
     Vander
    -0.62
     Protestant
    -0.62
     Sacrament
    -0.62
    ij士
    -0.62
    POSITIVE LOGITS
    aclysm
    1.38
    cat
    1.03
    heter
    1.02
    fish
    1.01
    cats
    1.00
    alogue
    0.95
    apult
    0.93
    Cat
    0.88
     cats
    0.85
     kitten
    0.84
    Act Density 0.011%

    No Known Activations