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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who are members of specified groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to group affiliation or membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     daylight
    -0.67
    rums
    -0.66
     symmetry
    -0.60
     torches
    -0.56
     tomatoes
    -0.56
    ourses
    -0.55
     plumbing
    -0.54
     unbeliev
    -0.54
     carnage
    -0.54
     rout
    -0.54
    POSITIVE LOGITS
     of
    1.15
    hips
    0.96
     thereof
    0.93
    OF
    0.82
    Of
    0.81
     Of
    0.77
     OF
    0.75
    atical
    0.75
    less
    0.73
    idable
    0.70
    Act Density 0.033%

    No Known Activations