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

    Neuronpedia

    INDEX
    Explanations

    mentions of humans

    oai_token-act-pair · gpt-3.5-turbo

    references to humans and their characteristics or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Comprehensive
    -0.69
    paragraph
    -0.66
    Neigh
    -0.65
     Statements
    -0.64
    onite
    -0.63
     Sop
    -0.62
    olla
    -0.61
    FU
    -0.61
    Coun
    -0.61
    ANC
    -0.60
    POSITIVE LOGITS
    folk
    1.16
     beings
    0.96
    oids
    0.85
    zee
    0.80
     Humans
    0.76
    omorphic
    0.76
    anguages
    0.76
     readable
    0.75
     inhab
    0.74
    mite
    0.74
    Act Density 0.021%

    No Known Activations