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

    Neuronpedia

    INDEX
    Explanations

    mentions of close friends or companions

    oai_token-act-pair · gpt-3.5-turbo

    references to friends or social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mandatory
    -0.77
    MED
    -0.75
     Rational
    -0.73
    externalActionCode
    -0.68
    Mist
    -0.64
     Refuge
    -0.63
     Quran
    -0.63
     Situation
    -0.63
     Psychology
    -0.62
     Bir
    -0.62
    POSITIVE LOGITS
     pals
    1.35
    ies
    0.91
    opher
    0.78
    ervatives
    0.78
    hip
    0.78
    arious
    0.76
    eties
    0.76
    ersen
    0.75
    hips
    0.75
    ignt
    0.75
    Act Density 0.013%

    No Known Activations