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

    Neuronpedia

    INDEX
    Explanations

    mentions of interactions with strangers

    oai_token-act-pair · gpt-3.5-turbo

    references to strangers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rity
    -0.86
    iox
    -0.84
    rates
    -0.79
    prus
    -0.75
    vez
    -0.73
    orie
    -0.70
    iano
    -0.70
    inion
    -0.70
    ramid
    -0.69
    ris
    -0.68
    POSITIVE LOGITS
     strangers
    0.80
     grop
    0.79
     stranger
    0.78
     bitten
    0.77
     flung
    0.77
    liness
    0.75
     whom
    0.75
    worldly
    0.73
    ishly
    0.72
     acquainted
    0.70
    Act Density 0.023%

    No Known Activations