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

    Neuronpedia

    INDEX
    Explanations

    instances of interactions with strangers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stranger."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rity
    -0.83
    aeda
    -0.82
    prus
    -0.81
    rix
    -0.78
    erb
    -0.76
    erenn
    -0.75
    chwitz
    -0.72
    amina
    -0.72
    REE
    -0.71
    inion
    -0.71
    POSITIVE LOGITS
     stranger
    0.90
    liness
    0.84
     strangers
    0.83
    ishly
    0.79
    worldly
    0.74
     Colossus
    0.71
     Reincarn
    0.68
     whom
    0.67
     Stranger
    0.66
     Tuls
    0.65
    Act Density 0.007%

    No Known Activations