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

    Neuronpedia

    INDEX
    Explanations

    the word "stranger" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rity
    -0.86
    iox
    -0.83
    vez
    -0.78
    rates
    -0.73
    prus
    -0.73
    reon
    -0.72
    odium
    -0.72
    urer
    -0.70
    pleting
    -0.70
    orie
    -0.69
    POSITIVE LOGITS
    liness
    0.95
     flung
    0.80
    ishly
    0.79
    worldly
    0.78
    hood
    0.75
     whom
    0.73
     grop
    0.71
    lihood
    0.69
     bitten
    0.69
     stranger
    0.69
    Act Density 0.041%

    No Known Activations