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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical scars

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "scar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ostics
    -0.79
    ĨĴ
    -0.75
    ullivan
    -0.69
    hower
    -0.65
     expectancy
    -0.65
    ablishment
    -0.64
    sterdam
    -0.64
    ablish
    -0.62
    £ı
    -0.61
    ADRA
    -0.61
    POSITIVE LOGITS
    red
    1.13
    ring
    1.09
    lets
    1.02
    crow
    0.96
    fing
    0.96
    pered
    0.91
    abs
    0.91
    fed
    0.91
    nton
    0.89
    ves
    0.88
    Act Density 0.043%

    No Known Activations