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

    Neuronpedia

    INDEX
    Explanations

    email addresses or other alphanumeric patterns

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical data or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waiter
    -0.67
     Immunity
    -0.65
     exha
    -0.63
     guid
    -0.62
     immunity
    -0.62
     comprom
    -0.62
     direction
    -0.61
     natives
    -0.61
     palate
    -0.60
    é¾įå
    -0.59
    POSITIVE LOGITS
    soever
    0.94
    wm
    0.87
    e
    0.79
    606
    0.78
    Ever
    0.77
    285
    0.77
    211
    0.76
    708
    0.76
    704
    0.75
    rez
    0.75
    Act Density 0.088%

    No Known Activations