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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gpt-3.5-turbo

    structural or formatting elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.89
    ournal
    -0.85
    swick
    -0.85
    irtual
    -0.81
    hester
    -0.78
    inelli
    -0.77
    rador
    -0.76
     clipboard
    -0.74
    manship
    -0.74
    ovie
    -0.73
    POSITIVE LOGITS
    ÙĦ
    1.04
    Í
    0.91
    ا
    0.90
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.89
    Ùĩ
    0.86
    ļ
    0.85
    ¬¼
    0.84
    Ùİ
    0.83
    Ù
    0.83
    ĪĴ
    0.82
    Act Density 0.005%

    No Known Activations