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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and their associated contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orest
    -0.15
    atories
    -0.14
     Gins
    -0.14
    mens
    -0.14
    /Layout
    -0.14
    omens
    -0.14
    illions
    -0.13
    ãĥ¼ãĥĭ
    -0.13
     Granite
    -0.13
    æ¤į
    -0.13
    POSITIVE LOGITS
    orges
    0.15
    ANJI
    0.15
    quel
    0.14
    UTO
    0.14
    yal
    0.14
    ruk
    0.14
    quia
    0.14
    zas
    0.13
    _unicode
    0.13
     stamped
    0.13
    Act Density 0.007%

    No Known Activations