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

    Neuronpedia

    INDEX
    Explanations

    opening curly braces in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ija
    -0.18
    ongan
    -0.15
    cott
    -0.15
     __("
    -0.14
    éľ
    -0.14
    mons
    -0.14
    ç¨ĭ度
    -0.14
     Ultra
    -0.13
    437
    -0.13
    owie
    -0.13
    POSITIVE LOGITS
     gu
    0.15
    asic
    0.14
     empt
    0.14
    충
    0.14
     Berry
    0.13
     IND
    0.13
     Sok
    0.13
     meaning
    0.13
     rept
    0.13
    Lens
    0.13
    Act Density 0.001%

    No Known Activations