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

    Neuronpedia

    INDEX
    Explanations

    numeric values, specifically related to ISBN numbers and negative numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıб
    -0.16
    ember
    -0.15
    rego
    -0.15
    uze
    -0.15
    æľĽ
    -0.14
     representation
    -0.14
    buz
    -0.14
    ing
    -0.14
    ervas
    -0.13
     stabil
    -0.13
    POSITIVE LOGITS
     ëıĮ
    0.18
    IRO
    0.16
    ساÙĨ
    0.15
    kaar
    0.15
    issance
    0.15
    [section
    0.14
    Å¡ti
    0.14
    ÐĴÑĸд
    0.13
     Rica
    0.13
    á»ijc
    0.13
    Act Density 0.007%

    No Known Activations