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

    Neuronpedia

    INDEX
    Explanations

    mathematical relationships and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ound
    -0.06
    WK
    -0.06
     Tá»īnh
    -0.06
    ÅĻik
    -0.06
    bak
    -0.06
    /********
    -0.06
    Æ°á»Ŀn
    -0.06
    .sponge
    -0.06
    ÃĹ↵↵
    -0.06
    ÙĪÙģÙĬ
    -0.06
    POSITIVE LOGITS
     B
    0.14
     b
    0.10
    _B
    0.09
    B
    0.09
    _b
    0.09
    Âłb
    0.08
     ÎĴ
    0.08
     ب
    0.08
     ब
    0.08
    (B
    0.08
    Act Density 0.241%

    No Known Activations