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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whim
    -0.15
     Tong
    -0.15
    Ä
    -0.14
    Tro
    -0.14
     Tro
    -0.14
    ruba
    -0.14
    806
    -0.14
    rosso
    -0.14
    AME
    -0.14
    dia
    -0.14
    POSITIVE LOGITS
    orne
    0.16
    utsch
    0.16
    antom
    0.15
     англ
    0.14
    è²
    0.14
    377
    0.14
    undi
    0.14
     ï¼ľ
    0.14
    erna
    0.13
    asm
    0.13
    Act Density 0.337%

    No Known Activations