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

    Neuronpedia

    INDEX
    Explanations

    words related to quarrels or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esty
    -0.18
    ÑĪки
    -0.16
    دار
    -0.14
    amide
    -0.14
    벨
    -0.14
    ój
    -0.14
     Hairst
    -0.14
     cl
    -0.14
    ãĥ¬ãĥ³
    -0.14
    strup
    -0.13
    POSITIVE LOGITS
     Operators
    0.17
    uple
    0.15
    idlo
    0.15
     Operator
    0.14
    teenth
    0.14
     tela
    0.14
    اظ
    0.14
    ishi
    0.14
     Wilson
    0.14
    uchos
    0.13
    Act Density 0.039%

    No Known Activations