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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating categorization or listing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.16
     Mutual
    -0.15
    CUS
    -0.14
    /AP
    -0.14
    dux
    -0.14
    긴
    -0.14
    हर
    -0.14
    hausen
    -0.13
    icum
    -0.13
    طر
    -0.13
    POSITIVE LOGITS
    rypto
    0.21
    unde
    0.17
     etc
    0.17
    endale
    0.15
    chwitz
    0.15
    ÏĮγ
    0.15
    rase
    0.14
    ensch
    0.14
    inel
    0.14
    ateur
    0.14
    Act Density 0.032%

    No Known Activations