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

    Neuronpedia

    INDEX
    Explanations

    phrases and references to visual elements and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asser
    -0.15
    rych
    -0.14
    ATO
    -0.14
     unb
    -0.14
    ASON
    -0.14
    ICA
    -0.14
    orts
    -0.13
    setQuery
    -0.13
    line
    -0.13
    atos
    -0.13
    POSITIVE LOGITS
    zeÅĦ
    0.18
    eyen
    0.17
    بÙĪÙĦ
    0.15
    егоÑĢ
    0.15
    ToLocal
    0.14
     Downs
    0.14
    verity
    0.14
    ë²Į
    0.14
    gnore
    0.14
    strap
    0.13
    Act Density 0.002%

    No Known Activations