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

    Neuronpedia

    INDEX
    Explanations

    references to casual interactions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollen
    -0.17
    elts
    -0.17
     vice
    -0.15
    ÑĸнÑĮ
    -0.14
     rep
    -0.14
    istrovstvÃŃ
    -0.14
    atre
    -0.14
    asser
    -0.14
    esel
    -0.13
    letal
    -0.13
    POSITIVE LOGITS
    OOD
    0.16
    beit
    0.16
    eyin
    0.16
    nes
    0.15
    tics
    0.15
    urus
    0.15
    uctor
    0.14
    à¤ķरण
    0.14
    çŃĴ
    0.14
    ugo
    0.14
    Act Density 0.006%

    No Known Activations