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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating causality or reason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     if
    -0.16
     whereas
    -0.16
    ;
    -0.16
    и
    -0.15
    ns
    -0.15
     which
    -0.15
     because
    -0.15
    окол
    -0.15
    :
    -0.14
     rz
    -0.13
    POSITIVE LOGITS
    alink
    0.16
     ìĤ¬ëŀĮìĿĢ
    0.16
    978
    0.15
    emer
    0.15
    azon
    0.15
    dess
    0.15
    nutÃŃ
    0.15
    جاج
    0.15
    .literal
    0.14
    TouchEvent
    0.14
    Act Density 0.057%

    No Known Activations