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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or situational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quette
    -0.17
    lessness
    -0.15
    se
    -0.15
    rych
    -0.15
    	throws
    -0.14
    isÃŃ
    -0.14
    aÅŁ
    -0.14
    archy
    -0.14
    piler
    -0.14
    owi
    -0.13
    POSITIVE LOGITS
    Ïİ
    0.16
    avour
    0.15
    ONTAL
    0.15
    ëĭ¥
    0.14
    IFA
    0.14
    ird
    0.14
     fault
    0.14
    ÏĦολ
    0.14
    ils
    0.14
    ãĥ³ãĥģ
    0.14
    Act Density 0.276%

    No Known Activations