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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate certainty, frequency, or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    865
    -0.14
     Overnight
    -0.14
    ä¾
    -0.14
    -env
    -0.13
    eldon
    -0.13
     Panic
    -0.13
     kuru
    -0.13
    thon
    -0.13
    ÅĻ
    -0.12
    539
    -0.12
    POSITIVE LOGITS
    rupt
    0.16
    gın
    0.14
    anou
    0.14
    Publication
    0.14
    Neutral
    0.14
     supposed
    0.13
     gonna
    0.13
    ÙĤب
    0.13
    vsp
    0.13
    amus
    0.13
    Act Density 0.576%

    No Known Activations