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

    Neuronpedia

    INDEX
    Explanations

    symbols or punctuation marks representing a pause or shift in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.37
    ্দ
    -0.31
    utilisons
    -0.31
    ĭ
    -0.31
    ษา
    -0.28
     Sof
    -0.28
     CUR
    -0.27
    َّ
    -0.26
     course
    -0.25
     fail
    -0.25
    POSITIVE LOGITS
     —
    1.36
    ———
    1.23
    ————
    1.11
    ————————————————
    1.10
    —————
    1.09
    ————————
    1.08
    ——
    1.06
     —,
    1.04
    ——————
    1.02
    —-
    1.02
    Act Density 0.298%

    No Known Activations