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

    Neuronpedia

    INDEX
    Explanations

    instances of dashes or em dashes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ㆍ
    -0.37
    ِّ
    -0.32
     ``
    -0.31
    َّ
    -0.29
    -0.29
     CUR
    -0.28
     tambin
    -0.28
    ity
    -0.28
    -0.27
     fail
    -0.27
    POSITIVE LOGITS
     —
    1.47
    ———
    1.33
    ————————————————
    1.30
    —————
    1.24
    ————————
    1.23
    ————
    1.22
    ——————
    1.14
     —,
    1.09
    ——
    1.09
    ————————————
    1.08
    Act Density 0.399%

    No Known Activations