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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks, particularly colons and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ref
    -0.16
    avis
    -0.16
    Äĩ
    -0.16
    cano
    -0.15
     Styles
    -0.14
    arias
    -0.13
     Herbert
    -0.13
    etailed
    -0.13
     Signature
    -0.13
     Pulse
    -0.13
    POSITIVE LOGITS
    linkplain
    0.16
    itime
    0.16
    ''"
    0.15
    omite
    0.14
    ripe
    0.14
    arget
    0.14
     Cres
    0.14
    ipar
    0.14
    ORY
    0.13
    entic
    0.13
    Act Density 0.015%

    No Known Activations