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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.70
     '\\;'
    -0.67
    HasForeignKey
    -0.66
    coltà
    -0.58
    khid
    -0.56
     newOwner
    -0.54
     VEND
    -0.54
    UnitTesting
    -0.53
    theless
    -0.53
     مشار
    -0.52
    POSITIVE LOGITS
    .$.
    1.20
    (_.
    1.15
     (_.
    1.11
    ()].
    1.09
    */].
    1.05
    (&:
    1.05
    >().
    1.05
     {.
    1.03
    "]').
    1.03
    \.
    1.00
    Act Density 0.588%

    No Known Activations