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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly periods and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighbor
    -0.17
    assage
    -0.16
    uters
    -0.16
    _firestore
    -0.15
    hoe
    -0.14
    uele
    -0.14
    //{{
    -0.14
     muschi
    -0.14
    ediator
    -0.14
    ç¿°
    -0.14
    POSITIVE LOGITS
     indeed
    0.17
     Indeed
    0.15
     Weak
    0.14
     fund
    0.14
     LO
    0.14
    æİĽ
    0.14
    883
    0.14
    Adds
    0.14
     Disposable
    0.14
     he
    0.14
    Act Density 0.042%

    No Known Activations