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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly commas and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Strom
    -0.16
    yes
    -0.15
    aster
    -0.14
    ual
    -0.14
    ester
    -0.14
    ยม
    -0.14
    iei
    -0.14
    ils
    -0.14
    /document
    -0.14
    filer
    -0.13
    POSITIVE LOGITS
     Bowman
    0.17
     waive
    0.14
     RuntimeObject
    0.14
    867
    0.14
    ÂĿ
    0.14
    abbr
    0.13
     ActionTypes
    0.13
    ÑĶм
    0.13
    rna
    0.13
    ozy
    0.13
    Act Density 0.109%

    No Known Activations