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

    Neuronpedia

    INDEX
    Explanations

    occurrences and references to quotes and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪÑĤ
    -0.16
    erness
    -0.15
    slaught
    -0.14
     Doll
    -0.14
    ĭ
    -0.14
    WD
    -0.13
    885
    -0.13
    StateException
    -0.13
    ements
    -0.13
    ward
    -0.13
    POSITIVE LOGITS
    able
    0.17
    paque
    0.16
    enance
    0.16
    ãĥ¥
    0.15
    age
    0.15
    ting
    0.15
    book
    0.15
    bable
    0.15
    /tag
    0.15
    oped
    0.14
    Act Density 0.023%

    No Known Activations