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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Percival
    -0.68
     Fergus
    -0.68
     Furman
    -0.67
    likle
    -0.66
    prav
    -0.66
    bestand
    -0.65
    ajur
    -0.65
     Fot
    -0.65
    aData
    -0.64
    Viitteet
    -0.63
    POSITIVE LOGITS
    )",
    1.10
    )".
    1.05
    ",
    1.04
     Walpole
    1.00
    '",
    0.97
    ]",
    0.96
    ']").
    0.96
    __*/
    0.95
    ?",
    0.95
    ,",
    0.93
    Act Density 0.080%

    No Known Activations