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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons and evaluations of quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Johnny
    -0.16
     literally
    -0.16
     Stock
    -0.16
     stock
    -0.16
     Broadcasting
    -0.15
     CH
    -0.15
    anny
    -0.15
     pure
    -0.15
     Esp
    -0.15
    elin
    -0.15
    POSITIVE LOGITS
     moderately
    0.16
     respectable
    0.16
     decent
    0.16
    ymes
    0.16
    erras
    0.16
     ÑĥмеÑĢ
    0.16
    azor
    0.15
    æĻ®éĢļ
    0.15
    dit
    0.15
     modest
    0.15
    Act Density 0.242%

    No Known Activations