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

    Neuronpedia

    INDEX
    Explanations

    specific verb phrases indicating actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingu
    -0.15
     eg
    -0.15
    Fuck
    -0.15
    ibur
    -0.14
     ï½ŀ
    -0.14
    æĸ°èģŀ
    -0.14
    idan
    -0.14
     fuck
    -0.14
    opr
    -0.14
    ibu
    -0.14
    POSITIVE LOGITS
    ï¸
    0.14
     Nich
    0.14
     å·Ŀ
    0.13
    .acc
    0.13
    rek
    0.13
     alphabetical
    0.13
     Dud
    0.13
    anders
    0.13
    .googleapis
    0.13
     Fits
    0.13
    Act Density 0.000%

    No Known Activations