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

    Neuronpedia

    INDEX
    Explanations

    repeated symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters used for emphasis or formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.90
    iple
    -0.82
    unal
    -0.79
    est
    -0.78
    tek
    -0.75
    oola
    -0.74
    sters
    -0.73
    zzle
    -0.72
    ackle
    -0.71
    ster
    -0.71
    POSITIVE LOGITS
    _>
    1.42
     Contents
    0.89
     Preferences
    0.82
    =~=~
    0.82
    ĸļ
    0.77
    =>
    0.77
     ********************************
    0.70
     Taken
    0.70
    >>>>
    0.70
    Present
    0.67
    Act Density 0.035%

    No Known Activations