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

    Neuronpedia

    INDEX
    Explanations

    phrases with repeated characters

    oai_token-act-pair · gpt-3.5-turbo

    specific patterns or sequences of characters related to dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.86
     Scarlet
    -0.75
     gad
    -0.69
     whistle
    -0.69
    é¾įå¥ij士
    -0.68
     friendly
    -0.67
     Samar
    -0.66
     decomp
    -0.66
     prevailing
    -0.65
     charm
    -0.63
    POSITIVE LOGITS
    ł
    0.86
    elong
    0.82
    ı
    0.81
    0.81
    º
    0.79
    Ī
    0.78
    ±
    0.78
    į
    0.78
    ĸļ
    0.77
    ttle
    0.77
    Act Density 0.096%

    No Known Activations