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

    Neuronpedia

    INDEX
    Explanations

    capital letters or special characters in the middle of words

    oai_token-act-pair · gpt-3.5-turbo

    instances of placeholders or incomplete thoughts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -1.01
    ò
    -0.94
     pione
    -0.91
    aditional
    -0.90
    Þ
    -0.90
     exting
    -0.86
     practition
    -0.85
    ThumbnailImage
    -0.84
    Ý
    -0.83
    senal
    -0.82
    POSITIVE LOGITS
    Anyway
    0.71
    ³³³
    0.68
    ↵
    0.67
    NULL
    0.67
    BUT
    0.65
    Honestly
    0.63
    ³³³³³³³³³³³³³³³³
    0.62
    OH
    0.60
     Imran
    0.60
    ³³³³
    0.59
    Act Density 0.546%

    No Known Activations