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

    Neuronpedia

    INDEX
    Explanations

    dates and events mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exclusively
    -0.63
     enrol
    -0.61
     cradle
    -0.61
     footing
    -0.59
    pecially
    -0.58
     reception
    -0.58
     withd
    -0.58
     induct
    -0.57
     unob
    -0.56
     face
    -0.56
    POSITIVE LOGITS
     Regardless
    0.98
    Downloadha
    0.97
     Also
    0.94
     Fortunately
    0.91
     Likewise
    0.91
     Anyway
    0.90
     Nevertheless
    0.90
     Ultimately
    0.89
     That
    0.89
     Eventually
    0.89
    Act Density 0.926%

    No Known Activations