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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence-ending marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bonded
    -0.69
     involuntary
    -0.68
     magistrate
    -0.63
    anyahu
    -0.62
    ropy
    -0.62
    ynamic
    -0.61
    ',"
    -0.61
     rodent
    -0.61
    idine
    -0.61
     millenn
    -0.61
    POSITIVE LOGITS
    âĢ
    1.64
     Especially
    1.32
     âĢ
    1.25
     Which
    1.21
     Including
    1.16
     Honestly
    1.16
     ðŁij
    1.16
     ðŁĺ
    1.15
     Granted
    1.15
     Literally
    1.12
    Act Density 0.512%

    No Known Activations