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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a punctuation mark '.'

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of completion or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.94
     challeng
    -0.76
    itaire
    -0.76
    ikuman
    -0.73
     assassin
    -0.70
     fermented
    -0.68
    onga
    -0.66
     cradle
    -0.65
     earthqu
    -0.65
     hunted
    -0.65
    POSITIVE LOGITS
     However
    1.09
     Therefore
    1.06
     Additionally
    1.04
     Examples
    1.03
     Alternatively
    1.00
     Whether
    1.00
     Usually
    0.99
     Hence
    0.99
     Flavoring
    0.99
     Besides
    0.98
    Act Density 0.770%

    No Known Activations