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

    Neuronpedia

    INDEX
    Explanations

    text separated by special characters such as dots and commas

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or governmental entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unaff
    -0.74
     acting
    -0.67
     endeav
    -0.67
     dissu
    -0.64
     estranged
    -0.63
     victorious
    -0.63
    .</
    -0.63
     entirely
    -0.61
     agon
    -0.61
     endeavor
    -0.61
    POSITIVE LOGITS
    ³³³
    1.06
    posted
    1.02
    Anyway
    1.02
    anon
    1.00
    Posted
    0.99
    ³³³³
    0.99
    Advertisements
    0.98
    ³³³³³³³³³³³³³³³³
    0.97
    Secondly
    0.94
    Regarding
    0.91
    Act Density 0.699%

    No Known Activations