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

    Neuronpedia

    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.67
     induct
    -0.67
     enclosure
    -0.67
     gaze
    -0.65
     pit
    -0.64
     shedding
    -0.64
     honoured
    -0.62
     tack
    -0.61
     waved
    -0.60
     spoiled
    -0.60
    POSITIVE LOGITS
    Downloadha
    1.14
    tumblr
    1.05
     However
    1.00
     Additionally
    0.97
     Specifically
    0.94
     Conversely
    0.94
     Needless
    0.93
     Similarly
    0.92
     Likewise
    0.92
    exe
    0.92
    Act Density 1.119%

    No Known Activations