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

    Neuronpedia

    INDEX
    Explanations

    quotation exchanges between characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.73
    malink
    -0.71
    ranean
    -0.71
    ateral
    -0.69
    cv
    -0.68
     Calories
    -0.67
    inas
    -0.64
    uded
    -0.64
     ensemble
    -0.61
    WT
    -0.61
    POSITIVE LOGITS
     hello
    0.71
    asia
    0.70
     '[
    0.69
     politely
    0.64
    hett
    0.64
     bye
    0.63
     '(
    0.63
    bryce
    0.63
     TAMADRA
    0.62
     hes
    0.60
    Act Density 0.231%

    No Known Activations