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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people in images or text

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or figures, particularly in the context of images or photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.69
    cipled
    -0.64
    bin
    -0.63
    ente
    -0.63
    imester
    -0.62
    Attempts
    -0.58
    Marginal
    -0.58
     actionGroup
    -0.57
    psc
    -0.57
     pretext
    -0.57
    POSITIVE LOGITS
     smiling
    0.86
     kneeling
    0.83
     interacting
    0.77
     grinning
    0.77
     disappearing
    0.72
    hoe
    0.71
     behaving
    0.70
    Done
    0.70
     handwriting
    0.70
     lying
    0.69
    Act Density 0.699%

    No Known Activations