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

    Neuronpedia

    INDEX
    Explanations

    dates and locations mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     artisan
    -0.82
     intensive
    -0.78
     intelligent
    -0.70
     lull
    -0.69
     wre
    -0.69
     incons
    -0.68
     Gutenberg
    -0.68
     glare
    -0.67
     flock
    -0.66
     piping
    -0.66
    POSITIVE LOGITS
    pictured
    1.37
    sic
    1.34
    see
    1.32
    albeit
    1.27
    including
    1.25
    emphasis
    1.25
    although
    1.23
    which
    1.21
    via
    1.19
    though
    1.19
    Act Density 0.181%

    No Known Activations