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

    Neuronpedia

    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shock
    -0.78
     metic
    -0.77
     lure
    -0.76
     median
    -0.75
     variance
    -0.72
     maximum
    -0.72
     wonder
    -0.71
     pitch
    -0.71
     overlap
    -0.71
     variability
    -0.70
    POSITIVE LOGITS
    before
    1.89
    until
    1.87
    during
    1.87
    without
    1.86
    into
    1.86
    within
    1.84
    against
    1.84
    because
    1.82
    through
    1.80
    with
    1.79
    Act Density 0.175%

    No Known Activations