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

    Neuronpedia

    INDEX
    Explanations

    dates specified in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     drift
    -0.76
     everyday
    -0.75
     mature
    -0.73
     intangible
    -0.73
     intelligent
    -0.72
     occupancy
    -0.69
     clin
    -0.69
     flock
    -0.69
     intensive
    -0.69
     extingu
    -0.68
    POSITIVE LOGITS
    pictured
    1.55
    PDF
    1.46
    pdf
    1.38
    see
    1.35
    emphasis
    1.30
    which
    1.29
    via
    1.28
    below
    1.26
    shown
    1.25
    albeit
    1.23
    Act Density 0.172%

    No Known Activations