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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    time-related information, specifically timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     curves
    -0.61
     corrections
    -0.60
     Abrams
    -0.59
     disclaim
    -0.58
     evolution
    -0.57
     overall
    -0.57
     collections
    -0.57
     authority
    -0.56
     shrink
    -0.56
     comparisons
    -0.55
    POSITIVE LOGITS
    30
    1.21
    45
    1.12
    00
    1.10
    59
    1.08
    15
    0.99
    50
    0.98
    55
    0.96
    05
    0.94
    20
    0.94
    40
    0.94
    Act Density 0.026%

    No Known Activations