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

    Neuronpedia

    INDEX
    Explanations

    times and durations

    oai_token-act-pair · gpt-3.5-turbo

    time-related information and scheduling details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chain
    -0.68
    olis
    -0.64
     dogged
    -0.61
     lineback
    -0.61
     womb
    -0.61
     cris
    -0.60
     gobl
    -0.59
     bedrock
    -0.59
     chains
    -0.59
     bloom
    -0.59
    POSITIVE LOGITS
    00
    1.54
    30
    1.40
    59
    1.28
    45
    1.19
    50
    1.07
    55
    1.05
    15
    1.05
    05
    1.04
    58
    0.97
    40
    0.96
    Act Density 0.029%

    No Known Activations