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

    Neuronpedia

    INDEX
    Explanations

    timestamps in the format hour:minute

    oai_token-act-pair · gpt-3.5-turbo

    specific time indicators in a narrative, focusing heavily on time formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ($)
    -0.60
    alties
    -0.60
     Viz
    -0.59
     Zucker
    -0.56
     Abrams
    -0.56
     gamb
    -0.56
    swers
    -0.54
     Hitman
    -0.53
    uyomi
    -0.52
     Abyss
    -0.52
    POSITIVE LOGITS
    30
    1.52
    45
    1.36
    50
    1.24
    40
    1.23
    55
    1.21
    15
    1.21
    00
    1.21
    59
    1.20
    20
    1.19
    35
    1.14
    Act Density 0.025%

    No Known Activations