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

    Neuronpedia

    INDEX
    Explanations

    time references

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate approximate time or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NEY
    -0.76
    oland
    -0.67
    ographed
    -0.65
    Reviewer
    -0.64
    neys
    -0.64
    oric
    -0.63
     Puzzle
    -0.61
     Peaks
    -0.61
    ses
    -0.60
    hesis
    -0.60
    POSITIVE LOGITS
    PsyNetMessage
    0.74
    aleb
    0.72
    300
    0.71
    200
    0.70
     midway
    0.67
    fff
    0.67
    600
    0.65
    abama
    0.64
     dozen
    0.64
    120
    0.61
    Act Density 0.051%

    No Known Activations