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

    Neuronpedia

    INDEX
    Explanations

    dates and times in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates and times in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozo
    -0.83
    orc
    -0.76
    eele
    -0.75
    atem
    -0.73
    olester
    -0.72
    agos
    -0.69
    othing
    -0.69
    oat
    -0.69
     skelet
    -0.67
    operated
    -0.65
    POSITIVE LOGITS
     04
    1.17
     06
    1.16
     03
    1.16
     02
    1.15
     05
    1.14
     07
    1.11
     09
    1.10
     08
    1.03
     01
    1.01
     00
    0.92
    Act Density 0.010%

    No Known Activations