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

    Neuronpedia

    INDEX
    Explanations

    instances where routines or standard procedures occur

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "routine."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugs
    -0.70
    arag
    -0.70
    ippi
    -0.69
    onz
    -0.69
    iva
    -0.68
     Straw
    -0.68
    avin
    -0.68
    wit
    -0.67
    atorial
    -0.67
    oras
    -0.67
    POSITIVE LOGITS
     routine
    1.15
     routines
    1.03
     maintenance
    0.93
     regimen
    0.75
    outine
    0.75
    dayName
    0.75
    motion
    0.74
    zed
    0.74
    ised
    0.72
    cy
    0.71
    Act Density 0.010%

    No Known Activations