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

    Neuronpedia

    INDEX
    Explanations

    habits or repetitive actions

    oai_token-act-pair · gpt-3.5-turbo

    references to habits and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SAR
    -0.76
    ndum
    -0.73
    cross
    -0.67
     RIS
    -0.66
    yz
    -0.65
     GOODMAN
    -0.63
    ramid
    -0.63
    zac
    -0.62
    headers
    -0.61
    mberg
    -0.61
    POSITIVE LOGITS
    ually
    1.13
    uated
    1.10
     habit
    1.04
     habits
    1.03
    uation
    0.99
    uate
    0.97
    uates
    0.80
    uating
    0.78
    itual
    0.73
    dayName
    0.70
    Act Density 0.013%

    No Known Activations