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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning or intending to do something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to intention or scheming actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cause
    -0.69
    govtrack
    -0.69
    Gam
    -0.65
    inas
    -0.64
    bour
    -0.62
    ths
    -0.62
    partisan
    -0.61
    int
    -0.61
    shire
    -0.60
    holes
    -0.59
    POSITIVE LOGITS
     Parenthood
    1.15
    paren
    1.04
    escape
    0.88
     obs
    0.80
     meals
    0.76
     vacations
    0.75
     trips
    0.75
     accordingly
    0.73
     beforehand
    0.72
     pregnancies
    0.72
    Act Density 0.045%

    No Known Activations