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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expulsion or removal

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.72
    cious
    -0.70
    antry
    -0.67
    avorite
    -0.65
    MH
    -0.63
    Export
    -0.61
    inski
    -0.61
    ionic
    -0.61
    rontal
    -0.60
    ppy
    -0.60
    POSITIVE LOGITS
    stretched
    0.90
    fitted
    0.84
    ta
    0.81
    lier
    0.79
    wards
    0.75
    dated
    0.73
    posts
    0.73
    doors
    0.72
    gradation
    0.71
    door
    0.70
    Act Density 0.054%

    No Known Activations