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

    Neuronpedia

    INDEX
    Explanations

    the word stem "intrud" or "extrud"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intrusion and protrusion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -1.04
    hare
    -0.82
    fully
    -0.81
    wagen
    -0.80
    SHIP
    -0.76
    LESS
    -0.75
    hift
    -0.71
    heet
    -0.70
    baum
    -0.70
    bucks
    -0.69
    POSITIVE LOGITS
    uders
    1.47
    uding
    1.39
    usions
    1.27
    uded
    1.25
    udes
    1.16
    aband
    1.12
    aneous
    1.06
    usive
    1.04
    usted
    1.04
    asonic
    1.02
    Act Density 0.039%

    No Known Activations