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

    Neuronpedia

    INDEX
    Explanations

    words related to physical movement, specifically walking

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "walk."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.82
    cffff
    -0.81
    encies
    -0.79
    illian
    -0.72
    uliffe
    -0.71
    ional
    -0.70
    anyahu
    -0.70
    afort
    -0.68
    uchin
    -0.68
    ultz
    -0.68
    POSITIVE LOGITS
    own
    1.00
    Walk
    0.96
    walk
    0.93
     Walk
    0.92
    lihood
    0.85
     walk
    0.82
    walking
    0.81
    walker
    0.81
    athon
    0.78
    ways
    0.78
    Act Density 0.024%

    No Known Activations