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

    Neuronpedia

    INDEX
    Explanations

    expressions related to physical movement

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    starter
    -0.73
    erion
    -0.72
    vell
    -0.71
    inguished
    -0.65
    aste
    -0.63
    ray
    -0.63
    bor
    -0.62
     Server
    -0.62
    sted
    -0.62
    ftime
    -0.62
    POSITIVE LOGITS
     movements
    3.89
     movement
    2.47
     Movement
    1.93
     motions
    1.91
    move
    1.56
     revolutions
    1.46
    Move
    1.43
     gestures
    1.42
     Move
    1.38
     moves
    1.34
    Act Density 0.016%

    No Known Activations