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

    Neuronpedia

    INDEX
    Explanations

    words related to physical movements

    oai_token-act-pair · gpt-3.5-turbo

    references to physical movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unts
    -0.73
    ryn
    -0.68
    nect
    -0.67
    zona
    -0.67
    é¾įå
    -0.65
    neath
    -0.64
    çļ
    -0.63
    ãĥ¯ãĥ³
    -0.63
    ric
    -0.62
    ãĤ¨ãĥ«
    -0.62
    POSITIVE LOGITS
     movements
    1.30
     movement
    1.18
     motions
    1.03
    move
    0.90
     Movement
    0.89
     agitation
    0.87
     motion
    0.83
    ĸļ
    0.82
    ngth
    0.77
     Motion
    0.76
    Act Density 0.017%

    No Known Activations