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

    Neuronpedia

    INDEX
    Explanations

    words associated with movement or motion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.52
    1:0.02
    2:0.03
    3:0.03
    4:0.05
    5:0.03
    6:0.08
    7:0.06
    8:0.03
    9:0.02
    10:0.06
    11:0.03
    Negative Logits
    ケ
    -1.69
     SAY
    -1.65
     MPEG
    -1.51
     Defin
    -1.46
    ité
    -1.45
    ハ
    -1.41
     UD
    -1.39
    ADVERTISEMENT
    -1.39
    闘
    -1.38
     Dept
    -1.37
    POSITIVE LOGITS
    pload
    1.92
    pole
    1.82
    jer
    1.74
    ople
    1.65
    atz
    1.50
    ener
    1.46
    ups
    1.46
    ood
    1.46
    combe
    1.45
    wagon
    1.45
    Act Density 0.550%

    No Known Activations