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

    Neuronpedia

    INDEX
    Explanations

    instances of physical actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.04
    4:0.07
    5:0.02
    6:0.08
    7:0.48
    8:0.03
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    warning
    -1.72
    paren
    -1.61
    calling
    -1.55
    Office
    -1.55
    spection
    -1.48
    omnia
    -1.47
    pection
    -1.43
    lance
    -1.42
    fax
    -1.40
    nesday
    -1.39
    POSITIVE LOGITS
     heap
    1.73
     rabbits
    1.70
     rabbit
    1.63
     pile
    1.62
     ranks
    1.60
     bushes
    1.58
     basket
    1.56
     piles
    1.55
     spiral
    1.54
     cliffs
    1.52
    Act Density 0.021%

    No Known Activations