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

    Neuronpedia

    INDEX
    Explanations

    keywords related to action or motion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.08
    3:0.09
    4:0.07
    5:0.07
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
    ascript
    -2.64
     unsupported
    -2.14
     mistaken
    -2.03
     inaccurate
    -2.03
    inventoryQuantity
    -1.97
     faked
    -1.96
    cknowled
    -1.96
    earch
    -1.94
     suicidal
    -1.94
    intent
    -1.93
    POSITIVE LOGITS
    Republic
    2.17
     Relic
    2.14
    riot
    2.08
     ripple
    2.07
    Liber
    2.05
    spring
    2.04
    arters
    1.94
     Cloak
    1.91
    aneously
    1.90
    roups
    1.86
    Act Density 0.000%

    No Known Activations