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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating motion or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.10
    3:0.08
    4:0.06
    5:0.07
    6:0.07
    7:0.08
    8:0.10
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
     VO
    -2.58
     vaping
    -2.39
     ageing
    -2.35
     ILCS
    -2.30
     Veterinary
    -2.29
     McGregor
    -2.20
     Wrestling
    -2.11
     Dynam
    -2.06
     Explosive
    -2.02
    xual
    -2.02
    POSITIVE LOGITS
    irements
    2.32
    izons
    2.24
    endas
    2.06
    plain
    1.98
    intend
    1.96
    cients
    1.93
     traced
    1.92
     prejudices
    1.91
    first
    1.91
    minist
    1.90
    Act Density 0.000%

    No Known Activations