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

    Neuronpedia

    INDEX
    Explanations

    elements related to physical actions and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caminha
    -0.43
    過ごし
    -0.39
    AccessorTable
    -0.39
     walks
    -0.38
     walking
    -0.36
     edilen
    -0.34
     hombros
    -0.34
     walk
    -0.34
    walking
    -0.34
     actual
    -0.33
    POSITIVE LOGITS
    :✨
    0.64
     gusto
    0.60
     throttle
    0.50
     hammer
    0.50
     aggressive
    0.49
     hammers
    0.49
     ferocious
    0.48
     unleashed
    0.48
    principalColumn
    0.47
    猛
    0.47
    Act Density 0.246%

    No Known Activations