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

    Neuronpedia

    INDEX
    Explanations

    action words associated with cooking and vehicle control

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Lawson
    -0.85
     Malone
    -0.74
     Atlas
    -0.70
    Démographie
    -0.69
     Goldberg
    -0.69
    y
    -0.69
     Valdez
    -0.68
     Max
    -0.67
     Lawton
    -0.67
    pezi
    -0.67
    POSITIVE LOGITS
    Stir
    1.56
     Stir
    1.55
     stir
    1.33
    stir
    1.27
     Stirling
    1.23
     stirred
    1.08
     stirring
    0.99
     stirs
    0.96
    steering
    0.94
     steering
    0.92
    Act Density 0.004%

    No Known Activations