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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to automotive performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulkan
    -0.16
    λÏī
    -0.16
    alar
    -0.16
    alous
    -0.15
    iras
    -0.15
    hek
    -0.15
    essa
    -0.15
    imon
    -0.15
     weather
    -0.15
    xbb
    -0.15
    POSITIVE LOGITS
     output
    0.22
     outputs
    0.22
     Output
    0.20
     power
    0.19
     torque
    0.17
    output
    0.17
     performance
    0.17
     Outputs
    0.17
    lek
    0.17
     punch
    0.16
    Act Density 0.026%

    No Known Activations