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

    Neuronpedia

    INDEX
    Explanations

    references to rates of speed and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InitVars
    -0.59
    parsedMessage
    -0.57
    rawDesc
    -0.57
    neiden
    -0.52
    Pai
    -0.49
    inafter
    -0.48
    InstanceState
    -0.48
     shivered
    -0.48
     Tight
    -0.47
    Tight
    -0.47
    POSITIVE LOGITS
     speed
    1.75
     speeds
    1.48
    speed
    1.42
     faster
    1.39
     Speed
    1.38
     fastest
    1.38
    Speed
    1.34
    faster
    1.28
    SPEED
    1.28
     velocity
    1.27
    Act Density 0.522%

    No Known Activations