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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and trends within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mix
    -0.14
     Progressive
    -0.13
    elp
    -0.13
     progressive
    -0.13
     Winds
    -0.13
    .dispatcher
    -0.13
     Progress
    -0.13
    vern
    -0.13
    Dispatcher
    -0.13
     Æ°á»Ľc
    -0.13
    POSITIVE LOGITS
     fluct
    0.40
     fluctuations
    0.35
     drop
    0.34
     drops
    0.33
     volatile
    0.33
     oscill
    0.32
     dropping
    0.32
     volatility
    0.31
     DROP
    0.30
    -drop
    0.29
    Act Density 0.265%

    No Known Activations