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

    Neuronpedia

    INDEX
    Explanations

    references to speed and related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    speed control command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     four
    -0.48
     one
    -0.47
     the
    -0.44
     [*]
    -0.43
     Laub
    -0.43
     a
    -0.42
     quaisquer
    -0.41
     Cot
    -0.41
     three
    -0.41
    argout
    -0.41
    POSITIVE LOGITS
    Speed
    1.17
     Speed
    1.16
     SPEED
    1.14
    speed
    1.13
     speed
    1.13
    SPEED
    1.06
     pleaſure
    1.03
    peed
    1.01
     Speeds
    0.97
     speeds
    0.96
    Act Density 0.013%

    No Known Activations