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

    Neuronpedia

    INDEX
    Explanations

    references to scaling in different contexts

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

    Mentions scaling, scales, or scaled

    np_acts-logits-general · gemini-2.0-flash

    scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    **/
    -0.57
    RetentionPolicy
    -0.53
    dza
    -0.48
     bună
    -0.47
    슷
    -0.47
     [
    -0.46
     tight
    -0.46
    __*/
    -0.45
    -0.45
    )]);
    -0.45
    POSITIVE LOGITS
     SCALE
    1.31
     scales
    1.29
     Scales
    1.28
     Scale
    1.25
     Scal
    1.23
    Scales
    1.17
    scales
    1.13
    Scale
    1.13
     scale
    1.08
    SCALE
    1.06
    Act Density 0.073%
    No Known Activations