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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scaling laws and their associated functions in various contexts

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

    scaling collapses, argument, exponent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >{@
    -0.57
    存于互联网档案馆
    -0.56
    __':
    -0.52
    enumii
    -0.48
    ♥♥
    -0.45
    ♥
    -0.45
     Referential
    -0.44
    Попис
    -0.44
    RadioGroup
    -0.43
    IUrlHelper
    -0.43
    POSITIVE LOGITS
     Scaling
    1.94
     scaling
    1.94
    scaling
    1.83
    Scaling
    1.81
     scaled
    1.70
    scaled
    1.55
    Scaled
    1.36
    caling
    1.36
    caled
    1.13
     Scal
    0.96
    Act Density 0.009%

    No Known Activations