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

    Neuronpedia

    INDEX
    Explanations

    references to shadows and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atorship
    -0.49
     AttributeSet
    -0.47
     vốn
    -0.47
     Access
    -0.46
    يق
    -0.45
    ereço
    -0.45
    Access
    -0.44
    stino
    -0.44
    셉
    -0.43
    olera
    -0.43
    POSITIVE LOGITS
     shadow
    0.85
     shadows
    0.85
     effects
    0.75
     للاسماء
    0.74
     ripple
    0.73
    shadow
    0.72
     ripples
    0.72
     effect
    0.71
    caused
    0.71
     impact
    0.70
    Act Density 0.584%

    No Known Activations