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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "shadow" and its various implications in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.44
     CreateTagHelper
    -0.43
    SourceChecksum
    -0.43
    windowFixed
    -0.42
    setupUi
    -0.39
    ReusableCell
    -0.38
    mobileqq
    -0.37
    osoba
    -0.37
     getan
    -0.36
     FMC
    -0.36
    POSITIVE LOGITS
     shadow
    2.89
    shadow
    2.64
     Shadow
    2.52
     SHADOW
    2.45
     shadows
    2.42
    Shadow
    2.39
    SHADOW
    2.17
     Shadows
    2.08
    shadows
    1.98
    hadow
    1.94
    Act Density 0.095%

    No Known Activations