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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or strong language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     any
    -0.55
     Carmichael
    -0.53
     Drop
    -0.53
     monotonic
    -0.51
     exactly
    -0.50
     perdere
    -0.50
    Drop
    -0.49
    ieee
    -0.49
     defStyle
    -0.48
     Varianten
    -0.48
    POSITIVE LOGITS
     שוליים
    0.74
    InSection
    0.73
     IndexPath
    0.70
    modelBuilder
    0.70
    RenderAtEndOf
    0.69
    TagMode
    0.68
    CppMethod
    0.68
    uxxxx
    0.67
    BoxShadow
    0.65
    LabelTagHelper
    0.65
    Act Density 0.622%

    No Known Activations