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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional statements and uncertainty in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.92
     Paglinawan
    -0.77
    PerformLayout
    -0.76
    twimg
    -0.76
     незавершена
    -0.73
    WriteTagHelper
    -0.73
    исленность
    -0.71
     esternos
    -0.70
    liosis
    -0.70
    ndata
    -0.69
    POSITIVE LOGITS
    /*
    0.45
     düş
    0.43
    rike
    0.43
    摩
    0.42
     doch
    0.41
     halv
    0.40
    ToBe
    0.40
     derece
    0.39
    exitRule
    0.39
    gonic
    0.39
    Act Density 0.473%

    No Known Activations