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

    Neuronpedia

    INDEX
    Explanations

    instances of programming-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.54
     fazia
    -0.54
     sape
    -0.50
    WireFormatLite
    -0.50
     would
    -0.49
     میخ
    -0.49
     faceva
    -0.49
    ivano
    -0.48
    ican
    -0.47
     говорил
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.87
    Hentet
    0.73
    رشف
    0.69
     дописавши
    0.69
     EconPapers
    0.65
     AGAIN
    0.61
    windowFixed
    0.60
    WriteAttribute
    0.60
     again
    0.59
     autorytatywna
    0.58
    Act Density 0.009%

    No Known Activations