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

    Neuronpedia

    INDEX
    Explanations

    instances of the letters "Di" at the beginning of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.92
     Crud
    -0.82
     nakalista
    -0.79
    UnitTesting
    -0.78
    ReusableCell
    -0.77
    ImageContext
    -0.76
     препратки
    -0.76
    eah
    -0.75
    CreateModel
    -0.75
     perpétu
    -0.75
    POSITIVE LOGITS
     Di
    1.17
     Dietz
    1.15
    Di
    1.08
     di
    1.06
     DiCaprio
    1.02
     DI
    1.01
    di
    0.98
    DI
    0.94
     Dix
    0.90
     DIB
    0.89
    Act Density 0.223%

    No Known Activations