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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance of specific subjects or factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Biôgrafia
    -0.81
     AssemblyCulture
    -0.79
    CloseOperation
    -0.75
    MigrationBuilder
    -0.74
     Roskov
    -0.71
    :✨
    -0.71
    AutoresizingMask
    -0.69
    MLLoader
    -0.67
     fufficient
    -0.67
     greateſt
    -0.66
    POSITIVE LOGITS
     inilah
    0.70
     именно
    0.67
     саме
    0.60
     Именно
    0.57
     właśnie
    0.54
    podar
    0.53
    Genau
    0.51
     itulah
    0.50
     comportement
    0.49
     dopiero
    0.49
    Act Density 0.157%

    No Known Activations