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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons of quality and popularity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    exitRule
    -0.92
    (!__
    -0.92
    MigrationBuilder
    -0.89
    principalTable
    -0.85
    HideFlags
    -0.85
    Rüyada
    -0.84
    SharedCtor
    -0.84
    MessageTagHelper
    -0.82
    IsMutable
    -0.82
     kaarangay
    -0.81
    POSITIVE LOGITS
     consider
    0.51
     this
    0.48
    قام
    0.47
     that
    0.44
     has
    0.43
    畢竟
    0.43
     the
    0.42
     maje
    0.42
    ชาติ
    0.42
    ziej
    0.41
    Act Density 0.050%

    No Known Activations