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

    Neuronpedia

    INDEX
    Explanations

    numeric values and mathematical operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.90
     Majefty
    -0.83
    ArgsConstructor
    -0.82
    InputBorder
    -0.79
    RegressionTest
    -0.79
    ValueStyle
    -0.78
    adaptiveStyles
    -0.78
     myſelf
    -0.77
     InputDecoration
    -0.75
     houſe
    -0.73
    POSITIVE LOGITS
    Composable
    0.51
    MLLoader
    0.50
     net
    0.49
    dibly
    0.48
    multicolumn
    0.47
    cinta
    0.44
    રા
    0.44
    сь
    0.43
    dymyr
    0.43
     mar
    0.42
    Act Density 0.026%

    No Known Activations