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

    Neuronpedia

    INDEX
    Explanations

    numeric values and related patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hwar
    -0.86
     Puff
    -0.78
     jButton
    -0.77
    DotNetBar
    -0.76
    EClass
    -0.73
    +#+
    -0.71
    OTHY
    -0.69
    хь
    -0.68
    ohy
    -0.67
    Ctx
    -0.66
    POSITIVE LOGITS
     Vega
    0.71
    NOPQRST
    0.69
     Laine
    0.67
     NLR
    0.67
    صار
    0.66
     pngtree
    0.66
     ResNet
    0.65
     Zane
    0.63
    antlr
    0.62
     Martine
    0.61
    Act Density 0.481%

    No Known Activations