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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values and specific identifiers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    第二次
    -0.32
     isempty
    -0.30
    TRIBUTES
    -0.30
    bamos
    -0.28
     tempor
    -0.28
    existing
    -0.28
    Kenn
    -0.28
     innov
    -0.28
    gic
    -0.28
    cso
    -0.27
    POSITIVE LOGITS
     two
    0.91
     seven
    0.80
     three
    0.80
     six
    0.79
     five
    0.79
     four
    0.78
     deux
    0.77
    IsMutable
    0.75
     eight
    0.75
     nine
    0.74
    Act Density 0.967%

    No Known Activations