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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts or structures, specifically related to analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -1.04
    nya
    -0.92
    n
    -0.79
    د
    -0.77
    m
    -0.72
    ly
    -0.65
    p
    -0.65
    נות
    -0.65
    d
    -0.64
    c
    -0.64
    POSITIVE LOGITS
     SSI
    1.44
     MCI
    1.44
     CCI
    1.38
     GTI
    1.27
     PPI
    1.25
     CSI
    1.25
     TSI
    1.21
     DPI
    1.20
     STI
    1.18
    깐
    1.17
    Act Density 0.666%

    No Known Activations