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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or logical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -1.12
    nya
    -1.02
    n
    -0.82
    د
    -0.79
    m
    -0.71
    נות
    -0.68
    ly
    -0.68
    p
    -0.67
    d
    -0.67
    lar
    -0.64
    POSITIVE LOGITS
     SSI
    1.39
     CCI
    1.38
     MCI
    1.37
     CSI
    1.23
     GTI
    1.23
     STI
    1.21
     TSI
    1.21
     PPI
    1.18
     DPI
    1.17
    깐
    1.16
    Act Density 0.703%

    No Known Activations