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

    Neuronpedia

    INDEX
    Explanations

    references to statistical measures and their calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BufferException
    -0.58
    perma
    -0.46
    spir
    -0.45
     vasto
    -0.45
     plen
    -0.45
     kín
    -0.44
     Unger
    -0.44
     Ter
    -0.44
    setOpaque
    -0.43
     zum
    -0.43
    POSITIVE LOGITS
    BeginContext
    0.89
     median
    0.88
    median
    0.86
    ValueStyle
    0.85
     Median
    0.84
    Median
    0.81
    mean
    0.80
    SharedCtor
    0.78
    MEAN
    0.75
     Monfieur
    0.75
    Act Density 0.658%

    No Known Activations