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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical distributions and homogeneity in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Functional
    -0.59
    InputTagHelper
    -0.58
    Functional
    -0.54
    ntable
    -0.52
    ➟
    -0.51
    PYX
    -0.50
    __":
    -0.49
    measurable
    -0.47
     functional
    -0.47
    harvard
    -0.47
    POSITIVE LOGITS
     concentrated
    1.04
    concentr
    1.03
     density
    1.03
    density
    0.95
    Concentr
    0.94
     concentrates
    0.93
     concentrate
    0.91
    Density
    0.89
     Density
    0.89
     densities
    0.86
    Act Density 1.543%

    No Known Activations