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

    Neuronpedia

    INDEX
    Explanations

    words related to statistical terms, particularly 'standard'

    oai_token-act-pair · gpt-3.5-turbo

    references to various standards and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lez
    -0.79
    cig
    -0.74
    acan
    -0.73
    shit
    -0.71
    Rus
    -0.67
     destro
    -0.67
     fumes
    -0.66
    asus
    -0.65
    scient
    -0.65
    amia
    -0.65
    POSITIVE LOGITS
     deviation
    1.58
     deviations
    1.40
     bearer
    1.31
    ised
    1.18
    ization
    1.17
    isation
    1.03
    izes
    0.92
    ized
    0.90
    izations
    0.89
    izing
    0.89
    Act Density 0.031%

    No Known Activations