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

    Neuronpedia

    INDEX
    Explanations

    words related to organization and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phro
    -0.86
    namb
    -0.81
    ילום
    -0.69
    ppert
    -0.66
    internalType
    -0.65
     att
    -0.65
     Ella
    -0.65
     Pont
    -0.63
    miyorum
    -0.63
    nought
    -0.62
    POSITIVE LOGITS
    ized
    1.39
    ize
    1.30
    izations
    1.28
    ization
    1.28
    IZED
    1.25
     Maximize
    1.19
    izing
    1.17
    IZATION
    1.07
     privatization
    1.05
    IZE
    1.04
    Act Density 0.288%

    No Known Activations