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

    Neuronpedia

    INDEX
    Explanations

    concepts related to equity and the distribution of resources or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.15
    inand
    -0.13
    ulton
    -0.13
    olin
    -0.13
    eldorf
    -0.12
    .GetOrdinal
    -0.12
    esz
    -0.12
    ukan
    -0.12
    unde
    -0.12
    etz
    -0.12
    POSITIVE LOGITS
     equal
    0.86
     equ
    0.75
     Equal
    0.71
    equal
    0.71
     Equ
    0.69
     EQUAL
    0.69
     equality
    0.68
    equ
    0.68
    Equal
    0.66
     equally
    0.66
    Act Density 0.494%

    No Known Activations