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

    Neuronpedia

    INDEX
    Explanations

    words related to societal issues and actions, particularly negative ones

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with political or societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.73
    ertodd
    -0.71
     McGr
    -0.71
    ĸļ
    -0.68
    uala
    -0.61
    awaru
    -0.60
    å°Ĩ
    -0.58
    姫
    -0.58
     Edited
    -0.57
     Maxwell
    -0.57
    POSITIVE LOGITS
     portion
    0.90
     aspect
    0.80
     component
    0.80
     axis
    0.79
     impulse
    0.79
     facade
    0.78
     element
    0.74
     notion
    0.74
     impulses
    0.72
    iest
    0.72
    Act Density 0.774%

    No Known Activations