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

    Neuronpedia

    INDEX
    Explanations

    terms associated with socioeconomic disparities and value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aurus
    -0.25
    ized
    -0.22
    ization
    -0.19
    ised
    -0.18
    thon
    -0.18
    IZED
    -0.18
    ización
    -0.17
    izers
    -0.17
    kers
    -0.16
    phere
    -0.16
    POSITIVE LOGITS
    fully
    0.28
    iness
    0.26
    lessly
    0.26
    fulness
    0.25
    ily
    0.20
    ãĢħ
    0.20
    ful
    0.19
    ster
    0.18
    enberg
    0.18
    FUL
    0.17
    Act Density 0.093%

    No Known Activations