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

    Neuronpedia

    INDEX
    Explanations

    references to age, race, or class distinctions with a focus on individuals of color

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amount
    -0.15
    osti
    -0.15
    eness
    -0.15
    ifo
    -0.15
    irim
    -0.15
    rates
    -0.15
    abis
    -0.14
    aminer
    -0.14
    .presentation
    -0.14
    aty
    -0.14
    POSITIVE LOGITS
    Means
    0.19
     stature
    0.18
     consequence
    0.18
     integrity
    0.18
     means
    0.17
     mixed
    0.17
     Means
    0.16
     goodwill
    0.16
     substance
    0.15
    ë¯
    0.15
    Act Density 0.050%

    No Known Activations