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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions related to diversity and inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obi
    -0.17
    uien
    -0.16
    ham
    -0.16
    eer
    -0.15
    ister
    -0.15
    stones
    -0.15
    prises
    -0.15
    TERN
    -0.15
    tings
    -0.15
    lob
    -0.15
    POSITIVE LOGITS
    /div
    0.28
     richness
    0.17
    andin
    0.16
    tape
    0.15
    /custom
    0.15
    oru
    0.15
    alette
    0.15
    Kid
    0.14
     backgrounds
    0.14
    ANGLE
    0.14
    Act Density 0.025%

    No Known Activations