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

    Neuronpedia

    INDEX
    Explanations

    specific names and proper nouns related to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keit
    -0.22
    tection
    -0.18
    stery
    -0.17
    er
    -0.17
    inton
    -0.16
    ób
    -0.16
    erer
    -0.15
    arness
    -0.15
    ged
    -0.15
    lette
    -0.15
    POSITIVE LOGITS
    ertainment
    0.25
    ucky
    0.21
    itled
    0.20
    sov
    0.18
    t
    0.17
    tir
    0.17
    ech
    0.17
    ilation
    0.17
    roduced
    0.17
    une
    0.16
    Act Density 0.090%

    No Known Activations