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

    Neuronpedia

    INDEX
    Explanations

    references to negative qualities, particularly related to health and performance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evi
    -0.17
    entai
    -0.17
    ean
    -0.17
    eligible
    -0.14
    elic
    -0.14
    gle
    -0.14
    886
    -0.14
    olest
    -0.14
    -ÑĤо
    -0.14
     åĸ
    -0.14
    POSITIVE LOGITS
    -quality
    0.19
    /no
    0.16
    ening
    0.16
    lyn
    0.15
    (er
    0.15
    isle
    0.15
    quality
    0.14
    /null
    0.14
    /free
    0.14
    sville
    0.14
    Act Density 0.055%

    No Known Activations