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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that convey a sense of lightness or freshness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ŀ
    -0.15
    оÑĢÑĤ
    -0.15
    lez
    -0.15
    ean
    -0.14
    atically
    -0.14
    amet
    -0.14
    iston
    -0.14
     Richt
    -0.14
    ideshow
    -0.13
    ª
    -0.13
    POSITIVE LOGITS
    ening
    0.30
    ened
    0.27
    ning
    0.26
    NING
    0.25
    nings
    0.24
    enment
    0.22
    -weight
    0.21
    bul
    0.21
    (light
    0.21
    -duty
    0.20
    Act Density 0.019%

    No Known Activations