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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe states of being or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unce
    -0.09
    ulton
    -0.08
    ilen
    -0.07
    ÙıÙĨ
    -0.07
    ildo
    -0.07
    rine
    -0.07
    ilder
    -0.07
    unication
    -0.07
    /npm
    -0.07
     bey
    -0.07
    POSITIVE LOGITS
    ly
    0.10
    -wise
    0.09
    ely
    0.09
    aneously
    0.09
    ingly
    0.08
    wise
    0.08
    à¹Ĩ
    0.08
    ewise
    0.08
    LY
    0.08
     olarak
    0.08
    Act Density 0.065%

    No Known Activations