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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest complexity or depth in communication and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ate
    -0.15
    intern
    -0.14
    ull
    -0.14
    oya
    -0.14
     quickly
    -0.14
    ushman
    -0.14
    abl
    -0.14
     Stone
    -0.14
    ateur
    -0.13
    rer
    -0.13
    POSITIVE LOGITS
    ucose
    0.16
    oog
    0.15
    دÙĪ
    0.15
    ned
    0.15
    ourcing
    0.15
    нение
    0.14
    isses
    0.14
    odzi
    0.14
    oggler
    0.14
    ì²Ļ
    0.14
    Act Density 0.011%

    No Known Activations