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

    Neuronpedia

    INDEX
    Explanations

    references to intensity or extremes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rial
    -0.17
    roll
    -0.17
    apus
    -0.16
    deme
    -0.15
    erable
    -0.15
     Herrera
    -0.15
    ability
    -0.15
    ry
    -0.15
    TEGR
    -0.14
     pus
    -0.14
    POSITIVE LOGITS
    /ext
    0.19
    /fast
    0.17
    ities
    0.16
    ìłģìĿ¸
    0.15
    cly
    0.15
    leigh
    0.15
    ely
    0.15
    (QObject
    0.14
     levels
    0.14
    اÙ
    0.14
    Act Density 0.050%

    No Known Activations