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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and concepts that express value or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.17
    brids
    -0.16
    ertoire
    -0.15
    lf
    -0.14
    conom
    -0.14
    ìĦ±
    -0.14
    odem
    -0.14
    ulum
    -0.13
    atsu
    -0.13
    VEC
    -0.13
    POSITIVE LOGITS
    oldem
    0.15
    osy
    0.14
    ucken
    0.14
    maları
    0.14
    cased
    0.13
    ÙĪÛĮس
    0.13
     سÙģ
    0.13
    capture
    0.13
    Concrete
    0.13
     punct
    0.13
    Act Density 0.451%

    No Known Activations