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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uch
    -0.20
    anga
    -0.16
     Joi
    -0.15
     phóng
    -0.15
    erce
    -0.15
    acer
    -0.15
     Gregory
    -0.14
     Erotik
    -0.14
    empo
    -0.14
    ạo
    -0.14
    POSITIVE LOGITS
     grade
    0.15
    bf
    0.15
    it
    0.14
     Grade
    0.14
    -grade
    0.14
    ÅĤad
    0.14
    èĪ¬
    0.14
     Cent
    0.14
    pane
    0.14
     Austr
    0.13
    Act Density 0.030%

    No Known Activations