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

    Neuronpedia

    INDEX
    Explanations

    mentions of categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryo
    -0.17
    ly
    -0.16
    erty
    -0.15
    éal
    -0.15
    leigh
    -0.15
    ayd
    -0.15
    ors
    -0.14
    breaker
    -0.14
    ora
    -0.14
    swer
    -0.14
    POSITIVE LOGITS
    atsby
    0.18
    (Category
    0.17
    /categories
    0.17
    alars
    0.15
    /class
    0.15
    égorie
    0.15
    åĪ¥
    0.15
    ãģ°ãģĭãĤĬ
    0.15
    kos
    0.15
    paces
    0.14
    Act Density 0.029%

    No Known Activations