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

    Neuronpedia

    INDEX
    Explanations

    articles and quantifiers in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Luz
    -0.14
    939
    -0.14
    ÑĢÑıд
    -0.14
    ç¥
    -0.14
    heid
    -0.14
    afone
    -0.14
    metric
    -0.13
    metrics
    -0.13
    937
    -0.13
    ventus
    -0.13
    POSITIVE LOGITS
    aginator
    0.22
    ãĥ³ãĥIJ
    0.15
    856
    0.15
    оÑĢдин
    0.15
    zilla
    0.15
    °ëĭ¤
    0.14
    ulator
    0.13
    ел
    0.13
    ials
    0.13
     Manning
    0.13
    Act Density 0.132%

    No Known Activations