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

    Neuronpedia

    INDEX
    Explanations

    references to structured data and source definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.86
    windowFixed
    -0.77
    Portale
    -0.74
    TagMode
    -0.74
    Datuak
    -0.73
    RegressionTest
    -0.72
    مراجع
    -0.71
    tonode
    -0.70
     GenerationType
    -0.70
    Portail
    -0.69
    POSITIVE LOGITS
    الإنجليزية
    0.59
     تضيفلها
    0.59
    ."</
    0.54
    いたり
    0.54
     Chwiliwch
    0.52
    Conclusie
    0.49
     transfieras
    0.49
     infine
    0.49
    […]
    0.47
    usiai
    0.47
    Act Density 0.537%

    No Known Activations