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

    Neuronpedia

    INDEX
    Explanations

    Python code snippets related to class definitions and memory usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trolling
    -0.14
    antz
    -0.14
    森
    -0.14
    oring
    -0.14
    oran
    -0.13
    anou
    -0.13
    orer
    -0.13
    orial
    -0.13
    owi
    -0.13
     portion
    -0.13
    POSITIVE LOGITS
    оÑĤÑĮ
    0.17
    pray
    0.15
    QualifiedName
    0.15
    309
    0.15
    OUS
    0.15
    exus
    0.14
    Controllers
    0.14
    397
    0.14
    ÑĨин
    0.13
    905
    0.13
    Act Density 0.015%

    No Known Activations