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

    Neuronpedia

    INDEX
    Explanations

    references to data observations and their status in a project or analysis context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sovereign
    -0.15
     slow
    -0.15
     direct
    -0.14
    goog
    -0.14
     magnitude
    -0.14
     court
    -0.14
    894
    -0.14
    253
    -0.13
     Dale
    -0.13
     mo
    -0.13
    POSITIVE LOGITS
    TestingModule
    0.17
    idel
    0.17
     example
    0.15
    IRO
    0.15
    илÑı
    0.14
    \Migrations
    0.14
     внÑĥÑĤ
    0.14
    оба
    0.14
    example
    0.14
    ezi
    0.14
    Act Density 0.172%

    No Known Activations