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

    Neuronpedia

    INDEX
    Explanations

    statements related to licensing and file headers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peran
    -0.59
    ceb
    -0.56
    meral
    -0.54
    Luka
    -0.54
     ActionResult
    -0.54
    icle
    -0.52
    veer
    -0.52
     vetro
    -0.52
     Cliffs
    -0.50
     DEAD
    -0.50
    POSITIVE LOGITS
    ");
    2.14
    ");
    1.92
    "));
    1.79
    "))
    1.78
    ")
    1.78
    "),
    1.76
    ").
    1.70
    ")[
    1.70
    ")).
    1.66
    ")
    1.65
    Act Density 0.106%

    No Known Activations