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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, including names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     something
    -0.62
     talk
    -0.49
     بيها
    -0.48
    ...@
    -0.48
    FirstResponder
    -0.46
    ...>
    -0.45
     som
    -0.45
    =[];
    -0.45
    -
    -0.45
     modern
    -0.45
    POSITIVE LOGITS
     فريبيس
    1.21
     Italijanski
    0.97
    rungsseite
    0.94
    RegressionTest
    0.91
    تقاوى
    0.88
    IntoConstraints
    0.88
    UnusedPrivate
    0.87
    __((
    0.83
    @[+][
    0.83
    InjectAttribute
    0.82
    Act Density 2.189%

    No Known Activations