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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical expressions and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -1.29
     kaarangay
    -1.24
    rungsseite
    -1.21
    دانشنامهٔ
    -1.09
    SourceChecksum
    -1.08
    ]")]
    -0.99
     ویکی‌پدی
    -0.98
    MessageOf
    -0.98
    tagHelperRunner
    -0.97
    Geplaatst
    -0.95
    POSITIVE LOGITS
    ↵
    0.62
    .
    0.62
    ).
    0.61
     etc
    0.60
    [toxicity=0]
    0.54
     thereof
    0.52
     …
    0.51
     […]
    0.50
    +:+
    0.50
     therefrom
    0.47
    Act Density 35.039%

    No Known Activations