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

    Neuronpedia

    INDEX
    Explanations

    references to formal recognition events like awards or ceremonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.84
     $_"
    -0.80
     Majefty
    -0.80
    ArrowToggle
    -0.80
     Cuthbert
    -0.78
     Italijani
    -0.78
    σθαι
    -0.77
    MessageState
    -0.76
     समीक्षक
    -0.75
     Italijanski
    -0.75
    POSITIVE LOGITS
    ↵
    1.36
    ↵↵
    1.28
    ↵↵↵↵↵
    1.09
    ↵↵↵
    1.08
    ↵↵↵↵
    1.02
    </tr>
    1.02
    ↵↵↵↵↵↵
    1.00
    ↵↵↵↵↵↵↵↵
    0.90
    ↵↵↵↵↵↵↵
    0.90
    [toxicity=0]
    0.88
    Act Density 0.039%

    No Known Activations