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

    Neuronpedia

    INDEX
    Explanations

    instances of closing braces or curly brackets in code or formatted text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '}),
    -0.85
    __':
    -0.83
    ’.”
    -0.82
    ')],
    -0.82
    '});
    -0.82
    Билгалдахарш
    -0.82
    ')}
    -0.81
    '."
    -0.79
    */),
    -0.78
    ])]
    -0.78
    POSITIVE LOGITS
    }'
    0.77
    OfMonth
    0.55
    }',
    0.52
     cn
    0.51
    🏻
    0.50
    μάτων
    0.50
     saja
    0.49
    tor
    0.48
     mode
    0.47
    cn
    0.47
    Act Density 0.105%

    No Known Activations