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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical symbols or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.85
     photolibrary
    -0.84
    )");
    -0.80
    </u>
    -0.78
     itſelf
    -0.77
     ZS
    -0.77
    +#+#
    -0.76
    </strong>
    -0.74
    :");
    -0.73
     
    -0.73
    POSITIVE LOGITS
    <eos>
    0.88
    ↵↵
    0.83
    ↵↵↵
    0.79
    ↵↵↵↵
    0.73
    .
    0.73
    ↵
    0.71
    )))),
    0.65
    ↵↵↵↵↵
    0.64
    )))))
    0.61
    ;
    0.57
    Act Density 1.570%

    No Known Activations