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

    Neuronpedia

    INDEX
    Explanations

    tokens that signal the beginning of a new section or idea, such as <bos>

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.74
     Bennett
    -0.69
    ophi
    -0.67
    ませんが
    -0.66
    Rüyada
    -0.65
    cpy
    -0.64
     Levy
    -0.62
    Enllaces
    -0.61
    Levy
    -0.61
    IALES
    -0.59
    POSITIVE LOGITS
     nakalista
    0.86
    </caption>
    0.80
     CreateTagHelper
    0.75
     שוליים
    0.74
    </th>
    0.73
    enumi
    0.72
    ">)</
    0.71
    \{\\
    0.70
    getMenuInflater
    0.70
    </h2>
    0.70
    Act Density 0.026%

    No Known Activations