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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific structured data or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.88
    tableFuture
    -0.86
    principalColumn
    -0.86
    Datuak
    -0.84
    Tikang
    -0.77
    ГЛА
    -0.76
    出版年
    -0.73
    MessageOf
    -0.73
     joaat
    -0.73
    addCriterion
    -0.72
    POSITIVE LOGITS
    <eos>
    0.68
    ↵↵↵
    0.60
    ValueStyle
    0.57
    ↵↵↵↵
    0.54
     дописавши
    0.53
    </h6>
    0.52
    arent
    0.52
    ↵↵
    0.51
    hdashline
    0.50
    вед
    0.49
    Act Density 0.057%

    No Known Activations