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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text segments or sections marked by a specific token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.90
    تقاوى
    -0.83
    Datuak
    -0.79
    最快更新
    -0.78
    Portály
    -0.78
    Personensuche
    -0.76
    PhysRevD
    -0.74
     Chwiliwch
    -0.73
    зулта
    -0.73
    hubanes
    -0.68
    POSITIVE LOGITS
    <bos>
    0.68
    tagHelperRunner
    0.56
     
    0.46
    ’
    0.44
    TagHelpers
    0.41
     cliquez
    0.41
    TextHelper
    0.41
    tso
    0.41
     referentes
    0.41
     doświad
    0.40
    Act Density 0.014%

    No Known Activations