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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that start with a specific token or marker, indicating the beginning of a new section or segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -1.41
     CreateTagHelper
    -1.03
    RenderAtEndOf
    -1.02
     '\\;'
    -0.94
    ValueStyle
    -0.92
    
    -0.87
    ViewFeatures
    -0.87
     betweenstory
    -0.84
    AndEndTag
    -0.84
     AssemblyCompany
    -0.84
    POSITIVE LOGITS
    <bos>
    0.57
    be
    0.50
    .
    0.50
    Special
    0.49
     Special
    0.47
    Sta
    0.44
    sta
    0.42
    wedge
    0.40
    Step
    0.40
     принадле
    0.40
    Act Density 0.000%

    No Known Activations