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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases and references to various participants or elements in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.06
    KommentareTeilen
    -1.01
    WriteTagHelper
    -0.92
     GenerationType
    -0.89
    الدراسه
    -0.87
    ftagPool
    -0.82
     betweenstory
    -0.81
     lenker
    -0.80
    EndProject
    -0.79
    complexContent
    -0.78
    POSITIVE LOGITS
    <eos>
    0.80
     tartalomajánló
    0.58
     дописавши
    0.56
     للاسماء
    0.48
    Koordinaten
    0.45
     getRule
    0.44
    ↵↵↵
    0.44
    AccessorTable
    0.42
    ↵↵↵↵
    0.42
    ないように
    0.42
    Act Density 1.560%

    No Known Activations