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

    Neuronpedia

    INDEX
    Explanations

    structures in programming code or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Witch
    -0.35
     mess
    -0.34
     SIMBAD
    -0.34
    Witch
    -0.33
     انگلیسی
    -0.33
     Verdad
    -0.32
     Irland
    -0.32
    Välkommen
    -0.32
    Vý
    -0.32
    ruk
    -0.32
    POSITIVE LOGITS
     للاسماء
    0.84
    出版年
    0.65
     zijne
    0.64
    TagMode
    0.62
    \{\\
    0.61
    Diweddarwch
    0.61
     ostavi
    0.59
     فريبيس
    0.59
    expandindo
    0.59
    NameInMap
    0.58
    Act Density 0.248%

    No Known Activations