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

    Neuronpedia

    INDEX
    Explanations

    elements related to model construction and detailing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новниш
    -0.45
    Sklici
    -0.45
     Umum
    -0.44
    geführten
    -0.44
     שוליים
    -0.44
    geführt
    -0.43
     enseña
    -0.43
    führt
    -0.43
     Pemer
    -0.43
    lässlich
    -0.42
    POSITIVE LOGITS
    ={({
    0.46
    NOWLEDG
    0.39
    ביוגרפיה
    0.37
    BuilderFactory
    0.35
     cheap
    0.35
     nahilalakip
    0.34
     bVar
    0.34
    انتهای
    0.34
     кре
    0.34
    !(:
    0.34
    Act Density 0.560%

    No Known Activations