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

    Neuronpedia

    INDEX
    Explanations

    specific linguistic patterns involving pronouns and structures in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ävän
    -0.62
     المعيارى
    -0.59
    exitRule
    -0.58
    SourceChecksum
    -0.57
     '\\;'
    -0.57
    jspx
    -0.56
    petto
    -0.56
     nakalista
    -0.56
    BeginContext
    -0.56
    HandlerContext
    -0.54
    POSITIVE LOGITS
     biz
    0.58
     acaba
    0.56
     emin
    0.56
     seni
    0.56
     sende
    0.52
    Biz
    0.51
     senden
    0.51
     valla
    0.51
    Seni
    0.50
    Umar
    0.50
    Act Density 0.066%

    No Known Activations