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

    Neuronpedia

    INDEX
    Explanations

    the presence of punctuation and structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -1.02
     pylint
    -0.93
    setVerticalGroup
    -0.84
    verwijspagina
    -0.83
    MENAFN
    -0.83
     سكانية
    -0.80
     חיצוניים
    -0.79
    tvguidetime
    -0.76
    istoitu
    -0.75
    RectangleBorder
    -0.73
    POSITIVE LOGITS
     The
    1.10
     What
    0.95
     When
    0.95
        
    0.88
     If
    0.85
     How
    0.85
          
    0.83
     For
    0.83
     There
    0.82
    The
    0.81
    Act Density 0.614%

    No Known Activations