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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     estremamente
    0.88
     매우
    0.88
     extremamente
    0.87
     absolutamente
    0.87
     অত্যন্ত
    0.85
     extrêmement
    0.85
     అనేక
    0.77
     굉장히
    0.77
     niezwy
    0.76
    极其
    0.75
    POSITIVE LOGITS
     beforehand
    0.94
     overall
    0.90
     afterward
    0.87
     :)
    0.85
     upfront
    0.85
     😊
    0.85
     :).
    0.84
     initially
    0.84
     otherwise
    0.83
    .).
    0.82
    Act Density 3.310%

    No Known Activations