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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     smoky
    0.49
     abiotic
    0.47
     tweeting
    0.46
     spelling
    0.45
     automaker
    0.44
     songs
    0.44
    żenia
    0.44
     distribution
    0.43
     tweet
    0.43
     arts
    0.42
    POSITIVE LOGITS
     பெரும்பாலும்
    0.44
    見積
    0.44
     годах
    0.43
    chmal
    0.43
    기의
    0.43
     Вам
    0.43
     ይህ
    0.42
    gebäude
    0.42
     سلس
    0.42
    Victory
    0.42
    Act Density 0.002%

    No Known Activations