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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lessly
    1.11
    tive
    1.06
    Си
    0.98
     дело
    0.97
    ชร์
    0.96
    ндагы
    0.94
    𝙪
    0.94
    सभा
    0.93
    tenir
    0.91
    varande
    0.91
    POSITIVE LOGITS
     Rage
    1.17
     Saat
    1.17
     eyelashes
    1.15
    غة
    1.15
     Docs
    1.15
     tiếng
    1.14
     spirals
    1.13
     stints
    1.12
     격
    1.12
     ein
    1.12
    Act Density 0.000%

    No Known Activations