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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     insulator
    1.24
     luisant
    1.23
     câte
    1.20
     instincts
    1.20
     veliko
    1.19
     steaming
    1.19
    泂
    1.17
    nickname
    1.17
    çalves
    1.15
     cravings
    1.15
    POSITIVE LOGITS
    ع
    1.31
    с
    1.30
    der
    1.30
    紹介
    1.14
    bec
    1.12
    アクセサリー
    1.12
    다
    1.09
    어야
    1.07
    DER
    1.05
    N
    1.04
    Act Density 0.000%

    No Known Activations