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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     اليس
    0.42
    اص
    0.41
    că
    0.40
     prick
    0.39
    Hb
    0.38
    IdleSync
    0.37
     администрации
    0.36
    irão
    0.36
    весто
    0.36
    適
    0.36
    POSITIVE LOGITS
     authoritative
    0.41
    ুদ্ধে
    0.39
     persona
    0.37
    Define
    0.37
    things
    0.37
     thoughtfulness
    0.37
     বেশিরভাগ
    0.36
    Bond
    0.36
     Appearance
    0.36
     sos
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.