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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    树
    -0.07
    าร
    -0.07
    ألع
    -0.07
    孑
    -0.06
    려
    -0.06
    ascar
    -0.06
    髂
    -0.06
    cke
    -0.06
    굵
    -0.06
    udiant
    -0.06
    POSITIVE LOGITS
     especial
    0.07
    쵥
    0.07
    SUB
    0.06
    𝄴
    0.06
    딉
    0.06
    (template
    0.06
     cooldown
    0.06
     analyzer
    0.06
    该怎么办
    0.06
     muttered
    0.06
    Act Density 0.002%

    No Known Activations