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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    เรื่อง
    0.49
    计划
    0.48
    実行
    0.46
    曺
    0.46
     strategie
    0.45
     компет
    0.45
    議題
    0.45
     бизне
    0.44
     دعوت
    0.43
    挨拶
    0.43
    POSITIVE LOGITS
     상태
    0.52
     부분이
    0.50
     모양
    0.48
    放入
    0.47
    线条
    0.46
     부분
    0.45
    얇
    0.45
     형태
    0.44
    材质
    0.44
     부분을
    0.44
    Act Density 0.001%

    No Known Activations