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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     followed
    -0.31
    jec
    -0.27
    è¿ij
    -0.26
     Follow
    -0.26
     follow
    -0.26
     ASS
    -0.25
     vá»ı
    -0.24
     AUG
    -0.24
    quis
    -0.23
     ensemble
    -0.23
    POSITIVE LOGITS
    è§Ħéģ¿
    0.31
    stan
    0.29
    顾
    0.27
    梯
    0.26
    è·¨è¶Ĭ
    0.24
    ÅĽnie
    0.24
    åįıåķĨ
    0.24
    InstanceState
    0.24
    ì¼ľ
    0.24
    åĨĴçĿĢ
    0.23
    Act Density 3.604%

    No Known Activations

    This feature has no known activations.