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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     LL
    -0.07
    ']].
    -0.07
     SIGN
    -0.07
    akespeare
    -0.06
    過
    -0.06
    IGHT
    -0.06
    ']])↵
    -0.06
    油气
    -0.06
    аль
    -0.06
    氨酸
    -0.06
    POSITIVE LOGITS
     Vanity
    0.07
    فشل
    0.07
     stash
    0.07
    ertain
    0.07
    尊敬
    0.07
     FIXED
    0.07
    _Login
    0.07
    农资
    0.07
    .libs
    0.07
     hates
    0.06
    Act Density 0.048%

    No Known Activations