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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     betray
    -0.07
     BI
    -0.06
     tolerate
    -0.06
    高额
    -0.06
    שתי
    -0.06
    (Link
    -0.06
    _virtual
    -0.06
    ,vector
    -0.06
    	active
    -0.06
    .Tele
    -0.06
    POSITIVE LOGITS
    ilia
    0.08
    里面
    0.07
    ınd
    0.07
    早上
    0.07
     meaning
    0.07
    .DisplayName
    0.07
    谬
    0.07
    ropped
    0.07
    iad
    0.07
    ogens
    0.06
    Act Density 0.001%

    No Known Activations