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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    넖
    -0.07
    孩童
    -0.07
    (comp
    -0.07
    judge
    -0.06
    ᄢ
    -0.06
     טוען
    -0.06
     fair
    -0.06
    iod
    -0.06
     correspondent
    -0.06
     Equipment
    -0.06
    POSITIVE LOGITS
    _closure
    0.07
    𝚎
    0.07
    ﾛ
    0.07
    与其他
    0.07
    roup
    0.06
     babel
    0.06
    _tpl
    0.06
    azione
    0.06
    (:,
    0.06
    ...');↵
    0.06
    Act Density 0.017%

    No Known Activations