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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rejoice
    -0.07
    �
    -0.07
     Jennifer
    -0.07
    配备
    -0.07
     Kind
    -0.07
    (with
    -0.07
     Charset
    -0.06
    �
    -0.06
     Ma
    -0.06
    (/
    -0.06
    POSITIVE LOGITS
    🙊
    0.07
     стоимости
    0.07
    ,double
    0.07
    𥔲
    0.07
    __,__
    0.07
    Propagation
    0.06
    -double
    0.06
    ();++
    0.06
    ">';
↵
    0.06
    abhäng
    0.06
    Act Density 0.002%

    No Known Activations