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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    apt
    -0.07
    感叹
    -0.07
     har
    -0.06
     fc
    -0.06
    每年
    -0.06
    byss
    -0.06
     Bour
    -0.06
     HOR
    -0.06
     Dum
    -0.06
    Aus
    -0.06
    POSITIVE LOGITS
    resco
    0.07
    Serializer
    0.07
    往往会
    0.07
     Britann
    0.06
    �
    0.06
    槌
    0.06
    IALIZ
    0.06
    ⏰
    0.06
    ("?
    0.06
     graphql
    0.06
    Act Density 0.007%

    No Known Activations