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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .screen
    -0.07
     doors
    -0.07
    jà
    -0.07
     vẻ
    -0.07
    不断创新
    -0.07
     MICRO
    -0.06
    oriasis
    -0.06
     loved
    -0.06
    癌症
    -0.06
    Five
    -0.06
    POSITIVE LOGITS
     happy
    0.08
    𬘬
    0.07
     cutoff
    0.07
     Fact
    0.07
     לגמרי
    0.07
     ברור
    0.07
     hun
    0.07
    愉快
    0.07
     party
    0.07
    AGE
    0.07
    Act Density 0.005%

    No Known Activations