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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ham
    -0.08
     agr
    -0.08
     butter
    -0.08
     oil
    -0.07
    noise
    -0.07
    .pid
    -0.07
    PUTE
    -0.07
    Brazil
    -0.07
    .For
    -0.07
    (nr
    -0.07
    POSITIVE LOGITS
    ochen
    0.08
    �
    0.07
    哈哈哈哈
    0.07
    カテゴ
    0.07
    か
    0.07
    置いて
    0.07
    思わ
    0.07
    �
    0.06
    あ
    0.06
    (ExpectedConditions
    0.06
    Act Density 0.000%

    No Known Activations