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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    chin
    -0.08
    鹆
    -0.07
     delays
    -0.07
    -Oct
    -0.07
     Ga
    -0.06
     gerne
    -0.06
     caul
    -0.06
     yayg
    -0.06
     Simmons
    -0.06
     barbar
    -0.06
    POSITIVE LOGITS
    ToBounds
    0.07
    𝚘
    0.07
    !)↵
    0.07
    /)↵
    0.07
     bondage
    0.07
    หนาว
    0.07
    heed
    0.07
    .FromResult
    0.07
    -terrorism
    0.06
    卧
    0.06
    Act Density 0.001%

    No Known Activations