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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ocaust
    -0.08
    -field
    -0.07
     soda
    -0.07
    ɤ
    -0.07
    _SECTION
    -0.07
    理事
    -0.07
    .basic
    -0.07
     regular
    -0.07
    .contact
    -0.07
     fork
    -0.07
    POSITIVE LOGITS
    又能
    0.08
     as
    0.08
    eday
    0.07
     enough
    0.07
    宁愿
    0.07
     constrain
    0.07
    🛏
    0.07
    าก
    0.07
    нет
    0.07
    𝓢
    0.07
    Act Density 0.012%

    No Known Activations