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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     core
    -0.08
    各有
    -0.07
    _module
    -0.07
    王子
    -0.07
     Put
    -0.07
     Hat
    -0.07
     thought
    -0.06
    兰花
    -0.06
    reamble
    -0.06
    酒吧
    -0.06
    POSITIVE LOGITS
    瞬
    0.07
    AILABLE
    0.07
    shaled
    0.07
     wybór
    0.07
     bask
    0.07
    昝
    0.07
    _PAGES
    0.07
    -initialized
    0.07
    ❘
    0.07
     aşağıd
    0.06
    Act Density 0.036%

    No Known Activations