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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (baseUrl
    -0.07
    reinterpret
    -0.07
    OPLE
    -0.07
    _an
    -0.07
    🥗
    -0.07
    unfold
    -0.07
    (newUser
    -0.07
     Chapter
    -0.07
    拮
    -0.07
    ꫀ
    -0.07
    POSITIVE LOGITS
     Sheldon
    0.07
     Fucked
    0.07
    牢
    0.07
    'R
    0.06
    ﻭ
    0.06
     destruction
    0.06
    coeff
    0.06
     ghetto
    0.06
    €�
    0.06
     בגין
    0.06
    Act Density 0.033%

    No Known Activations