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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lil
    -0.07
     punitive
    -0.07
     ul
    -0.07
    bor
    -0.07
    .\
    -0.07
    历
    -0.06
     Fiesta
    -0.06
     ji
    -0.06
     shutter
    -0.06
    ppo
    -0.06
    POSITIVE LOGITS
    不小
    0.07
    orarily
    0.07
    .feed
    0.07
    试试
    0.07
    脸上
    0.07
    resse
    0.07
    بطل
    0.07
    心情
    0.07
    =bool
    0.07
    Reducers
    0.07
    Act Density 0.000%

    No Known Activations