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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     traj
    -0.07
    暾
    -0.07
    <const
    -0.07
    骙
    -0.07
     Serum
    -0.07
     teg
    -0.07
    蕙
    -0.07
    钛
    -0.06
    /tasks
    -0.06
    することは
    -0.06
    POSITIVE LOGITS
    }></
    0.07
    Bomb
    0.07
    abilit
    0.07
    对我说
    0.07
    MODEL
    0.07
    ialog
    0.07
    bolt
    0.07
    *d
    0.07
    Cols
    0.07
    ROLLER
    0.07
    Act Density 0.048%

    No Known Activations