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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Absolute
    -0.08
    腹
    -0.08
    .Domain
    -0.07
    пись
    -0.07
    .profile
    -0.07
     Jelly
    -0.07
     ORIGINAL
    -0.07
    有不少
    -0.07
    亞
    -0.07
    )):↵
    -0.07
    POSITIVE LOGITS
     besser
    0.07
    _Run
    0.07
    gw
    0.06
     crédit
    0.06
     orchestr
    0.06
    adro
    0.06
    넗
    0.06
    movies
    0.06
     performed
    0.06
    荷
    0.06
    Act Density 0.003%

    No Known Activations