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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -enabled
    -0.07
    _PARAM
    -0.07
     suspense
    -0.07
    帘
    -0.07
    (_
    -0.07
     уже
    -0.07
    觊
    -0.07
    (cfg
    -0.07
    (config
    -0.07
     count
    -0.07
    POSITIVE LOGITS
     pemb
    0.07
    托运
    0.07
     Wooden
    0.07
    *sizeof
    0.06
    兰花
    0.06
    (fe
    0.06
    *ft
    0.06
    AIR
    0.06
    lfw
    0.06
    队伍建设
    0.06
    Act Density 0.005%

    No Known Activations