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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ################
    -0.08
    ########
    -0.07
    🎦
    -0.07
    _activate
    -0.07
     }}"↵
    -0.07
    \n
    -0.07
    เทคโน
    -0.06
    _drv
    -0.06
    :first
    -0.06
    .newaxis
    -0.06
    POSITIVE LOGITS
     Global
    0.08
     wholesome
    0.08
     układ
    0.07
     OT
    0.07
     Nicaragua
    0.07
    至上
    0.07
     Fuk
    0.07
     bum
    0.07
    pieczeń
    0.07
    맺
    0.06
    Act Density 0.013%

    No Known Activations