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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     השל
    -0.07
     cư
    -0.07
    胖
    -0.07
     стрем
    -0.07
     dark
    -0.07
    /MM
    -0.06
    没有人
    -0.06
     meets
    -0.06
     clown
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     asserted
    0.08
    recipient
    0.08
    💹
    0.07
    _commit
    0.07
    ocked
    0.07
     dando
    0.06
     ]]
    0.06
    _Out
    0.06
    Round
    0.06
    (rule
    0.06
    Act Density 0.002%

    No Known Activations