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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Av
    -0.07
    _Account
    -0.07
    cle
    -0.07
     !!
    -0.07
    ớ
    -0.07
    ⼊
    -0.06
     Protein
    -0.06
     fra
    -0.06
    ych
    -0.06
    empty
    -0.06
    POSITIVE LOGITS
    /******/
    0.08
     fireworks
    0.07
     parentheses
    0.07
    学会了
    0.07
     hük
    0.07
     Haram
    0.07
     ceremonial
    0.07
     Horde
    0.07
     persön
    0.07
    _formats
    0.07
    Act Density 0.022%

    No Known Activations