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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Brown
    -0.07
     Iranians
    -0.07
     holog
    -0.07
     hissed
    -0.06
    ihn
    -0.06
     dolphins
    -0.06
    amodel
    -0.06
     applicationWill
    -0.06
    ルフ
    -0.06
    ��이
    -0.06
    POSITIVE LOGITS
    emem
    0.08
    %.
    0.07
    ARING
    0.06
    faculty
    0.06
    .utc
    0.06
    prepend
    0.06
     instanceof
    0.06
    %.↵
    0.06
    FromString
    0.06
    혹
    0.06
    Act Density 0.000%

    No Known Activations