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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     imperson
    -0.06
     Number
    -0.06
    iler
    -0.06
    thing
    -0.06
     earlier
    -0.06
    asts
    -0.06
    ambi
    -0.05
    Number
    -0.05
     official
    -0.05
     pledges
    -0.05
    POSITIVE LOGITS
     myself
    0.08
    æĺ¯æĪij
    0.08
     my
    0.07
    isque
    0.07
     hopefully
    0.07
     íĦ
    0.07
    favor
    0.07
     vulner
    0.07
    è¥
    0.07
    ãĥģãĥ¥
    0.07
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.