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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nai
    -0.69
     complainant
    -0.66
    astered
    -0.65
     teammate
    -0.65
     accuser
    -0.65
     accus
    -0.63
    chal
    -0.63
     veh
    -0.62
    justice
    -0.62
    clock
    -0.61
    POSITIVE LOGITS
    poons
    0.77
    \":
    0.70
    bes
    0.69
    ãĥĺ
    0.69
    akings
    0.68
    olver
    0.68
     FANT
    0.67
    ales
    0.67
    ãĤ¤ãĥĪ
    0.67
     ende
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.