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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.80
    hyde
    -0.73
    rophic
    -0.72
    isode
    -0.72
    oppable
    -0.68
    estern
    -0.68
    quire
    -0.65
    achine
    -0.65
    enegger
    -0.65
    emonic
    -0.65
    POSITIVE LOGITS
    jas
    0.68
     harm
    0.61
     PKK
    0.61
     BAD
    0.60
    jan
    0.60
     Berk
    0.59
     SHA
    0.59
    >"
    0.58
     LLP
    0.58
     grievances
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.