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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    istor
    -0.82
    agher
    -0.80
    apo
    -0.77
    OPLE
    -0.74
    phrine
    -0.73
     Bride
    -0.71
     Editors
    -0.70
    reader
    -0.70
    ener
    -0.69
    Header
    -0.68
    POSITIVE LOGITS
     az
    0.66
     parap
    0.65
    ìĿ
    0.65
     realize
    0.65
     MIS
    0.64
    rid
    0.63
     grandson
    0.61
    sense
    0.60
     Vern
    0.60
    lot
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.