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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Else
    -0.75
    esse
    -0.73
    Introduced
    -0.72
    Hung
    -0.72
    Hunt
    -0.71
    nel
    -0.71
    DEP
    -0.71
     pestic
    -0.69
    Dispatch
    -0.67
    Hu
    -0.67
    POSITIVE LOGITS
    ardi
    0.72
    pta
    0.67
     Rei
    0.66
     Shinji
    0.62
    ostics
    0.61
    ero
    0.61
     Godd
    0.61
    ocard
    0.60
    ocations
    0.59
    istries
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.