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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oms
    -0.79
    ersen
    -0.73
    iens
    -0.69
    iances
    -0.68
    heim
    -0.68
    erer
    -0.66
    udes
    -0.65
    irement
    -0.65
    itude
    -0.64
    iers
    -0.64
    POSITIVE LOGITS
    Unix
    0.79
    ItemTracker
    0.68
    beam
    0.68
    Patch
    0.67
    DOS
    0.65
    OVA
    0.65
     Inqu
    0.64
     Klux
    0.64
    Know
    0.64
    nect
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.