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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Offense
    -0.76
    =\"
    -0.66
    addons
    -0.66
    urrent
    -0.65
     Diseases
    -0.64
    ements
    -0.64
     guiActiveUn
    -0.63
    Information
    -0.63
    Hill
    -0.61
    cia
    -0.61
    POSITIVE LOGITS
    pour
    0.73
     Papa
    0.72
    bringer
    0.69
     Hasan
    0.67
    asper
    0.64
    tained
    0.63
     paran
    0.63
    ardi
    0.61
     Carlo
    0.60
    acht
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.