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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    milo
    -0.82
    Initialized
    -0.78
    pection
    -0.68
    ixtape
    -0.67
    ierra
    -0.66
     Trooper
    -0.66
    olon
    -0.66
    DEN
    -0.65
    ONY
    -0.65
    VERTISEMENT
    -0.64
    POSITIVE LOGITS
    akable
    0.76
     Py
    0.72
    orthy
    0.65
    eming
    0.62
    mud
    0.61
     Saur
    0.60
     Voldemort
    0.60
    akov
    0.59
     stir
    0.59
    fell
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.