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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    morning
    -0.77
    porter
    -0.64
     maze
    -0.61
     background
    -0.61
     mog
    -0.59
    ndra
    -0.59
    sequence
    -0.59
    sembly
    -0.59
    crow
    -0.58
    Daily
    -0.58
    POSITIVE LOGITS
     Loyal
    0.68
     Riders
    0.68
     ACTIONS
    0.66
    ipolar
    0.65
     Tact
    0.62
    leans
    0.61
    witz
    0.61
    atz
    0.59
     tempered
    0.59
    amy
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.