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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Citiz
    -0.74
     hers
    -0.70
    ulia
    -0.70
    senal
    -0.67
     Morales
    -0.66
     Gw
    -0.64
     encyclopedia
    -0.64
     Mash
    -0.64
     Wikimedia
    -0.64
     practical
    -0.63
    POSITIVE LOGITS
    stein
    0.79
    DAY
    0.79
    rod
    0.76
    tyard
    0.71
    BG
    0.68
    bon
    0.68
    bage
    0.67
    ror
    0.67
    rupted
    0.66
    sted
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.