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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    room
    -0.85
    rooms
    -0.73
    ¨
    -0.69
    Du
    -0.66
    aba
    -0.64
     Gund
    -0.63
    PLA
    -0.63
    Cre
    -0.63
    DK
    -0.61
    =\"
    -0.61
    POSITIVE LOGITS
    renheit
    0.79
    anchester
    0.75
     rall
    0.74
     horizont
    0.70
    erning
    0.69
    rences
    0.68
     tongues
    0.67
    yd
    0.66
    itivity
    0.66
    vre
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.