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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cipline
    -0.80
    ilver
    -0.69
    verty
    -0.69
    addle
    -0.67
    arthy
    -0.67
     timet
    -0.66
    urat
    -0.66
    arak
    -0.65
    NL
    -0.65
    Buyable
    -0.64
    POSITIVE LOGITS
     pods
    0.71
    ĸļ
    0.70
    iners
    0.64
     salsa
    0.63
     7000
    0.61
     Mariners
    0.61
     canopy
    0.58
    cible
    0.57
     pod
    0.57
     booking
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.