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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Pacific
    -0.71
    CVE
    -0.70
    cause
    -0.70
    trap
    -0.69
    BY
    -0.66
     prol
    -0.66
    osponsors
    -0.65
    roxy
    -0.65
     Primal
    -0.64
    bleacher
    -0.63
    POSITIVE LOGITS
    llah
    0.83
    ihad
    0.69
    ente
    0.68
    aire
    0.66
     Muhammad
    0.65
    Hit
    0.63
    Grab
    0.61
     Hanson
    0.61
     Swed
    0.60
    rehens
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.