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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ients
    -0.83
     "$:/
    -0.77
    adesh
    -0.73
    atures
    -0.73
    cause
    -0.71
    iency
    -0.71
    izont
    -0.70
    atively
    -0.69
    ntil
    -0.68
    keyes
    -0.68
    POSITIVE LOGITS
     FT
    0.73
     Ryder
    0.70
    dated
    0.68
     Pegasus
    0.67
     OECD
    0.66
     Blueprint
    0.65
     Frozen
    0.65
     Rue
    0.64
     Lith
    0.63
     Failed
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.