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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sample
    -0.69
    share
    -0.62
    Lie
    -0.61
    halla
    -0.61
     Swiss
    -0.60
     Overwatch
    -0.60
     rehe
    -0.60
    etc
    -0.60
    define
    -0.59
    ãĤ¹
    -0.58
    POSITIVE LOGITS
    ays
    0.72
     eleph
    0.72
     pione
    0.71
    akings
    0.69
    âķIJâķIJ
    0.69
     srf
    0.69
    xual
    0.69
     bay
    0.67
    ortunately
    0.66
    abases
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.