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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.82
    asking
    -0.82
    rophe
    -0.72
    ilitary
    -0.71
    locks
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    luaj
    -0.63
    ONEY
    -0.62
     Flavoring
    -0.62
     quotas
    -0.62
    POSITIVE LOGITS
     otherwise
    0.85
     Archive
    0.66
    essed
    0.66
     Archives
    0.65
     embodiment
    0.64
    odic
    0.61
    ction
    0.60
     Goodwin
    0.60
    upt
    0.59
    ½
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.