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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mpire
    -0.78
    aminer
    -0.75
     Chronicle
    -0.72
     Doomsday
    -0.71
    ause
    -0.71
    rolog
    -0.71
     Chiefs
    -0.68
    ordon
    -0.68
    rant
    -0.66
    rogen
    -0.66
    POSITIVE LOGITS
    theless
    0.83
    bye
    0.73
    monitor
    0.69
    âĵĺ
    0.69
     rigging
    0.69
    \">
    0.66
     monitors
    0.65
    ogyn
    0.63
     accur
    0.63
    successfully
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.