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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    axter
    -0.82
    etsy
    -0.74
    dit
    -0.69
    Ware
    -0.68
    ebin
    -0.68
    ocking
    -0.65
    rig
    -0.64
    iver
    -0.64
    ayne
    -0.63
    onne
    -0.62
    POSITIVE LOGITS
     DEFENSE
    0.67
    iannopoulos
    0.66
     Kosovo
    0.65
    ufact
    0.65
    pan
    0.64
    ctors
    0.64
    abs
    0.64
     Slovenia
    0.63
     Mecca
    0.63
     Warsaw
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.