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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Poetry
    0.39
     geese
    0.39
    琇
    0.39
    자동
    0.38
     excitedly
    0.38
     ராஜா
    0.38
     priest
    0.37
     मैन
    0.37
     Acids
    0.37
     peep
    0.37
    POSITIVE LOGITS
     mercenary
    1.84
     mercenaries
    1.84
     merc
    1.63
     hired
    1.51
     Merc
    1.48
    Merc
    1.48
     hire
    1.30
    傭
    1.30
     MERC
    1.20
     hires
    1.17
    Act Density 0.013%

    No Known Activations