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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stole
    1.02
     hugged
    1.00
     propagand
    0.95
     parlato
    0.95
     pointer
    0.92
     cocoa
    0.92
    ora
    0.90
     sniff
    0.89
     assassination
    0.89
     nepot
    0.89
    POSITIVE LOGITS
     окра
    1.11
    ിലുള്ള
    1.06
    停车场
    1.02
    改装
    1.02
    焊接
    1.02
    inuation
    1.00
    ിലും
    0.99
    加工
    0.99
    дая
    0.97
     позд
    0.96
    Act Density 0.278%

    No Known Activations