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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "plate" and related terms or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.90
     onCancelled
    -0.86
     useRef
    -0.84
    OrNil
    -0.77
    lihood
    -0.76
    ]))
    -0.76
     مؤرشف
    -0.75
    ']?>
    -0.74
    ']));
    -0.74
    -0.73
    POSITIVE LOGITS
     plates
    1.88
     Plates
    1.80
     Plate
    1.69
    Plates
    1.68
     plate
    1.66
     PLATE
    1.59
     PLATES
    1.58
    Plate
    1.57
    plate
    1.53
    plates
    1.52
    Act Density 0.037%

    No Known Activations