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

    Neuronpedia

    INDEX
    Explanations

    acknowledgments of individuals' contributions in the context of gratitude or recognition

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    Alex
    -0.71
     Alex
    -0.70
    +#+#
    -0.70
     Emily
    -0.70
     wireType
    -0.67
     MainAxisSize
    -0.67
     Kate
    -0.66
    Kate
    -0.65
     Julia
    -0.64
    Emily
    -0.64
    POSITIVE LOGITS
     Debbie
    1.28
    Debbie
    1.20
    Deborah
    1.04
     Deborah
    1.02
     Marilyn
    1.02
     Brenda
    1.02
     Debra
    0.98
     Judy
    0.97
     Phyllis
    0.96
    Brenda
    0.96
    Act Density 0.011%

    No Known Activations