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

    Neuronpedia

    INDEX
    Explanations

    references to noble individuals and titles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    wn
    -0.66
     Francine
    -0.66
    >);
    -0.64
     trock
    -0.63
     dvo
    -0.63
    bnf
    -0.60
    n
    -0.60
     Martinez
    -0.60
     Healy
    -0.60
     Staates
    -0.59
    POSITIVE LOGITS
     Noble
    1.44
    Noble
    1.43
     Nobel
    1.28
     Nobles
    1.27
     nobles
    1.26
     noble
    1.22
    Nobel
    1.21
     nobility
    1.18
    noble
    1.10
     nobler
    1.07
    Act Density 0.004%

    No Known Activations