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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns and their associated references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.48
     ModelRenderer
    -0.47
     feroit
    -0.42
     auroit
    -0.42
    平民
    -0.41
     ExecuteAsync
    -0.41
     సౌకర్య
    -0.41
     ferons
    -0.41
     getAge
    -0.40
     vial
    -0.40
    POSITIVE LOGITS
     therefore
    0.56
    Havolalar
    0.54
     consequently
    0.52
     hence
    0.50
     hatta
    0.48
     especially
    0.48
     hlavně
    0.47
     others
    0.46
     consequent
    0.46
    อื่น
    0.44
    Act Density 0.820%

    No Known Activations