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

    Neuronpedia

    INDEX
    Explanations

    phrases related to publication and academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    published herein

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ESSMENT
    -0.38
     ATTOR
    -0.37
    uillez
    -0.35
     bumbu
    -0.33
     ajustar
    -0.32
     Olsson
    -0.32
     APPROACH
    -0.32
     Türen
    -0.32
    Referências
    -0.32
     attentes
    -0.32
    POSITIVE LOGITS
     publishing
    1.42
     publish
    1.39
     published
    1.37
    publish
    1.30
     Publish
    1.30
    Publishing
    1.28
     publication
    1.28
    published
    1.27
     Publishing
    1.26
    publishing
    1.25
    Act Density 0.068%

    No Known Activations