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

    Neuronpedia

    INDEX
    Explanations

    references to contribution and authorship in research documents

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

    Writing and drafting manuscripts

    np_acts-logits-general · gemini-2.0-flash

    drafting and writing manuscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     empreg
    -0.35
    Duración
    -0.35
     תע
    -0.35
    occasione
    -0.34
     employed
    -0.34
     alkalmaz
    -0.33
    DispatchToProps
    -0.32
     nadzieję
    -0.31
    ouvre
    -0.31
     saluti
    -0.31
    POSITIVE LOGITS
     draft
    1.70
     drafts
    1.40
    draft
    1.37
     Draft
    1.34
     preliminary
    1.30
    Draft
    1.28
     DRAFT
    1.27
    DRAFT
    1.16
     drafted
    1.09
     rough
    1.09
    Act Density 0.700%

    No Known Activations