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

    Neuronpedia

    INDEX
    Explanations

    first-person and third-person plural pronouns

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

    pronoun followed by auxiliary verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.57
    RenderAtEndOf
    -0.54
     ویکی‌پدی
    -0.54
    InSection
    -0.52
    NewUrlParser
    -0.52
    :✨
    -0.51
     Roskov
    -0.50
     <<<<<<<<<<<<<<
    -0.48
    henswürdigkeiten
    -0.47
     Photocase
    -0.47
    POSITIVE LOGITS
     sumpay
    0.44
    datable
    0.40
     astore
    0.35
     ISTAT
    0.33
     mismos
    0.33
     outlines
    0.33
    достатки
    0.33
    ?...
    0.32
     eft
    0.31
     mismas
    0.31
    Act Density 0.212%

    No Known Activations