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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political candidates and elections

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

    Relative pronouns (which, that, whose, where)

    np_acts-logits-general · gemini-2.0-flash

    relative clauses and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.71
    adpleegd
    -0.69
    parsedMessage
    -0.68
     Drapeau
    -0.66
    adaptiveStyles
    -0.64
     Paglinawan
    -0.63
    ensement
    -0.63
    CppCodeGen
    -0.62
     disambiguazione
    -0.62
    цездатний
    -0.60
    POSITIVE LOGITS
     whose
    1.41
     that
    1.40
     who
    1.31
    whose
    1.08
     which
    1.06
     where
    1.00
     cuyo
    0.94
     cuya
    0.92
     cuyas
    0.91
     Whose
    0.91
    Act Density 0.709%

    No Known Activations