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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or dialogue in the text

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

    Comes before attribution (says, said, added)

    np_acts-logits-general · gemini-2.0-flash

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.81
    +#+#
    -0.81
     ExecuteAsync
    -0.80
    TestingModule
    -0.77
    EDEFAULT
    -0.77
     חיצוניים
    -0.76
     محفوظة
    -0.76
     defaultstate
    -0.74
    ftagPool
    -0.74
    GEBURTSDATUM
    -0.74
    POSITIVE LOGITS
     says
    0.49
    ongeza
    0.48
     lanjut
    0.48
     said
    0.46
    ennifer
    0.46
    ibid
    0.46
     assures
    0.45
     emphasize
    0.45
    elseif
    0.43
    另
    0.42
    Act Density 0.055%

    No Known Activations