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

    Neuronpedia

    INDEX
    Explanations

    definite articles and possessive pronouns

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

    adjectives following determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     busto
    -0.49
     orale
    -0.48
    Sainte
    -0.46
     tige
    -0.46
    添
    -0.45
     initComponents
    -0.44
     Wund
    -0.42
     Creature
    -0.42
     GenerationType
    -0.42
    Civil
    -0.41
    POSITIVE LOGITS
    MarshalTo
    0.44
    lapsingToolbar
    0.43
    requireNonNull
    0.43
     noisy
    0.43
    IntoConstraints
    0.42
    脚注の使い方
    0.41
    RegressionTest
    0.41
    ftagPool
    0.41
     increasingly
    0.41
     highly
    0.39
    Act Density 0.061%

    No Known Activations