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

    Neuronpedia

    INDEX
    Explanations

    concepts related to correctness and propriety in reasoning or judgments

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

    appropriateness, correctness, or propriety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最快更新
    -0.48
     tartalomajánló
    -0.47
     ivelany
    -0.44
     gyhoeddwyd
    -0.42
     محفوظة
    -0.42
    verwijspagina
    -0.40
    IsContent
    -0.40
     autorytatywna
    -0.40
     dirait
    -0.39
     PeEnEo
    -0.39
    POSITIVE LOGITS
     appropriateness
    0.57
    มาะ
    0.48
    antwoorden
    0.46
     propriety
    0.45
     inappropriate
    0.42
    妥
    0.41
     legitimacy
    0.40
    不对
    0.40
    mità
    0.40
     correctness
    0.39
    Act Density 0.370%

    No Known Activations