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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to etiquette and manners

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

    etiquette

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _-
    -0.48
     nahilalakip
    -0.45
    Hentet
    -0.42
     mères
    -0.41
     jonka
    -0.40
     véhicules
    -0.39
     journaux
    -0.38
     nôtre
    -0.38
     насељу
    -0.37
     navires
    -0.37
    POSITIVE LOGITS
     Etiquette
    1.57
     etiquette
    1.47
    Eti
    1.06
     Eti
    0.89
    eti
    0.88
     ETI
    0.86
     eti
    0.82
     manners
    0.81
    quette
    0.79
    quettes
    0.76
    Act Density 0.010%

    No Known Activations