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

    Neuronpedia

    INDEX
    Explanations

    statements that express personal opinions and beliefs

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

    I think/believe personal opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.60
     Administrativna
    -0.56
     ſche
    -0.52
     Reſ
    -0.52
    GOTREF
    -0.52
     Diſ
    -0.52
     Eſ
    -0.52
     noDo
    -0.51
     gonzález
    -0.51
     HFILL
    -0.49
    POSITIVE LOGITS
     ouder
    0.40
     arrivato
    0.38
    addGap
    0.37
    Coordonnées
    0.36
    trong
    0.36
     аргу
    0.35
    Попис
    0.35
    awtextra
    0.34
     montanha
    0.34
    Args
    0.34
    Act Density 0.038%

    No Known Activations