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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and contemplation

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

    well-being thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.77
    ſelves
    -0.72
     pleaſure
    -0.66
     ſta
    -0.65
     greateſt
    -0.65
     queſta
    -0.64
     Majefty
    -0.63
     ſtand
    -0.63
     ſche
    -0.63
     ſte
    -0.62
    POSITIVE LOGITS
    My
    0.43
     conclusão
    0.38
    Now
    0.38
    ViewImports
    0.37
     uyar
    0.34
     söyledi
    0.32
     encontrarse
    0.32
     rând
    0.32
     trouvez
    0.32
     pię
    0.32
    Act Density 0.013%

    No Known Activations