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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion or subjective statements

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

    of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fug
    -0.38
    IntoConstraints
    -0.38
     Chill
    -0.38
     Arrondissement
    -0.36
    Adrian
    -0.36
    ged
    -0.36
    Fug
    -0.35
     propOrder
    -0.35
    dog
    -0.35
    iney
    -0.35
    POSITIVE LOGITS
    følgelig
    0.85
     natuurlijk
    0.84
     natürlich
    0.83
     Natürlich
    0.83
     oczywiście
    0.76
     naturalmente
    0.71
     évidemment
    0.69
    Natürlich
    0.69
    verständlich
    0.68
     naturligt
    0.68
    Act Density 0.049%

    No Known Activations