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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions of experiences, particularly in customer service or product interactions

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

    Preceding words that indicate quality or skill

    np_acts-logits-general · gemini-2.0-flash

    audit quality or transparency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lardır
    -0.52
     folly
    -0.51
     rospy
    -0.48
     allora
    -0.47
    thalten
    -0.46
     infamous
    -0.46
     indiscriminate
    -0.45
     DialogInterface
    -0.45
    aturing
    -0.45
     mapStateToProps
    -0.45
    POSITIVE LOGITS
     excellent
    0.94
     excellently
    0.94
     nicely
    0.94
    excellent
    0.83
     Excellent
    0.79
    Excellent
    0.79
     wonderfully
    0.78
     thoughtfully
    0.76
     excelente
    0.73
     wonderful
    0.72
    Act Density 0.182%

    No Known Activations