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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating high-quality service or positive evaluations of businesses

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

    Preceding positive customer service reviews

    np_acts-logits-general · gemini-2.0-flash

    friendly customer, hot cup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ldorf
    -0.63
    momix
    -0.60
    AddTagHelper
    -0.60
     Италијани
    -0.57
    Datuak
    -0.56
    protoimpl
    -0.56
    styleType
    -0.56
    AutoField
    -0.55
    tagHelperRunner
    -0.55
     portanto
    -0.54
    POSITIVE LOGITS
    Always
    0.73
     customer
    0.69
    Friendly
    0.68
     friendly
    0.68
     always
    0.68
     rapides
    0.67
     Always
    0.67
     Friendly
    0.67
    Customer
    0.64
     courteous
    0.63
    Act Density 0.040%

    No Known Activations