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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantity or frequency

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.02
     ujednoznacz
    -0.89
    клопе
    -0.85
    InSection
    -0.83
    expandindo
    -0.82
    Revenir
    -0.78
    AddTagHelper
    -0.77
    ultuous
    -0.76
    >{@
    -0.73
    öbb
    -0.73
    POSITIVE LOGITS
     methods
    0.53
    方式
    0.49
     method
    0.49
    ToBe
    0.48
    的方法
    0.48
     factors
    0.47
     Pies
    0.47
     способов
    0.46
     способы
    0.45
    گم
    0.45
    Act Density 0.032%

    No Known Activations