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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and prepositions

    oai_token-act-pair · gemini-2.0-flash

    numerical terms and quantitative expressions

    np_token-act-pair-logits · gpt-4o-mini

    Experiencing or witnessing events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     has
    -0.59
     since
    -0.58
     have
    -0.55
     been
    -0.54
    since
    -0.50
     Since
    -0.49
    Since
    -0.48
    has
    -0.47
    wijl
    -0.45
     had
    -0.45
    POSITIVE LOGITS
     propOrder
    0.79
     Efq
    0.75
     Мексичка
    0.71
     dozens
    0.69
     hundreds
    0.67
    تقاوى
    0.66
    Thousands
    0.66
     rhestr
    0.66
    jacency
    0.65
    OGND
    0.65
    Act Density 7.132%

    No Known Activations