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

    Neuronpedia

    INDEX
    Explanations

    words appearing in a list or enumeration

    oai_token-act-pair · gemini-2.0-flash

    multi-language tokens or mixed language content

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

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.87
    ,
    -0.79
    .
    -0.75
    '
    -0.73
    1
    -0.69
     -
    -0.68
    -
    -0.68
    3
    -0.68
    ’
    -0.67
     (
    -0.66
    POSITIVE LOGITS
    IntoConstraints
    1.62
    expandindo
    1.46
     виправивши
    1.43
     tartalomajánló
    1.42
     itſelf
    1.41
     Theſe
    1.41
     متعلقه
    1.40
    脚注の使い方
    1.37
     المعيارى
    1.36
     Мексичка
    1.32
    Act Density 8.181%

    No Known Activations