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

    Neuronpedia

    INDEX
    Explanations

    instances of strong sentiment or emotional expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ########.
    -0.47
    めない
    -0.47
     vPvB
    -0.47
    หาย
    -0.46
    тистика
    -0.46
    ,”
    -0.44
    natured
    -0.44
    ↵↵
    -0.44
     Lively
    -0.44
    емости
    -0.43
    POSITIVE LOGITS
     createStore
    0.70
    UnusedPrivate
    0.69
    inį
    0.66
    ServletException
    0.66
     externi
    0.64
    AdapterFactory
    0.63
     Theſe
    0.63
    Expedia
    0.63
    HtmlAttribute
    0.63
    曖昧さ回避
    0.62
    Act Density 0.010%

    No Known Activations