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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain connective words within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pattes
    -0.51
    /*
    -0.46
     sifat
    -0.45
    /**
    -0.45
     ejus
    -0.44
     menores
    -0.44
     eius
    -0.43
     yıld
    -0.43
     sebe
    -0.43
     neden
    -0.43
    POSITIVE LOGITS
     Мексичка
    1.23
    aarrggbb
    0.96
     Савезне
    0.91
    цездатний
    0.89
    évaluateur
    0.89
     चीज़ों
    0.87
     transfieras
    0.87
    تقاوى
    0.87
    ^(@)
    0.80
     الدولى
    0.80
    Act Density 0.446%

    No Known Activations