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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions used in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -1.01
     beginnetje
    -0.91
     Мексичка
    -0.81
    InstrumentedTest
    -0.80
    Rüyada
    -0.80
    colgroup
    -0.79
    دانشنامهٔ
    -0.78
    transQ
    -0.76
    prüche
    -0.76
    astéro
    -0.76
    POSITIVE LOGITS
     example
    0.73
     examples
    0.72
     przykład
    0.67
     esempio
    0.65
     exemples
    0.64
     ejemplo
    0.61
     instance
    0.61
     exemple
    0.60
     ejemplos
    0.60
    examples
    0.59
    Act Density 0.219%

    No Known Activations