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

    Neuronpedia

    INDEX
    Explanations

    titles of sections within an article or study

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Assista
    -0.92
    Obrigada
    -0.87
    Abraços
    -0.85
    Abraço
    -0.83
    اقرأ
    -0.81
    Todavía
    -0.80
    Conheça
    -0.80
    Ambos
    -0.79
    Opinión
    -0.79
    Curiosidades
    -0.78
    POSITIVE LOGITS
     increa
    1.62
     encomp
    1.61
     maneu
    1.56
     depic
    1.55
     reluct
    1.51
     guarante
    1.51
     suscep
    1.51
     impra
    1.49
     attemp
    1.46
     wherea
    1.46
    Act Density 0.270%

    No Known Activations