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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we," indicating a focus on collective authorship or perspective

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.71
    дём
    -0.54
    mos
    -0.53
    sik
    -0.52
    chka
    -0.52
    pes
    -0.51
     pem
    -0.51
     complementary
    -0.51
     laten
    -0.50
    чё
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.77
    antaranya
    0.75
     vPvB
    0.75
     raiſ
    0.74
    χρι
    0.72
    IndentedString
    0.71
     Huguen
    0.71
     EconPapers
    0.70
    unnitel
    0.69
     betweenstory
    0.69
    Act Density 0.046%

    No Known Activations