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

    Neuronpedia

    INDEX
    Explanations

    prepositions, particularly the word “de” in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -0.88
     raiſ
    -0.83
     itſelf
    -0.79
     ―――――
    -0.75
     purpoſe
    -0.73
     Majefty
    -0.72
     Asturias
    -0.72
     Kanna
    -0.72
     himſelf
    -0.71
     iſt
    -0.71
    POSITIVE LOGITS
     de
    1.18
     De
    1.07
    Σε
    0.95
    De
    0.94
     DE
    0.92
    indd
    0.92
     the
    0.89
    員の
    0.84
    بوابة
    0.84
     DeV
    0.83
    Act Density 0.027%

    No Known Activations