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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "de" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.98
     Anſ
    -0.97
     raiſ
    -0.96
     himſelf
    -0.88
     becauſe
    -0.85
     uſed
    -0.84
     purpoſe
    -0.83
     ―――――
    -0.82
     iſt
    -0.81
     Majefty
    -0.81
    POSITIVE LOGITS
     de
    1.19
     De
    1.11
    Σε
    0.96
    De
    0.95
     DE
    0.94
     the
    0.90
    Về
    0.88
    indd
    0.82
     a
    0.80
    ナの
    0.80
    Act Density 0.028%

    No Known Activations