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

    Neuronpedia

    INDEX
    Explanations

    the preposition "de" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -0.95
     itſelf
    -0.87
     raiſ
    -0.85
     ―――――
    -0.79
     himſelf
    -0.76
     ་་
    -0.76
     purpoſe
    -0.74
     uſed
    -0.73
     becauſe
    -0.72
     Hift
    -0.71
    POSITIVE LOGITS
     de
    0.89
    indd
    0.87
     the
    0.87
    Σε
    0.87
     a
    0.82
    Về
    0.77
    PositiveButton
    0.75
    بوابة
    0.75
     către
    0.74
    []>(
    0.73
    Act Density 0.021%

    No Known Activations