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

    Neuronpedia

    INDEX
    Explanations

    the recurring presence of the word "et," indicating a focus on citations or references in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -0.86
     ſever
    -0.84
     tranſ
    -0.84
     purpoſe
    -0.82
     Conſ
    -0.82
     reaſon
    -0.81
     Anſ
    -0.80
     ſeveral
    -0.80
     diſt
    -0.79
     fevere
    -0.78
    POSITIVE LOGITS
     للمعارف
    1.14
     et
    1.12
     appelez
    0.88
    NOWLEDG
    0.82
     تانيه
    0.82
     AttributeSet
    0.79
     cetera
    0.76
     متعلقه
    0.75
     Архів
    0.74
    anyard
    0.73
    Act Density 0.058%

    No Known Activations