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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "de."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.50
     Theſe
    -1.48
     Monfieur
    -1.47
     Anſ
    -1.43
     itſelf
    -1.41
     themſelves
    -1.40
     pleaſure
    -1.36
     ſeveral
    -1.35
     himſelf
    -1.35
     cauſe
    -1.34
    POSITIVE LOGITS
     de
    3.75
     De
    2.53
    De
    2.16
     DE
    1.77
    de
    1.64
     де
    1.58
     des
    1.39
     del
    1.37
     di
    1.26
     du
    1.18
    Act Density 0.068%

    No Known Activations