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

    Neuronpedia

    INDEX
    Explanations

    negations or instances of the prefix "de-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.18
    WillAppear
    -1.01
    BufferException
    -0.98
     iſt
    -0.96
     Anſ
    -0.94
     Beſ
    -0.93
     ainfi
    -0.89
    +#+#
    -0.88
     myſelf
    -0.87
    ScopeManager
    -0.87
    POSITIVE LOGITS
     de
    2.72
     De
    2.28
    De
    2.22
    de
    1.95
     DE
    1.87
    DE
    1.62
     де
    1.58
    デ
    1.20
    Де
    1.04
     Де
    1.04
    Act Density 0.082%

    No Known Activations