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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical data and coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     of
    -0.67
     V
    -0.67
     du
    -0.64
     O
    -0.63
     II
    -0.62
     U
    -0.62
     E
    -0.62
     g
    -0.61
     C
    -0.61
    CLUDING
    -0.61
    POSITIVE LOGITS
     itſelf
    1.48
     purpoſe
    1.42
     greateſt
    1.41
     pleaſure
    1.33
     deſt
    1.30
     myſelf
    1.29
     ſmall
    1.28
     ſche
    1.28
     houſe
    1.28
     reaſon
    1.26
    Act Density 0.300%

    No Known Activations