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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving parentheses and nested operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     la
    -0.64
     or
    -0.61
     do
    -0.60
     Paul
    -0.58
     a
    -0.57
     and
    -0.57
     by
    -0.57
     is
    -0.57
     out
    -0.56
     \
    -0.56
    POSITIVE LOGITS
     Monfieur
    1.18
     raiſ
    1.17
     pleaſure
    1.12
     Majefty
    1.11
     greateſt
    1.10
     ſmall
    1.07
    (((
    1.07
     Anſ
    1.07
     houſe
    1.06
     myſelf
    1.05
    Act Density 0.133%

    No Known Activations