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

    Neuronpedia

    INDEX
    Explanations

    percentage symbols and their associated numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doubtnut
    -1.18
     myſelf
    -1.11
     ―――――
    -1.10
     Theſe
    -1.09
     faſt
    -1.07
     itſelf
    -1.04
     themſelves
    -1.00
     Monfieur
    -1.00
     raiſ
    -0.99
     uſed
    -0.97
    POSITIVE LOGITS
     %
    2.50
     \%
    1.39
     %,
    1.31
     %)
    1.30
     %),
    1.11
     %.
    1.11
     $\%$
    1.09
     (%
    1.06
     "%
    1.06
     %(
    1.06
    Act Density 0.059%

    No Known Activations