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

    Neuronpedia

    INDEX
    Explanations

    references to percentages and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.22
     itſelf
    -1.13
     faſt
    -1.08
     Monfieur
    -1.08
     Jefus
    -1.06
     myſelf
    -1.05
     raiſ
    -1.04
     doubtnut
    -1.04
     Anſ
    -1.03
     pleaſure
    -0.99
    POSITIVE LOGITS
    %
    1.01
     %
    0.77
    \%
    0.73
    IMPORTED
    0.70
     \%$
    0.69
     
    0.67
     \
    0.67
     percent
    0.66
     "
    0.63
     "%
    0.62
    Act Density 0.047%

    No Known Activations