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

    Neuronpedia

    INDEX
    Explanations

    symbols and variables commonly used in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -3.06
     itſelf
    -2.94
     Efq
    -2.72
     Monfieur
    -2.64
     faſt
    -2.61
     raiſ
    -2.60
     ―――――
    -2.59
     pleaſure
    -2.57
     Theſe
    -2.56
     Jefus
    -2.51
    POSITIVE LOGITS
     $
    3.66
     $\
    2.50
    $
    2.02
     
    1.79
     "
    1.76
     ${
    1.73
     ($
    1.71
     $(
    1.71
    ($
    1.67
     '
    1.56
    Act Density 0.647%

    No Known Activations