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

    Neuronpedia

    INDEX
    Explanations

    references to functions in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.17
     Jefus
    -1.11
     themſelves
    -1.09
     poffible
    -1.08
     faſt
    -1.04
     ſmall
    -1.02
     Monfieur
    -1.02
     himſelf
    -1.01
     ſtate
    -1.00
     ſtand
    -0.99
    POSITIVE LOGITS
     function
    1.67
     functions
    1.65
     Function
    1.56
    Function
    1.51
    functions
    1.50
    function
    1.45
     Functions
    1.40
    FUNCTION
    1.37
    Functions
    1.34
     FUNCTION
    1.32
    Act Density 0.106%

    No Known Activations