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

    Neuronpedia

    INDEX
    Explanations

    references to functions and their definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.12
     Jefus
    -1.08
     poffible
    -1.05
     themſelves
    -1.02
     Monfieur
    -1.01
     faſt
    -1.00
     doubtnut
    -0.99
     chré
    -0.98
     ſmall
    -0.98
     ſtate
    -0.98
    POSITIVE LOGITS
     functions
    1.58
     function
    1.53
     Function
    1.45
    functions
    1.44
    Function
    1.36
    function
    1.34
     Functions
    1.34
    Functions
    1.29
    FUNCTION
    1.29
     FUNCTION
    1.24
    Act Density 0.098%

    No Known Activations