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

    Neuronpedia

    INDEX
    Explanations

    programming terminology and structure in the context of coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -0.78
    ſelf
    -0.73
     ſind
    -0.68
     iſt
    -0.68
    __*/
    -0.65
    []
    -0.65
     ſte
    -0.64
    [];
    -0.63
     queſta
    -0.63
    ']->
    -0.63
    POSITIVE LOGITS
     =
    1.86
    =
    1.13
     $=$
    1.03
     $=
    0.93
     =
    0.91
     $=\
    0.89
     =\
    0.86
     = 
    0.81
     =$
    0.79
    }=
    0.79
    Act Density 1.063%

    No Known Activations