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

    Neuronpedia

    INDEX
    Explanations

    numeric and symbolic elements related to data structures or code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.57
     caneca
    -0.50
     تضيفلها
    -0.48
     IconData
    -0.47
     Walkover
    -0.47
     biała
    -0.47
     christlichen
    -0.46
     białe
    -0.46
    SBATCH
    -0.44
     casada
    -0.44
    POSITIVE LOGITS
     referrerpolicy
    0.43
    inos
    0.42
     preferências
    0.41
     curs
    0.41
     tute
    0.40
     erb
    0.39
    şört
    0.39
     BLOCK
    0.39
     encore
    0.39
     tail
    0.39
    Act Density 0.405%

    No Known Activations