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

    Neuronpedia

    INDEX
    Explanations

    CSS styling properties and their corresponding values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.79
     ویکی‌پدیا
    -0.61
     
    -0.61
     $
    -0.58
    <eos>
    -0.57
    (
    -0.56
    }}}{
    -0.55
    +#+
    -0.53
    ']").
    -0.53
     to
    -0.51
    POSITIVE LOGITS
     pleaſure
    0.88
     myſelf
    0.84
     ſeveral
    0.82
     itſelf
    0.79
     tfsi
    0.74
     dafs
    0.73
     ་་
    0.72
     ſmall
    0.71
     ſever
    0.71
     greateſt
    0.70
    Act Density 0.112%

    No Known Activations