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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terms and concepts related to biology and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -1.01
     greateſt
    -0.97
     leaſt
    -0.94
     myſelf
    -0.89
     ſeveral
    -0.88
     ſmall
    -0.87
    ſelves
    -0.87
     ſou
    -0.87
    ſelf
    -0.86
     ſte
    -0.86
    POSITIVE LOGITS
    .
    0.57
    ,
    0.53
     at
    0.48
     la
    0.43
    WHEREAS
    0.43
    令
    0.43
     (
    0.43
     est
    0.42
     y
    0.42
    emptyList
    0.41
    Act Density 1.469%

    No Known Activations