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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical derivatives and differentiation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nya
    -0.10
    een
    -0.09
    atics
    -0.09
    سÙĪب
    -0.08
    eer
    -0.08
    енд
    -0.08
    ness
    -0.08
    akeup
    -0.08
    ëłĩ
    -0.08
    surf
    -0.08
    POSITIVE LOGITS
    over
    0.07
    atives
    0.07
    ief
    0.06
    of
    0.06
    å¢
    0.06
    -of
    0.06
    ivative
    0.06
    /add
    0.06
    aint
    0.06
     har
    0.06
    Act Density 0.008%

    No Known Activations