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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts in quantitative metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     as
    -0.35
     als
    -0.25
     sebagai
    -0.22
     как
    -0.21
     jako
    -0.19
    ä½ľä¸º
    -0.18
    为
    -0.18
     ÏīÏĤ
    -0.17
    	as
    -0.17
     Ñıк
    -0.16
    POSITIVE LOGITS
    qrt
    0.16
    linky
    0.14
    937
    0.14
    errupted
    0.14
    oggler
    0.13
    ezier
    0.13
     melhores
    0.13
    볤
    0.13
    erval
    0.13
     köln
    0.13
    Act Density 0.115%

    No Known Activations