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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics and measurements related to performance or production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    каÑģ
    -0.07
    zell
    -0.07
    vyk
    -0.07
    owell
    -0.07
    ä¹ħ
    -0.07
    kest
    -0.07
    isku
    -0.07
    пÑĢ
    -0.07
    icorn
    -0.06
    egal
    -0.06
    POSITIVE LOGITS
     compared
    0.09
     than
    0.07
    auen
    0.07
     per
    0.06
    ann
    0.06
     Convention
    0.06
    en
    0.06
     doubles
    0.06
    å°ĭ
    0.06
     fragment
    0.06
    Act Density 0.027%

    No Known Activations