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

    Neuronpedia

    INDEX
    Explanations

    terms related to approximation and estimation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emma
    -0.17
    resi
    -0.16
    ieu
    -0.16
    duck
    -0.15
    ëĭ¹
    -0.15
    ãģĨãģ¡
    -0.15
    opal
    -0.15
    strand
    -0.14
    hle
    -0.14
    ixin
    -0.14
    POSITIVE LOGITS
    asley
    0.18
    corn
    0.15
    ongyang
    0.14
    /mock
    0.14
    ãĥ¡ãĥ³ãĥĪ
    0.14
    ynchronously
    0.14
    okud
    0.14
    ikip
    0.14
    spb
    0.14
     Riy
    0.14
    Act Density 0.019%

    No Known Activations