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

    Neuronpedia

    INDEX
    Explanations

    references to academic submissions and proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ny
    -0.17
    intro
    -0.16
     Intro
    -0.15
    rek
    -0.15
    fb
    -0.15
    Intro
    -0.15
    -errors
    -0.15
    alı
    -0.15
    ãĤ¤
    -0.15
    mont
    -0.14
    POSITIVE LOGITS
    eeper
    0.16
    аниÑĨ
    0.15
    acock
    0.14
    γκα
    0.14
    Sizer
    0.14
    UGIN
    0.14
     eens
    0.14
    æŁ»
    0.14
    лÑĥб
    0.14
    esa
    0.14
    Act Density 0.022%

    No Known Activations