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

    Neuronpedia

    INDEX
    Explanations

    notation related to graphs and mathematical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warzys
    -0.41
    łaj
    -0.41
    脚注の使い方
    -0.39
    paramref
    -0.39
     فريبيس
    -0.38
     fact
    -0.36
     orilla
    -0.36
    principalColumn
    -0.36
     Römer
    -0.36
    enderror
    -0.35
    POSITIVE LOGITS
     G
    2.23
    G
    2.03
    Ｇ
    1.55
     g
    1.27
     Gs
    1.14
     Г
    1.14
    Gs
    1.06
     GG
    1.05
    Г
    0.99
    𝐺
    0.99
    Act Density 0.372%

    No Known Activations