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

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "sub" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leon
    -0.18
    ario
    -0.18
    ouz
    -0.17
    ions
    -0.16
    iero
    -0.15
    icias
    -0.15
     Mell
    -0.15
    ÑĢиÑĦ
    -0.14
    inking
    -0.14
    ycl
    -0.14
    POSITIVE LOGITS
    -Saharan
    0.22
    (Sub
    0.20
    =sub
    0.20
    mers
    0.19
    (sub
    0.18
    [sub
    0.18
    andard
    0.18
    tember
    0.17
    -sub
    0.17
     Rosa
    0.17
    Act Density 0.023%

    No Known Activations