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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    empo
    -0.16
     både
    -0.15
    eki
    -0.15
    ems
    -0.15
    ">ÃĹ</
    -0.15
    аниÑĨ
    -0.15
    太éĥİ
    -0.14
    urve
    -0.14
    ylon
    -0.14
    опÑĢоÑģ
    -0.14
    POSITIVE LOGITS
    /or
    0.34
    phans
    0.30
    ifice
    0.28
    lando
    0.24
    acular
    0.24
    许
    0.23
     else
    0.22
    naments
    0.22
    phan
    0.22
     indeed
    0.20
    Act Density 0.273%

    No Known Activations