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

    Neuronpedia

    INDEX
    Explanations

    concepts related to relationships and interactions among objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otu
    -0.06
    -valu
    -0.06
    alse
    -0.06
     fitte
    -0.06
    ooth
    -0.06
    andon
    -0.06
    okino
    -0.06
    _PRIVATE
    -0.06
    bao
    -0.06
    سبب
    -0.06
    POSITIVE LOGITS
     two
    0.14
    两个
    0.13
    two
    0.10
     двÑĥÑħ
    0.10
     две
    0.10
     два
    0.09
     deux
    0.09
    两
    0.09
     zwei
    0.09
    åħ©
    0.09
    Act Density 0.095%

    No Known Activations