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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of a majority in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lement
    -0.17
    oom
    -0.17
    bert
    -0.16
    nore
    -0.16
    ittel
    -0.16
    eling
    -0.15
    rais
    -0.14
    ÅĻe
    -0.14
    enz
    -0.14
    oth
    -0.14
    POSITIVE LOGITS
    aires
    0.17
    utilus
    0.17
    ảo
    0.16
    ringe
    0.15
    phans
    0.15
     Tut
    0.15
    .tc
    0.14
     Erd
    0.14
    alaxy
    0.14
    cul
    0.14
    Act Density 0.016%

    No Known Activations