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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.14
     Raq
    -0.14
    ocache
    -0.14
    ãģŁãĤī
    -0.13
    hape
    -0.13
     Boutique
    -0.13
    -alist
    -0.13
    èģĺ
    -0.13
    une
    -0.13
    inder
    -0.13
    POSITIVE LOGITS
    çļĦæĺ¯
    0.20
     ones
    0.20
     something
    0.20
     either
    0.20
    either
    0.17
    eed
    0.15
    something
    0.15
     Either
    0.15
     simply
    0.14
    aki
    0.14
    Act Density 0.176%

    No Known Activations