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

    Neuronpedia

    INDEX
    Explanations

    references to religious themes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lyre
    -0.90
     onPage
    -0.84
     miliki
    -0.82
     dė
    -0.82
     définiti
    -0.81
    lehnt
    -0.80
     argint
    -0.80
    writeField
    -0.79
     lemmas
    -0.76
    typeparam
    -0.75
    POSITIVE LOGITS
    ness
    1.59
    NESS
    1.03
    IOUS
    0.93
    acious
    0.87
    lious
    0.85
    0.81
    s
    0.81
    いる
    0.80
    rious
    0.80
    ious
    0.79
    Act Density 0.167%

    No Known Activations