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

    Neuronpedia

    INDEX
    Explanations

    ranges of values or quantities

    oai_token-act-pair · gpt-3.5-turbo

    terms that denote a continuous spectrum or variation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verse
    -0.69
    jiang
    -0.68
    mit
    -0.64
    orc
    -0.63
     syndrome
    -0.62
    oliath
    -0.61
    elta
    -0.61
    æµ
    -0.61
     root
    -0.60
     reason
    -0.60
    POSITIVE LOGITS
    ogyn
    0.82
    finder
    0.79
    range
    0.78
    ranging
    0.78
     Emin
    0.74
     ranging
    0.73
     ranges
    0.71
    anges
    0.70
     Luxem
    0.68
    Ĥª
    0.67
    Act Density 0.017%

    No Known Activations