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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research and technology

    oai_token-act-pair · gpt-3.5-turbo

    any text or segments that appear to be blank or contain minimal content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.96
    ß
    -0.87
     tremend
    -0.86
    ò
    -0.86
     oun
    -0.86
     occas
    -0.85
     newcom
    -0.85
     citiz
    -0.83
    aditional
    -0.82
     exting
    -0.78
    POSITIVE LOGITS
    ↵
    0.80
    Merit
    0.78
    PHOTOS
    0.75
    DragonMagazine
    0.74
    Grey
    0.70
    NPR
    0.69
    prem
    0.67
    00200000
    0.67
    SPONSORED
    0.67
    idable
    0.67
    Act Density 0.905%

    No Known Activations