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

    Neuronpedia

    INDEX
    Explanations

    numbers within a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numerical codes or identifiers related to specific events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iku
    -0.71
     Rica
    -0.70
    imaru
    -0.65
    igslist
    -0.63
    olean
    -0.63
     derog
    -0.63
    govtrack
    -0.62
     targ
    -0.61
    theless
    -0.61
     nudity
    -0.61
    POSITIVE LOGITS
    th
    1.05
    teenth
    1.05
     richest
    0.88
    %-
    0.86
    venth
    0.85
     largest
    0.85
    %"
    0.85
    ieth
    0.85
     Greatest
    0.82
     wealthiest
    0.79
    Act Density 0.137%

    No Known Activations