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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in positions of authority or societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.55
    Lago
    -0.52
    iland
    -0.52
    utical
    -0.50
    itored
    -0.50
    oppable
    -0.46
    é¾įå
    -0.46
    ourke
    -0.45
    ļé
    -0.45
    chuk
    -0.45
    POSITIVE LOGITS
    iest
    0.74
    liest
    0.70
    hest
    0.68
     portion
    0.61
    est
    0.52
     aspect
    0.52
     tremend
    0.51
     keyword
    0.51
     matchup
    0.50
    icter
    0.50
    Act Density 5.113%

    No Known Activations