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

    Neuronpedia

    INDEX
    Explanations

    URLs with hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    the article 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orlando
    -0.70
    lasses
    -0.66
     Everton
    -0.66
    mie
    -0.66
     Irving
    -0.65
     Angus
    -0.65
    chart
    -0.64
     Fowler
    -0.64
     Erie
    -0.63
    lines
    -0.62
    POSITIVE LOGITS
    usterity
    1.56
    esthetic
    1.06
    irst
    1.04
    cknow
    0.95
    ird
    0.89
    ctors
    0.89
     few
    0.86
     couple
    0.84
    verages
    0.84
    chieve
    0.84
    Act Density 0.132%

    No Known Activations