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

    Neuronpedia

    INDEX
    Explanations

    names of persons

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iku
    -0.93
    ector
    -0.78
    sha
    -0.73
    idth
    -0.68
    anka
    -0.64
    silver
    -0.62
    unes
    -0.62
    akery
    -0.62
    awar
    -0.60
    rets
    -0.60
    POSITIVE LOGITS
     More
    1.68
    more
    1.59
     more
    1.54
    More
    1.51
     less
    1.41
     Less
    1.36
     MORE
    1.36
     fewer
    1.30
    Less
    1.20
    MORE
    1.10
    Act Density 0.169%

    No Known Activations