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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical data and sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eg
    -0.76
    obyl
    -0.76
    riage
    -0.67
    otin
    -0.64
    affe
    -0.62
    ãĤ¨ãĥ«
    -0.61
    estern
    -0.61
    igmat
    -0.60
    apons
    -0.60
    IFT
    -0.58
    POSITIVE LOGITS
     sources
    0.90
    SOURCE
    0.80
    Rank
    0.70
    Sources
    0.66
     Reuters
    0.66
     WS
    0.65
     anecd
    0.63
     estimates
    0.63
    patrick
    0.62
    source
    0.62
    Act Density 0.043%

    No Known Activations