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

    Neuronpedia

    INDEX
    Explanations

    sentences with temporal references

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive experiences or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Publisher
    -0.60
    lihood
    -0.59
     trademarks
    -0.53
    ãĤ¨ãĥ«
    -0.52
     acronym
    -0.50
     recy
    -0.48
     fid
    -0.48
    ourgeois
    -0.47
    advertisement
    -0.47
    hid
    -0.47
    POSITIVE LOGITS
    jri
    0.69
    cember
    0.65
    enium
    0.60
    isode
    0.59
    apse
    0.58
    sync
    0.58
     adolesc
    0.57
    idays
    0.57
    Reviewer
    0.56
    aye
    0.54
    Act Density 2.027%

    No Known Activations