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

    Neuronpedia

    INDEX
    Explanations

    computer code syntax characters and specific string patterns

    oai_token-act-pair · gpt-3.5-turbo

    highly significant updates or information related to changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.66
    icter
    -0.64
    testers
    -0.63
     Kurd
    -0.63
     travellers
    -0.62
     spoilers
    -0.62
    holes
    -0.62
     partisans
    -0.61
     Tale
    -0.61
    furt
    -0.58
    POSITIVE LOGITS
    DOC
    0.75
    Fax
    0.74
    atu
    0.68
    ohyd
    0.67
    ulous
    0.65
    ADVERTISEMENT
    0.65
    paralle
    0.63
    AMI
    0.63
    ãĥ´
    0.62
    OAD
    0.62
    Act Density 0.000%

    No Known Activations