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

    Neuronpedia

    INDEX
    Explanations

    official or formal statements or reports

    oai_token-act-pair · gpt-3.5-turbo

    formal documents and their references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ventus
    -0.73
    NetMessage
    -0.71
    ntil
    -0.68
    omething
    -0.66
    ãĤ¤ãĥĪ
    -0.65
     actionGroup
    -0.62
    imilar
    -0.60
     <=
    -0.60
    afety
    -0.60
     brill
    -0.60
    POSITIVE LOGITS
     reads
    0.99
     adds
    0.96
     cited
    0.95
     quoted
    0.92
     concludes
    0.91
     added
    0.91
     authors
    0.89
     notes
    0.86
     cites
    0.86
     says
    0.84
    Act Density 0.122%

    No Known Activations