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

    Neuronpedia

    INDEX
    Explanations

    capitalized acronyms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to technical or specialized concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.96
    atchewan
    -0.86
    enegger
    -0.85
    ãĥĩãĤ£
    -0.84
    odore
    -0.84
    tenance
    -0.84
    ItemTracker
    -0.84
    ãĤ±
    -0.84
    wagen
    -0.80
    doms
    -0.77
    POSITIVE LOGITS
    BC
    0.99
    FR
    0.98
    TF
    0.97
    PS
    0.96
    BI
    0.93
    FP
    0.92
    SP
    0.90
    BM
    0.90
    IM
    0.89
    RS
    0.88
    Act Density 0.107%

    No Known Activations