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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific theme or topic

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific name references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sequence
    -0.72
    shop
    -0.68
    iop
    -0.64
    ingen
    -0.62
    omics
    -0.61
    result
    -0.61
    products
    -0.60
     Dynamo
    -0.60
     customs
    -0.60
     util
    -0.57
    POSITIVE LOGITS
    horn
    2.60
    adden
    1.46
    annie
    1.39
    Name
    1.36
    ا
    1.17
    hart
    0.91
    ername
    0.91
    acho
    0.91
    usky
    0.89
    baum
    0.86
    Act Density 0.034%

    No Known Activations