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

    Neuronpedia

    INDEX
    Explanations

    terms related to redeployment and certain physical conditions like sickness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to employment and redeployment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akira
    -0.73
     sway
    -0.71
    +++
    -0.68
     bowl
    -0.68
     Metatron
    -0.68
     bowls
    -0.64
     textbooks
    -0.62
    UA
    -0.62
     antic
    -0.62
     FP
    -0.62
    POSITIVE LOGITS
    ploy
    4.87
    velop
    1.86
    vironment
    1.23
    cember
    1.23
    bris
    1.19
    burse
    1.17
    ufact
    1.14
    pread
    1.10
    emed
    1.09
    ppelin
    1.07
    Act Density 0.035%

    No Known Activations