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

    Neuronpedia

    INDEX
    Explanations

    keywords related to software functionality or compatibility

    oai_token-act-pair · gpt-3.5-turbo

    references to the functionality and operational status of software or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilings
    -0.76
    ultural
    -0.73
    rition
    -0.71
     Flavoring
    -0.71
    ulture
    -0.66
    RIC
    -0.65
    gart
    -0.63
    laus
    -0.62
     Jed
    -0.61
    osure
    -0.61
    POSITIVE LOGITS
    bench
    1.09
    heet
    1.04
    flows
    0.99
    paces
    0.96
     reliably
    0.92
     seamlessly
    0.90
     flaw
    0.90
    place
    0.89
     offline
    0.85
     correctly
    0.85
    Act Density 0.059%

    No Known Activations