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

    Neuronpedia

    INDEX
    Explanations

    phrases related to checking or verifying information

    oai_token-act-pair · gpt-3.5-turbo

    references to checking personal information or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    von
    -0.72
    rawdownloadcloneembedreportprint
    -0.66
    EStreamFrame
    -0.66
    ranged
    -0.63
    argument
    -0.62
    soever
    -0.61
    udeb
    -0.61
    <?
    -0.61
    ;;
    -0.60
    NetMessage
    -0.59
    POSITIVE LOGITS
     balances
    0.82
    atches
    0.73
     compatibility
    0.73
    worthiness
    0.73
     validity
    0.73
    balance
    0.71
    bones
    0.71
     boxes
    0.66
    geist
    0.66
     clearance
    0.65
    Act Density 0.096%

    No Known Activations