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

    Neuronpedia

    INDEX
    Explanations

    assertions and conclusions about significant findings or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kn
    -0.16
    ActionCreators
    -0.14
    illard
    -0.14
    ait
    -0.14
    rances
    -0.14
    lech
    -0.14
    sequ
    -0.14
    zet
    -0.13
     @{
    -0.13
    tar
    -0.13
    POSITIVE LOGITS
    ingen
    0.15
    Tro
    0.15
    idla
    0.15
     Tro
    0.14
    oner
    0.14
    ies
    0.14
    ilter
    0.14
    ]={↵
    0.14
    Conclusion
    0.14
    urate
    0.14
    Act Density 0.363%

    No Known Activations