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

    Neuronpedia

    INDEX
    Explanations

    events or incidents of intense action or conflict

    oai_token-act-pair · gpt-3.5-turbo

    events involving dramatic or disastrous outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amiliar
    -0.74
    EY
    -0.71
    Previous
    -0.69
     guiName
    -0.69
     Basics
    -0.67
    umeric
    -0.66
    é¾įå¥ij士
    -0.65
     Concepts
    -0.64
    earch
    -0.63
    FactoryReloaded
    -0.62
    POSITIVE LOGITS
    successfully
    1.30
     eventually
    1.29
     succeeded
    1.28
     survives
    1.28
     tragically
    1.27
     succeeds
    1.27
     ended
    1.27
     ultimately
    1.21
     survived
    1.17
     succumbed
    1.12
    Act Density 1.338%

    No Known Activations