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

    Neuronpedia

    INDEX
    Explanations

    terms related to various aspects of a topic or subject

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to content and performance criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thouse
    -0.75
    arnaev
    -0.73
    riots
    -0.70
    enegger
    -0.67
    pired
    -0.64
    obin
    -0.62
    aily
    -0.61
    nee
    -0.60
    icon
    -0.59
    mire
    -0.59
    POSITIVE LOGITS
     etiquette
    0.86
     arrang
    0.83
    anship
    0.82
     responsiveness
    0.79
     efficiency
    0.77
     duties
    0.77
     adequ
    0.77
     parameters
    0.77
     allocations
    0.76
     specifics
    0.76
    Act Density 0.484%

    No Known Activations