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

    Neuronpedia

    INDEX
    Explanations

    impersonal topics, such as news articles and reports, as well as communication mediums, such as emails and messages

    oai_token-act-pair · gpt-3.5-turbo

    references to online posts, emails, and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.79
    ernels
    -0.76
     Dragonbound
    -0.69
    aces
    -0.68
     Cups
    -0.68
     sexes
    -0.65
    ampires
    -0.64
     breaths
    -0.63
     Steps
    -0.63
    paces
    -0.63
    POSITIVE LOGITS
     titled
    1.00
     entitled
    0.94
     wherein
    0.92
     involving
    0.87
     purportedly
    0.85
     called
    0.83
     whereby
    0.82
     depicting
    0.78
     that
    0.77
     aimed
    0.77
    Act Density 0.435%

    No Known Activations