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

    Neuronpedia

    INDEX
    Explanations

    sentences that start with "This is a"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance or significance of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alties
    -0.83
    uin
    -0.81
    Versions
    -0.78
    anas
    -0.75
    Assistant
    -0.75
    AIDS
    -0.72
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.72
    ['
    -0.70
    olicy
    -0.70
    Īè
    -0.69
    POSITIVE LOGITS
     HUGE
    1.03
     continuation
    1.02
     huge
    1.00
     fascinating
    0.96
     VERY
    0.94
     serious
    0.93
     textbook
    0.92
     topic
    0.91
     reminder
    0.90
     very
    0.90
    Act Density 0.159%

    No Known Activations