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

    Neuronpedia

    INDEX
    Explanations

    questions or prompts to engage the user in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements that involve identifying individuals or making inquiries about information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.74
    obin
    -0.68
    etheless
    -0.68
     Defenders
    -0.67
    omal
    -0.67
    itutional
    -0.64
     LIA
    -0.63
     prosecutions
    -0.62
    iversal
    -0.60
    exclusive
    -0.60
    POSITIVE LOGITS
     groceries
    0.89
    terday
    0.81
     ______
    0.81
     pizza
    0.80
     homework
    0.80
     dinner
    0.78
     XY
    0.78
     sushi
    0.78
     stairs
    0.77
     classmate
    0.76
    Act Density 0.916%

    No Known Activations