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

    Neuronpedia

    INDEX
    Explanations

    links or prompts encouraging to learn more about various topics or technologies

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging further exploration or learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.90
    IPS
    -0.72
     teasp
    -0.70
    Rule
    -0.66
    §
    -0.66
    ammers
    -0.65
    uckle
    -0.65
    ovie
    -0.65
    ŃĶ
    -0.63
     cradle
    -0.63
    POSITIVE LOGITS
     than
    1.16
    natureconservancy
    1.10
     info
    0.99
     details
    0.96
     specifics
    0.86
    details
    0.86
     information
    0.81
     detail
    0.79
     detailed
    0.79
    than
    0.77
    Act Density 0.066%

    No Known Activations