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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the use of something for specific purposes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate purposes or reasons related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ername
    -0.73
    é¾
    -0.70
    osa
    -0.69
    edin
    -0.68
    ellen
    -0.67
    Learn
    -0.67
     Subscribe
    -0.66
    oller
    -0.66
    Ag
    -0.65
    mare
    -0.64
    POSITIVE LOGITS
     purposes
    1.65
     reasons
    1.36
    geries
    1.35
    gery
    1.11
     sake
    1.08
    aging
    1.04
     nefarious
    1.02
    bidden
    1.02
     centuries
    1.01
     purpose
    0.98
    Act Density 0.175%

    No Known Activations