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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to outdoor environments and settings

    oai_token-act-pair · gpt-3.5-turbo

    action sequences related to conflict or exploration within fantastical settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.62
    Writ
    -0.60
    elligence
    -0.59
     apolog
    -0.58
     antibodies
    -0.57
     inher
    -0.57
     apologized
    -0.57
     inexperienced
    -0.56
    Item
    -0.55
    rss
    -0.55
    POSITIVE LOGITS
     beaches
    1.12
     streets
    1.09
     highways
    1.09
     hills
    1.09
     runway
    1.09
     rooft
    1.08
     coastline
    1.04
     canyon
    1.02
     cliffs
    1.00
     coasts
    1.00
    Act Density 1.109%

    No Known Activations