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

    Neuronpedia

    INDEX
    Explanations

    locations or descriptions related to underground spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to geological formations and underground structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fn
    -0.82
     endorsements
    -0.73
     unconditional
    -0.72
     Choice
    -0.71
     Firearms
    -0.71
     substitution
    -0.70
     recommendation
    -0.67
     coupon
    -0.67
    reply
    -0.67
     waiver
    -0.67
    POSITIVE LOGITS
     inhabited
    1.10
     caves
    1.04
     beneath
    1.02
     depths
    0.99
     canyon
    0.94
     dwellings
    0.92
     cavern
    0.86
     protr
    0.86
    holes
    0.86
     habitats
    0.86
    Act Density 0.509%

    No Known Activations