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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations, possibly in a context of exploration or adventure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     nomine
    -1.38
     virtue
    -1.15
    bilt
    -1.12
    backer
    -1.00
     Coco
    -1.00
     Celest
    -0.99
     Patriot
    -0.95
     sclerosis
    -0.94
     Perse
    -0.93
     Honour
    -0.92
    POSITIVE LOGITS
    bing
    1.97
    stract
    1.93
    bed
    1.71
    yrinth
    1.65
    riel
    1.55
    uilt
    1.54
    raid
    1.52
    raham
    1.50
    rid
    1.48
    ilty
    1.44
    Act Density 0.934%

    No Known Activations