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

    Neuronpedia

    INDEX
    Explanations

    references to proximity, specifically locations and their surrounding areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pesos
    -0.58
    phosa
    -0.57
     abstrait
    -0.57
    etero
    -0.56
     sær
    -0.56
     réfugi
    -0.54
    стъ
    -0.54
     complètes
    -0.53
     devront
    -0.53
    setopt
    -0.52
    POSITIVE LOGITS
     neighbors
    1.16
     neighbours
    1.13
     neighbor
    1.10
     neighbour
    1.08
     neighboring
    1.01
     neigh
    1.00
     neighbouring
    0.99
    Nearby
    0.97
     Neighbor
    0.95
    nearby
    0.93
    Act Density 0.157%

    No Known Activations