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

    Neuronpedia

    INDEX
    Explanations

    references to neighborhoods and community-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fet
    -0.51
     tr
    -0.50
     realiz
    -0.48
     dos
    -0.47
     c
    -0.46
    大
    -0.45
    ``
    -0.44
     v
    -0.43
    getSelection
    -0.43
     et
    -0.43
    POSITIVE LOGITS
     neighbourhood
    1.30
     neighborhood
    1.27
     neighbour
    1.04
     neighbours
    1.04
     neighbourhoods
    1.03
    neighborhood
    1.02
     neighbor
    1.00
     Neigh
    0.97
     neigh
    0.97
     vicinity
    0.95
    Act Density 0.077%

    No Known Activations