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

    Neuronpedia

    INDEX
    Explanations

    words related to neighbors and neighborhood interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    retan
    -0.60
     arbejde
    -0.60
    ército
    -0.54
    teros
    -0.53
     Crews
    -0.53
     baku
    -0.52
     Sanz
    -0.52
    شور
    -0.51
    STC
    -0.51
    PDC
    -0.51
    POSITIVE LOGITS
     neighbors
    2.14
     neighbor
    2.09
     neighbours
    1.95
     neighbour
    1.88
     Neighbor
    1.84
     Neighbors
    1.77
     NEIGH
    1.77
     neigh
    1.75
     Neigh
    1.71
     neighboring
    1.70
    Act Density 0.081%

    No Known Activations