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

    Neuronpedia

    INDEX
    Explanations

    references to neighborhoods and community-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iastes
    -0.82
     jLabel
    -0.66
    новниш
    -0.64
    +#+#
    -0.62
    tdessen
    -0.62
    awtextra
    -0.61
    ніципалі
    -0.61
    rinfo
    -0.61
     onData
    -0.60
    ModelSerializer
    -0.59
    POSITIVE LOGITS
     neighborhood
    0.86
     neighbourhood
    0.82
     Neighborhood
    0.73
     breakthrough
    0.72
     Neighbourhood
    0.70
    Neighborhood
    0.70
    neighborhood
    0.67
     Proximity
    0.64
    neigh
    0.64
     vicinity
    0.64
    Act Density 0.166%

    No Known Activations