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

    Neuronpedia

    INDEX
    Explanations

    references to neighborhoods and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stanisław
    -0.37
    oldt
    -0.37
    handlungen
    -0.36
    이버
    -0.33
     mens
    -0.33
    Vanjske
    -0.33
     zap
    -0.32
     Cup
    -0.32
    mu
    -0.32
    is
    -0.31
    POSITIVE LOGITS
     neighborhoods
    0.86
     neighborhood
    0.77
     wijk
    0.76
     neighbourhoods
    0.74
     Neighborhood
    0.73
    Neighborhood
    0.72
    neighborhood
    0.71
     terecht
    0.68
     suburb
    0.67
     suburbs
    0.64
    Act Density 0.365%

    No Known Activations