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

    Neuronpedia

    INDEX
    Explanations

    references to locations, specifically Brussels

    oai_token-act-pair · gpt-3.5-turbo

    references to Brussels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vich
    -0.86
    ãģ¦
    -0.76
    ONSORED
    -0.73
     Samurai
    -0.71
    lease
    -0.70
    VALUE
    -0.70
    ointed
    -0.70
    manent
    -0.69
    LEASE
    -0.69
    served
    -0.69
    POSITIVE LOGITS
     Brussels
    0.97
    mouth
    0.90
     spr
    0.79
     Lumpur
    0.78
    chet
    0.73
    sterdam
    0.72
    furt
    0.72
    bourg
    0.72
    ween
    0.72
    boro
    0.71
    Act Density 0.005%

    No Known Activations