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

    Neuronpedia

    INDEX
    Explanations

    references to specific wards in a local context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.62
     ioe
    -0.60
    itzende
    -0.58
    ractable
    -0.58
     amg
    -0.57
    例句
    -0.56
    Royal
    -0.55
    ोंने
    -0.55
    liothèque
    -0.55
    первых
    -0.55
    POSITIVE LOGITS
     Ward
    1.23
    Ward
    1.15
     ward
    1.11
    ward
    1.07
     WARD
    1.07
    WARD
    0.94
     wards
    0.89
    dom
    0.74
     burned
    0.73
     cabin
    0.66
    Act Density 0.061%

    No Known Activations