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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific name "Ward"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific wards or regions within a geographic or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctions
    -0.83
    ãĥ¤
    -0.82
    alogue
    -0.81
    gdala
    -0.81
    ogene
    -0.81
    ãĥĪ
    -0.80
    ivia
    -0.78
    berus
    -0.76
    itability
    -0.75
    kered
    -0.74
    POSITIVE LOGITS
    robe
    1.47
    ynski
    0.86
    ages
    0.83
    age
    0.83
     Passage
    0.81
    ings
    0.79
    hips
    0.79
    ens
    0.78
    away
    0.78
    ling
    0.78
    Act Density 0.008%

    No Known Activations