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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical entities and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.97
     fubject
    -0.95
     raiſ
    -0.87
     faſt
    -0.86
    </caption>
    -0.85
     pleaſure
    -0.83
     Houſe
    -0.82
     juſt
    -0.81
     Anſ
    -0.81
     Monfieur
    -0.80
    POSITIVE LOGITS
     Bretagne
    0.71
     تضيفلها
    0.62
     porc
    0.60
    Sask
    0.58
     Saudi
    0.58
     Rhode
    0.57
     Welsh
    0.57
    Dana
    0.56
     Galway
    0.56
     modo
    0.56
    Act Density 1.442%

    No Known Activations