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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize particular attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Republic
    -0.50
     republic
    -0.46
     culture
    -0.46
    JI
    -0.46
     abandoned
    -0.46
     sulphuric
    -0.46
    altezza
    -0.45
     kaarangay
    -0.45
    ensee
    -0.45
     Civil
    -0.45
    POSITIVE LOGITS
     especially
    0.68
    0.60
     Sünde
    0.57
     cortesía
    0.55
     Wikiseite
    0.55
     Irán
    0.55
    especially
    0.52
     especialmente
    0.50
     christlichen
    0.49
    dientemente
    0.49
    Act Density 0.242%

    No Known Activations