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

    Neuronpedia

    INDEX
    Explanations

    references to political events and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.82
     Australia
    -0.66
    Australia
    -0.62
     AUSTRALIA
    -0.61
     australiano
    -0.60
    CloseOperation
    -0.58
    Australian
    -0.58
     Australian
    -0.58
     Австра
    -0.57
    клопе
    -0.57
    POSITIVE LOGITS
     Ball
    0.70
    Ball
    0.65
     Wag
    0.62
     Dub
    0.61
     regional
    0.60
     Wod
    0.59
     Orange
    0.59
     Lith
    0.59
     Broken
    0.59
     Tam
    0.58
    Act Density 0.153%

    No Known Activations