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

    Neuronpedia

    INDEX
    Explanations

    references to political candidates and their actions during debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.55
     orizz
    -0.50
    atzung
    -0.49
     Legislative
    -0.48
     élus
    -0.47
    StructEnd
    -0.47
    PHONY
    -0.46
     soja
    -0.46
     siedz
    -0.44
    ulho
    -0.44
    POSITIVE LOGITS
     debate
    0.92
     debates
    0.87
     campaign
    0.86
    debate
    0.79
     candidate
    0.78
     Debates
    0.77
     Debate
    0.77
     primary
    0.76
    Debate
    0.74
    theless
    0.72
    Act Density 0.384%

    No Known Activations