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

    Neuronpedia

    INDEX
    Explanations

    topics related to international negotiations or agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographer
    -0.70
    aunt
    -0.69
    robat
    -0.66
    Released
    -0.66
    Happy
    -0.66
    ographers
    -0.64
    Hero
    -0.64
    hero
    -0.63
     âĿ
    -0.63
     proud
    -0.63
    POSITIVE LOGITS
     issues
    0.98
     topics
    0.97
     whether
    0.96
     particulars
    0.93
     concerns
    0.92
     unresolved
    0.90
     allegations
    0.90
     questions
    0.89
     feasibility
    0.87
     Regarding
    0.86
    Act Density 0.355%

    No Known Activations