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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    dates related to Theresa May

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ECTION
    -0.82
     Hawai
    -0.80
     Tulsa
    -0.76
     Fatal
    -0.76
    Houston
    -0.75
     Honolulu
    -0.75
    Methods
    -0.73
    ¥µ
    -0.71
     Roku
    -0.71
     Asheville
    -0.70
    POSITIVE LOGITS
     appoint
    0.92
     ministerial
    0.90
    agher
    0.87
     reassured
    0.85
     adviser
    0.80
     ministers
    0.80
     advisor
    0.79
     supporter
    0.79
     cabinet
    0.79
     appointed
    0.77
    Act Density 0.050%

    No Known Activations