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

    Neuronpedia

    INDEX
    Explanations

    keywords related to international relations and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ById
    -0.66
     footprints
    -0.65
     illusions
    -0.62
     evid
    -0.61
    intosh
    -0.60
     millenn
    -0.60
     packets
    -0.60
    stuff
    -0.60
     loopholes
    -0.60
     deductions
    -0.59
    POSITIVE LOGITS
    ggles
    1.39
    wered
    1.25
    asted
    1.10
    pless
    1.04
    ilet
    1.04
    ppers
    1.03
    pper
    0.99
    pload
    0.98
    iling
    0.95
    asting
    0.92
    Act Density 0.196%

    No Known Activations