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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or developments

    oai_token-act-pair · gpt-3.5-turbo

    references to events that occur after significant incidents or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.95
     depended
    -0.79
     depends
    -0.78
     lasted
    -0.70
    gans
    -0.70
     prefers
    -0.69
     relies
    -0.68
     relied
    -0.67
     countered
    -0.66
    ryu
    -0.65
    POSITIVE LOGITS
     announcement
    1.47
     revelations
    1.27
     revelation
    1.22
     debacle
    1.19
     unveiling
    1.10
     deaths
    1.09
     tragic
    1.07
     announcements
    1.05
     demise
    1.04
     resignation
    1.04
    Act Density 0.389%

    No Known Activations