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

    Neuronpedia

    INDEX
    Explanations

    words related to diplomatic or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.79
    代
    -0.73
    antage
    -0.68
    enegger
    -0.65
     toget
    -0.65
    farious
    -0.63
    milo
    -0.62
     disg
    -0.62
    jri
    -0.62
    akespe
    -0.60
    POSITIVE LOGITS
     Rates
    0.81
     Finder
    0.78
     Profile
    0.73
     Album
    0.72
     Abilities
    0.70
     Transfer
    0.70
     Locations
    0.70
     Directory
    0.69
     Reviews
    0.69
     Components
    0.68
    Act Density 0.420%

    No Known Activations