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

    Neuronpedia

    INDEX
    Explanations

    countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å§
    -0.66
    tops
    -0.64
    naissance
    -0.64
     continu
    -0.62
    Discussion
    -0.62
    iple
    -0.60
    cill
    -0.60
    heny
    -0.59
    essen
    -0.59
    notation
    -0.59
    POSITIVE LOGITS
     Airlines
    0.96
     Yard
    0.85
    ican
    0.84
    borg
    0.83
     TODAY
    0.81
     Today
    0.78
     Votes
    0.72
     invaded
    0.71
    's
    0.70
    icans
    0.70
    Act Density 0.189%

    No Known Activations