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

    Neuronpedia

    INDEX
    Explanations

    names of countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of country names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gillespie
    -0.68
    espie
    -0.66
    iple
    -0.66
    å§
    -0.66
    soDeliveryDate
    -0.65
    inventoryQuantity
    -0.65
    naissance
    -0.64
    heny
    -0.64
    Discussion
    -0.63
    TAG
    -0.62
    POSITIVE LOGITS
     Airlines
    0.87
    borg
    0.82
    ican
    0.78
     TODAY
    0.76
    's
    0.73
     Today
    0.72
     invaded
    0.70
     Telecom
    0.69
     Yard
    0.69
    ESE
    0.67
    Act Density 0.216%

    No Known Activations