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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the identity or activities of a specific group or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to "Pirate" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.87
    uate
    -0.80
    uated
    -0.79
    mble
    -0.76
    uating
    -0.74
    andra
    -0.74
    negie
    -0.71
    minus
    -0.70
     Beir
    -0.70
    eger
    -0.69
    POSITIVE LOGITS
    Pir
    1.07
     Pirates
    0.89
     Pirate
    0.87
     pirates
    0.86
     Luffy
    0.85
     overboard
    0.77
    cean
    0.75
    lust
    0.73
     Ship
    0.73
     Parties
    0.71
    Act Density 0.010%

    No Known Activations