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

    Neuronpedia

    INDEX
    Explanations

    references to ships or shipping-related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     alert
    -0.60
    getActive
    -0.60
     poderão
    -0.60
     Pols
    -0.59
     تحد
    -0.59
     Lest
    -0.59
     ESP
    -0.57
     Laurent
    -0.57
     Fara
    -0.57
     Pee
    -0.56
    POSITIVE LOGITS
     Ship
    1.50
     Ships
    1.47
     ships
    1.45
     SHIP
    1.45
    Ships
    1.38
     ship
    1.37
    Ship
    1.30
    ships
    1.27
    SHIP
    1.23
    ship
    1.18
    Act Density 0.008%

    No Known Activations