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

    Neuronpedia

    INDEX
    Explanations

    words related to ships and maritime activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mp
    -0.76
    mem
    -0.67
     unfocusedRange
    -0.66
    alam
    -0.65
    oner
    -0.65
    ome
    -0.64
    ovember
    -0.64
    arov
    -0.63
    ggie
    -0.62
    ach
    -0.61
    POSITIVE LOGITS
     ships
    3.80
     Ships
    2.87
     warships
    2.55
     vessels
    2.39
     boats
    2.30
     ship
    2.23
     fleets
    1.96
     submarines
    1.93
    boats
    1.93
    ships
    1.87
    Act Density 0.013%

    No Known Activations