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

    Neuronpedia

    INDEX
    Explanations

    descriptions and actions related to a specific ship

    oai_token-act-pair · gpt-3.5-turbo

    references to ships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.85
    ADRA
    -0.80
    ichita
    -0.75
    66666666
    -0.73
    berra
    -0.70
    okers
    -0.70
    avez
    -0.69
     Decoder
    -0.69
    olars
    -0.66
    ãĥĥãĥĪ
    -0.64
    POSITIVE LOGITS
    wreck
    1.34
    wright
    1.19
     ship
    1.16
     Titanic
    1.09
    boat
    1.08
    boats
    0.98
    yard
    0.98
     ships
    0.98
    Ship
    0.97
     Ship
    0.95
    Act Density 0.015%

    No Known Activations