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

    Neuronpedia

    INDEX
    Explanations

    words related to ships and shipyards

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ships and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.88
    osate
    -0.82
    ADRA
    -0.73
    PsyNetMessage
    -0.72
    theless
    -0.71
    Downloadha
    -0.70
    âĶģ
    -0.70
    nesota
    -0.68
    okers
    -0.68
     confir
    -0.66
    POSITIVE LOGITS
    wreck
    1.66
    wright
    1.22
    yard
    1.21
    yards
    1.14
    shape
    1.07
    building
    1.03
     Graveyard
    1.02
    boat
    1.00
    mates
    0.97
     ship
    0.94
    Act Density 0.020%

    No Known Activations