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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and milestones related to submarines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é£ŀ
    -0.18
    é£Ľ
    -0.16
     fly
    -0.16
     flying
    -0.16
     wing
    -0.16
     aer
    -0.16
     wings
    -0.15
     Wing
    -0.15
     Fly
    -0.15
     Wings
    -0.15
    POSITIVE LOGITS
     submarines
    0.28
     submarine
    0.27
     submar
    0.26
    æ½ľ
    0.25
     surfaced
    0.25
     submerged
    0.23
     tor
    0.23
     torpedo
    0.23
     subs
    0.21
     sub
    0.20
    Act Density 0.024%

    No Known Activations