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

    Neuronpedia

    INDEX
    Explanations

    mentions of fuel tanks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tanks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jun
    -0.75
     Haskell
    -0.69
     Compton
    -0.69
     Languages
    -0.69
    hom
    -0.69
     Gael
    -0.68
     Garcia
    -0.68
     Alam
    -0.68
    inters
    -0.67
     Reese
    -0.66
    POSITIVE LOGITS
     tank
    3.90
     tanks
    3.14
    tank
    3.00
     Tank
    2.95
    Tank
    2.66
     Tanks
    2.39
     tanker
    1.94
     turret
    1.30
     armored
    1.28
     aquarium
    1.23
    Act Density 0.023%

    No Known Activations