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

    Neuronpedia

    INDEX
    Explanations

    concepts related to navigation and perception in tasks or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pitch
    -0.13
    μη
    -0.13
    okane
    -0.13
     Wass
    -0.13
     Deck
    -0.13
    \db
    -0.13
    Pitch
    -0.13
    odb
    -0.12
    iveau
    -0.12
    BU
    -0.12
    POSITIVE LOGITS
     policy
    0.35
     reward
    0.35
     Policy
    0.33
     RL
    0.32
     agents
    0.32
     agent
    0.31
     rewards
    0.31
    -policy
    0.31
    Policy
    0.31
    policy
    0.30
    Act Density 0.021%

    No Known Activations