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

    Neuronpedia

    INDEX
    Explanations

    instances of self-reflection and self-improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    reflexive pronouns referring to oneself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gql
    -0.43
    MockBean
    -0.36
     Packet
    -0.36
     Kick
    -0.35
     Badge
    -0.35
     script
    -0.34
     Protocol
    -0.34
     baskets
    -0.33
     mon
    -0.33
     mong
    -0.33
    POSITIVE LOGITS
    himself
    1.01
    Yourself
    1.00
     yourself
    0.99
    yourself
    0.99
     himself
    0.98
     thyself
    0.97
     herself
    0.97
     ourselves
    0.97
     oneself
    0.96
    herself
    0.96
    Act Density 0.038%

    No Known Activations