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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legate
    -0.17
    ائز
    -0.15
    ActionTypes
    -0.15
     nurt
    -0.15
    ignet
    -0.15
    ResponseBody
    -0.14
    หมาย
    -0.14
    allow
    -0.14
    inee
    -0.14
    £
    -0.14
    POSITIVE LOGITS
     get
    0.22
     become
    0.22
     stay
    0.20
     avoid
    0.20
     understand
    0.20
     progress
    0.20
     transition
    0.19
     achieve
    0.18
     along
    0.17
     to
    0.17
    Act Density 0.067%

    No Known Activations