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

    Neuronpedia

    INDEX
    Explanations

    pronouns for people or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups being involved in various actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siege
    -0.81
    vine
    -0.75
     Conversation
    -0.70
     SEA
    -0.68
     Mental
    -0.66
     Politics
    -0.66
     Megan
    -0.66
     Assault
    -0.66
    AMY
    -0.66
     Addiction
    -0.66
    POSITIVE LOGITS
    atically
    1.08
    self
    0.96
    atic
    0.90
     personally
    0.88
    selves
    0.86
    atar
    0.84
    atics
    0.81
     fatally
    0.78
    atical
    0.77
    alian
    0.77
    Act Density 0.216%

    No Known Activations