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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal challenges or obstacles that individuals have faced

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant life events or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )))
    -0.69
    =>
    -0.67
     POS
    -0.64
     Recommend
    -0.62
     DOD
    -0.62
    vector
    -0.61
     Committees
    -0.61
    }}}
    -0.60
    arget
    -0.60
    ))))
    -0.60
    POSITIVE LOGITS
     his
    1.06
     stint
    1.01
     he
    0.98
     autobi
    0.93
     her
    0.89
     upbringing
    0.88
    ventures
    0.86
     tattoos
    0.86
    His
    0.85
     she
    0.84
    Act Density 1.405%

    No Known Activations