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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    general expressions of thoughts or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .","
    -0.64
     ..."
    -0.60
     ``(
    -0.57
    PLIED
    -0.57
    rouse
    -0.56
    dk
    -0.56
     `
    -0.55
     indistinguishable
    -0.55
    ILY
    -0.54
    natureconservancy
    -0.54
    POSITIVE LOGITS
     Conclusion
    1.37
     Solution
    1.15
     Lastly
    1.00
     Regarding
    0.99
     Thoughts
    0.98
     Another
    0.98
     Anyway
    0.97
     Recommend
    0.95
     Further
    0.93
     Problems
    0.93
    Act Density 0.472%

    No Known Activations