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

    Neuronpedia

    INDEX
    Explanations

    mentions of gratitude or thanks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparisons and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )</
    -0.58
    .</
    -0.57
     ..."
    -0.52
     ''
    -0.50
    "},"
    -0.50
     thereto
    -0.50
    medi
    -0.49
    ``
    -0.49
    })
    -0.49
     theirs
    -0.49
    POSITIVE LOGITS
     meanwhile
    0.61
    ibliography
    0.57
     nutshell
    0.57
     Explan
    0.55
     disclaimer
    0.54
    ĻĤ
    0.53
     Sketch
    0.52
     Works
    0.52
     Summary
    0.51
     Conclusion
    0.50
    Act Density 1.028%

    No Known Activations