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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases with a strong emphasis at the end

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of finality or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.83
    ozyg
    -0.78
    ospons
    -0.77
    efe
    -0.74
     lawfully
    -0.70
     amnesty
    -0.70
    ieth
    -0.69
     repud
    -0.69
     Mehran
    -0.69
    vernment
    -0.68
    POSITIVE LOGITS
     Specifically
    1.10
     Ideally
    1.02
     Firstly
    0.99
     Including
    0.92
     Whilst
    0.92
     Especially
    0.92
     Particularly
    0.92
     Whereas
    0.92
     Lastly
    0.91
    Firstly
    0.91
    Act Density 0.776%

    No Known Activations