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

    Neuronpedia

    INDEX
    Explanations

    sentences with periods at the end

    oai_token-act-pair · gpt-3.5-turbo

    sentences that provide statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.79
     brut
    -0.76
     advoc
    -0.76
     fermented
    -0.73
     manif
    -0.72
     challeng
    -0.72
     nuts
    -0.72
     glim
    -0.71
     ogre
    -0.68
     masse
    -0.68
    POSITIVE LOGITS
     Besides
    1.07
     Especially
    1.01
     Its
    1.00
     They
    0.99
     Whether
    0.99
     Specifically
    0.97
     Whilst
    0.97
     Though
    0.96
     However
    0.95
     Although
    0.95
    Act Density 0.377%

    No Known Activations