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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply improvement or comparison to a higher standard

    oai_token-act-pair · gpt-3.5-turbo

    the term "Better" in various contexts indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pose
    -0.66
     enters
    -0.62
     invol
    -0.62
     consecut
    -0.62
    CVE
    -0.62
     sporadic
    -0.61
    lled
    -0.61
    inous
    -0.59
    ItemThumbnailImage
    -0.58
     tre
    -0.58
    POSITIVE LOGITS
     Better
    3.63
    Better
    2.93
    better
    2.08
     Faster
    1.71
     better
    1.63
     Worse
    1.61
     Higher
    1.44
     BET
    1.29
     Improved
    1.24
     smarter
    1.22
    Act Density 0.016%

    No Known Activations