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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pigs
    -0.75
     euth
    -0.71
     Mayo
    -0.71
     Camer
    -0.70
     incorrectly
    -0.70
     wrongly
    -0.67
     unexpectedly
    -0.67
     errone
    -0.66
     Lep
    -0.66
     erroneous
    -0.65
    POSITIVE LOGITS
    github
    1.89
    twitter
    1.79
    youtu
    1.54
    www
    1.54
    docs
    1.52
    medium
    1.41
    mega
    1.39
    doi
    1.37
    goo
    1.34
    sites
    1.31
    Act Density 0.016%

    No Known Activations