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

    Neuronpedia

    INDEX
    Explanations

    articles or pieces discussing specific topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    articles and titles related to various published works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extingu
    -0.70
     airst
    -0.70
    stairs
    -0.70
    zers
    -0.70
     detectors
    -0.68
     Santana
    -0.65
     customs
    -0.65
     resin
    -0.65
     transporter
    -0.64
     valves
    -0.64
    POSITIVE LOGITS
     titled
    0.90
     headlined
    0.87
    articles
    0.83
    vertisement
    0.83
     Blog
    0.81
     blogs
    0.80
    itled
    0.80
     reprinted
    0.80
     essays
    0.79
     blog
    0.79
    Act Density 0.394%

    No Known Activations