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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to users in a technical or online context

    oai_token-act-pair · gpt-3.5-turbo

    references to users in the context of technology or online services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Baptist
    -0.72
     Beir
    -0.70
     UNESCO
    -0.69
     Lutheran
    -0.65
    hovah
    -0.65
     Vaugh
    -0.65
    amer
    -0.63
     Shack
    -0.62
    western
    -0.60
     Bale
    -0.60
    POSITIVE LOGITS
    pace
    1.13
    hip
    1.10
    cript
    1.07
     interface
    0.96
    ettings
    0.94
     interfaces
    0.92
    interface
    0.87
    paces
    0.87
    erv
    0.80
    hare
    0.80
    Act Density 0.031%

    No Known Activations