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

    Neuronpedia

    INDEX
    Explanations

    mentions of luxurious or high-end locations and properties

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of buildings, structures, and living arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbohyd
    -0.72
     neut
    -0.71
    enhagen
    -0.68
     microscopic
    -0.65
    origin
    -0.63
    avez
    -0.63
    ás
    -0.62
    HK
    -0.62
    ãģĦ
    -0.62
    */(
    -0.61
    POSITIVE LOGITS
    lain
    0.96
     Ruins
    0.78
    keeper
    0.77
     Seat
    0.76
    tyard
    0.75
     Royale
    0.74
    goers
    0.73
    eous
    0.72
    bage
    0.72
     Oaks
    0.72
    Act Density 0.144%

    No Known Activations