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

    Neuronpedia

    INDEX
    Explanations

    terms related to enclosed spaces or rooms

    oai_token-act-pair · gpt-3.5-turbo

    references to "chamber" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wass
    -0.70
     Definitive
    -0.63
    ces
    -0.63
    ku
    -0.62
    COL
    -0.60
     sporadic
    -0.60
    uras
    -0.58
     Suk
    -0.57
     disproportionate
    -0.57
     vulgar
    -0.56
    POSITIVE LOGITS
    lain
    1.62
    maid
    1.14
     chamber
    1.10
     chambers
    1.01
    door
    0.95
    room
    0.88
    rooms
    0.87
    house
    0.84
    ican
    0.82
    icka
    0.81
    Act Density 0.008%

    No Known Activations