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

    Neuronpedia

    INDEX
    Explanations

    references to living arrangements and housing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oras
    -0.15
    ensch
    -0.14
    emy
    -0.14
    礼
    -0.14
     Exterior
    -0.14
    eday
    -0.14
     weddings
    -0.14
    ocre
    -0.13
     closures
    -0.13
    алÑĭ
    -0.13
    POSITIVE LOGITS
     flat
    0.41
     apartment
    0.38
     house
    0.31
    -flat
    0.31
    flat
    0.30
     pad
    0.30
     home
    0.29
     duplex
    0.29
     Flat
    0.28
    Flat
    0.27
    Act Density 0.251%

    No Known Activations