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

    Neuronpedia

    INDEX
    Explanations

    attributes and features of residential properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bed
    -0.15
    æ¾
    -0.14
    awan
    -0.14
    ubl
    -0.14
    Sortable
    -0.14
     bathrooms
    -0.14
    sian
    -0.13
     guest
    -0.13
     suites
    -0.13
     Ward
    -0.13
    POSITIVE LOGITS
     informal
    0.22
     Formal
    0.21
     formal
    0.21
     fires
    0.18
     formally
    0.18
     Hearth
    0.18
     eating
    0.18
    eating
    0.17
     sitting
    0.17
     wet
    0.17
    Act Density 0.069%

    No Known Activations