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

    Neuronpedia

    INDEX
    Explanations

    descriptions of features and amenities in properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anchors
    -0.16
    опиÑģ
    -0.15
    ANGES
    -0.14
    drv
    -0.14
    ensch
    -0.14
    Ľi
    -0.13
    ká
    -0.13
    аÑģÑģ
    -0.13
    torrent
    -0.13
    allery
    -0.13
    POSITIVE LOGITS
     radiator
    0.23
     extractor
    0.22
     obscure
    0.21
     airing
    0.20
     obscured
    0.20
     inset
    0.20
     Worcester
    0.19
     UP
    0.19
     tiled
    0.19
     spotlight
    0.19
    Act Density 0.012%

    No Known Activations