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

    Neuronpedia

    INDEX
    Explanations

    references to different physical locations or entities, particularly related to apartments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific apartment numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.95
    vous
    -0.87
    ²¾
    -0.86
    ¶ħ
    -0.85
    nir
    -0.81
    ा
    -0.81
    à¥
    -0.80
    xon
    -0.77
    xtap
    -0.76
    xual
    -0.74
    POSITIVE LOGITS
     complexes
    1.06
     apartment
    1.05
     apartments
    0.99
     balcony
    0.99
     dwellings
    0.91
     Dwell
    0.91
     buildings
    0.88
     rentals
    0.88
     balcon
    0.87
     furniture
    0.86
    Act Density 0.019%

    No Known Activations