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

    Neuronpedia

    INDEX
    Explanations

    phrases related to apartments

    oai_token-act-pair · gpt-3.5-turbo

    references to specific apartment numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -1.00
    ¶ħ
    -0.83
    ²¾
    -0.82
    vous
    -0.80
    xtap
    -0.79
    nir
    -0.76
    à¥
    -0.75
    xual
    -0.73
    ा
    -0.73
    ciating
    -0.72
    POSITIVE LOGITS
     complexes
    1.00
     balcony
    0.99
     apartment
    0.99
     apartments
    0.97
     Dwell
    0.96
     dwellings
    0.94
     buildings
    0.89
     balcon
    0.88
     rentals
    0.83
    raper
    0.82
    Act Density 0.020%

    No Known Activations