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

    Neuronpedia

    INDEX
    Explanations

    references to locations in a building, specifically basements

    oai_token-act-pair · gpt-3.5-turbo

    references to basements and cellars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uncture
    -0.79
    nir
    -0.76
    Cola
    -0.75
    itia
    -0.75
    Forward
    -0.72
    Asia
    -0.69
    Published
    -0.69
    yt
    -0.68
    NG
    -0.68
    lda
    -0.67
    POSITIVE LOGITS
     basement
    1.25
     cellar
    1.03
    stairs
    0.95
     lid
    0.89
     attic
    0.85
    ħĭ
    0.84
     annex
    0.83
     courtyard
    0.82
     bunker
    0.82
     closet
    0.81
    Act Density 0.005%

    No Known Activations