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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific spaces or locations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.92
    tvguidetime
    -0.87
    aarrggbb
    -0.79
    出版年
    -0.78
    rungsseite
    -0.76
     AssemblyCulture
    -0.76
     متعلقه
    -0.73
     CanadaChoose
    -0.72
    -0.72
    енча
    -0.71
    POSITIVE LOGITS
     room
    0.98
     rooms
    0.95
     interior
    0.83
     space
    0.83
     spacious
    0.81
     spaces
    0.78
     Room
    0.76
     interiors
    0.75
     indoor
    0.74
     floor
    0.74
    Act Density 0.240%

    No Known Activations