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

    Neuronpedia

    INDEX
    Explanations

    places or locations within a community

    oai_token-act-pair · gpt-3.5-turbo

    locations or places in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.75
    ancial
    -0.73
    æŃ
    -0.70
    ortium
    -0.69
    xit
    -0.67
    Poll
    -0.66
    pread
    -0.65
    Ô
    -0.65
     Modes
    -0.65
     Expand
    -0.64
    POSITIVE LOGITS
     aisle
    1.04
     courtyard
    0.97
     cafeteria
    0.91
     plaza
    0.90
     hallway
    0.90
     doorway
    0.87
     courthouse
    0.85
     kitchen
    0.85
     floor
    0.85
     freezer
    0.84
    Act Density 0.220%

    No Known Activations