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

    Neuronpedia

    INDEX
    Explanations

    specific locations within a building or legal setting

    oai_token-act-pair · gpt-3.5-turbo

    locations related to various settings or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.87
    Reviewer
    -0.80
    aldi
    -0.70
    thood
    -0.69
    çīĪ
    -0.69
    utm
    -0.64
    Strike
    -0.64
    NECT
    -0.64
    jiang
    -0.64
    姫
    -0.63
    POSITIVE LOGITS
     aisle
    1.00
     courtyard
    0.95
     doorway
    0.93
     unnoticed
    0.91
     hallway
    0.91
     doors
    0.89
     gates
    0.88
     door
    0.86
     stairs
    0.85
     floor
    0.85
    Act Density 0.230%

    No Known Activations