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

    Neuronpedia

    INDEX
    Explanations

    places or locations within a setting such as a hall, forest, or courtyard

    oai_token-act-pair · gpt-3.5-turbo

    locations and pathways in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.71
    thood
    -0.69
    entimes
    -0.67
    anson
    -0.64
    phabet
    -0.64
    Ô
    -0.63
    ilon
    -0.63
    anol
    -0.63
    rosso
    -0.61
    ":"/
    -0.61
    POSITIVE LOGITS
     ceiling
    1.01
    tyard
    0.94
     floor
    0.93
     doorway
    0.91
     entrance
    0.88
     courtyard
    0.87
     vicinity
    0.85
     ledge
    0.80
     doors
    0.79
     hallway
    0.79
    Act Density 0.245%

    No Known Activations