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

    Neuronpedia

    INDEX
    Explanations

    locations or directions within a physical space

    oai_token-act-pair · gpt-3.5-turbo

    locations and physical spaces within the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emonic
    -0.75
    anson
    -0.75
    htaking
    -0.74
     Flavoring
    -0.70
    ño
    -0.67
    anned
    -0.65
    haps
    -0.65
    sbm
    -0.65
    MN
    -0.64
    annot
    -0.63
    POSITIVE LOGITS
     doorway
    0.92
     courtyard
    0.90
     alley
    0.82
     balcony
    0.80
     doors
    0.80
     roof
    0.79
    tyard
    0.76
     fireplace
    0.76
     attic
    0.76
     hallway
    0.75
    Act Density 0.369%

    No Known Activations