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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and relationships with places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Golf
    -0.22
     golf
    -0.21
     hotels
    -0.17
     hotel
    -0.16
     vill
    -0.16
     gol
    -0.15
    å¾ħ
    -0.15
     Hotels
    -0.15
     Hilton
    -0.15
    ugar
    -0.15
    POSITIVE LOGITS
     Backpack
    0.33
     backpack
    0.32
     dorm
    0.28
     hostel
    0.28
     Dorm
    0.25
    shared
    0.24
     shared
    0.24
     Host
    0.23
    Shared
    0.23
     Shared
    0.22
    Act Density 0.024%

    No Known Activations