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

    Neuronpedia

    INDEX
    Explanations

    references to property features and amenities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abo
    -0.19
     Mississippi
    -0.16
     Bowman
    -0.15
    ãĥįãĥ«
    -0.15
     Belarus
    -0.15
     moh
    -0.15
     kaz
    -0.14
    borg
    -0.14
    ynamodb
    -0.14
    å£ģ
    -0.14
    POSITIVE LOGITS
     Bali
    0.47
     Indonesia
    0.35
     Ub
    0.35
     Indonesian
    0.33
     Bal
    0.32
     Indones
    0.30
    Ub
    0.29
    BAL
    0.28
    Bal
    0.28
     BAL
    0.27
    Act Density 0.010%

    No Known Activations