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

    Neuronpedia

    INDEX
    Explanations

    instances of evidence or items related to searching or discovering something hidden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     academies
    -0.53
     agencies
    -0.49
     stadiums
    -0.48
    ագրություններ
    -0.47
    Pubs
    -0.46
     invertible
    -0.45
     insolvency
    -0.44
     Class
    -0.43
     ganglia
    -0.43
     AGENCIES
    -0.43
    POSITIVE LOGITS
     downstairs
    1.25
     upstairs
    1.23
     kitchen
    1.10
     bedroom
    1.03
    Upstairs
    0.95
     bedrooms
    0.94
     house
    0.93
     household
    0.93
    kitchen
    0.88
     Kitchen
    0.85
    Act Density 0.433%

    No Known Activations