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

    Neuronpedia

    INDEX
    Explanations

    phrases related to Japanese culture and terminology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific cultural references or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accountability
    -0.88
     Applicant
    -0.84
     Task
    -0.82
    Real
    -0.82
     Rack
    -0.81
     Governments
    -0.81
     Opportun
    -0.81
     Employ
    -0.80
    CLASSIFIED
    -0.80
     Target
    -0.77
    POSITIVE LOGITS
    ensis
    1.19
    utic
    0.99
     mushrooms
    0.93
     beetle
    0.90
    xual
    0.89
     flower
    0.89
     trees
    0.88
     berries
    0.87
     dancers
    0.84
     tree
    0.84
    Act Density 0.232%

    No Known Activations