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

    Neuronpedia

    INDEX
    Explanations

    specific actions or effects related to increasing quantity or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic and operational efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.72
    »Ĵ
    -0.72
    ouse
    -0.68
    oros
    -0.68
    idav
    -0.68
     reformed
    -0.67
     quir
    -0.65
    lished
    -0.64
     Architects
    -0.64
    odcast
    -0.64
    POSITIVE LOGITS
     intensity
    1.04
     capacity
    1.03
     efficiency
    1.00
    capacity
    0.97
    ensity
    0.97
     productivity
    0.97
     incidence
    0.96
     rates
    0.96
     burden
    0.96
     burdens
    0.95
    Act Density 0.353%

    No Known Activations