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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high demand or popularity

    oai_token-act-pair · gpt-3.5-turbo

    references to demand in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombs
    -0.69
     gru
    -0.69
    spection
    -0.67
     dece
    -0.64
     secrecy
    -0.63
     cath
    -0.63
     surprise
    -0.62
     Woods
    -0.62
     surprises
    -0.62
     deceive
    -0.59
    POSITIVE LOGITS
    demand
    1.22
    Demand
    1.01
    bnb
    0.97
     Demand
    0.89
    ware
    0.88
    hyde
    0.81
    ragon
    0.78
    immune
    0.73
    flix
    0.73
    assian
    0.73
    Act Density 0.015%

    No Known Activations