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

    Neuronpedia

    INDEX
    Explanations

    references to providing services or options to consumers or users

    oai_token-act-pair · gpt-3.5-turbo

    terms related to users, consumers, and target audiences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tom
    -0.69
    Ń·
    -0.65
    Cooldown
    -0.63
    strip
    -0.62
    nder
    -0.59
    azar
    -0.59
    ignore
    -0.58
    appa
    -0.58
     Cosponsors
    -0.57
     incarcer
    -0.57
    POSITIVE LOGITS
     access
    1.10
     opportunities
    1.08
     alternatives
    1.04
     tools
    1.01
     options
    1.00
     incentives
    0.98
     ample
    0.97
     flexibility
    0.96
     insight
    0.94
     certainty
    0.93
    Act Density 0.105%

    No Known Activations