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

    Neuronpedia

    INDEX
    Explanations

    text prompting action such as clicking a link

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "click."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tions
    -0.84
    Ĥª
    -0.82
    wallet
    -0.76
    tests
    -0.74
    apesh
    -0.71
     fortun
    -0.70
    ĨĴ
    -0.70
    calling
    -0.70
    etheless
    -0.69
    testing
    -0.68
    POSITIVE LOGITS
     enlarge
    0.94
     learn
    0.86
     avoid
    0.85
     maximize
    0.85
     subscribe
    0.85
     view
    0.81
     activate
    0.80
     toggle
    0.78
     link
    0.77
     get
    0.77
    Act Density 0.138%

    No Known Activations