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

    Neuronpedia

    INDEX
    Explanations

    calls to action and encouragements for community engagement

    oai_token-act-pair · gpt-3.5-turbo

    calls to action and engagement prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omas
    -0.67
    axter
    -0.64
    oglu
    -0.63
     appell
    -0.61
    istani
    -0.60
     interpre
    -0.59
     Enlight
    -0.59
    sterdam
    -0.58
     Helpful
    -0.58
     McMaster
    -0.58
    POSITIVE LOGITS
    Feel
    0.90
    Actor
    0.87
    Trend
    0.86
    Loading
    0.82
    Prev
    0.81
    Learn
    0.80
    Hide
    0.78
    Please
    0.78
    Subscribe
    0.77
    Discover
    0.76
    Act Density 0.093%

    No Known Activations