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

    Neuronpedia

    INDEX
    Explanations

    people's first instances of certain experiences or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mund
    -0.83
    facts
    -0.74
    bara
    -0.72
    etics
    -0.71
     Canaver
    -0.70
    skirts
    -0.70
    bos
    -0.68
    holes
    -0.68
    ourge
    -0.66
     Vish
    -0.66
    POSITIVE LOGITS
     foray
    1.25
     outing
    0.97
     responders
    0.95
     baseman
    0.95
     incarnation
    0.90
     attempt
    0.89
     glimpse
    0.88
     batch
    0.87
     glance
    0.87
     lady
    0.86
    Act Density 0.046%

    No Known Activations