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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or governmental concepts and documents

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts related to lists or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ason
    -0.67
    zar
    -0.67
    esar
    -0.66
    bard
    -0.66
    hart
    -0.64
    :(
    -0.63
    eks
    -0.63
    aldo
    -0.63
    ETS
    -0.63
    achy
    -0.62
    POSITIVE LOGITS
     etc
    0.95
     assorted
    0.94
    etc
    0.82
     possibly
    0.80
     yes
    0.70
     consequ
    0.68
    ospace
    0.67
     carbohyd
    0.65
     optionally
    0.64
     other
    0.64
    Act Density 0.189%

    No Known Activations