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

    Neuronpedia

    INDEX
    Explanations

    references to a specific publication, "The Toronto Star"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Star."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.91
    ĸļ
    -0.84
    ipop
    -0.82
    sembly
    -0.81
    ongyang
    -0.80
    ĵĺ
    -0.78
    ecause
    -0.78
    odcast
    -0.78
    terday
    -0.76
    essee
    -0.75
    POSITIVE LOGITS
    vation
    1.06
    bucks
    0.95
    ved
    0.95
    light
    0.92
    ring
    0.88
    burst
    0.86
    ving
    0.84
    fish
    0.83
    buck
    0.83
    lings
    0.78
    Act Density 0.022%

    No Known Activations