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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a future event or action

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding future events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     drafts
    -0.66
     Advertisement
    -0.66
     Perspective
    -0.64
     perce
    -0.64
    quickShipAvailable
    -0.62
     Respons
    -0.60
     endings
    -0.60
    pointers
    -0.60
     Programming
    -0.58
    sports
    -0.58
    POSITIVE LOGITS
    ggles
    0.95
     accommodate
    0.92
    pload
    0.91
    dden
    0.89
    lled
    0.85
     meet
    0.83
     liberate
    0.83
    LEASE
    0.83
     eliminate
    0.82
     be
    0.81
    Act Density 0.080%

    No Known Activations