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

    Neuronpedia

    INDEX
    Explanations

    phrases describing something as the most important or final

    oai_token-act-pair · gpt-3.5-turbo

    Repeated mentions of the word "ultimate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bars
    -0.81
    ades
    -0.79
    ker
    -0.76
    rooms
    -0.74
    ohn
    -0.74
    crow
    -0.74
    then
    -0.73
    etimes
    -0.73
    iths
    -0.72
    oles
    -0.70
    POSITIVE LOGITS
     gratification
    1.03
     prize
    0.96
     goal
    0.90
     obstacle
    0.86
     culmination
    0.86
     embodiment
    0.84
     showdown
    0.79
     irony
    0.79
     pinnacle
    0.78
     insult
    0.77
    Act Density 0.038%

    No Known Activations