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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to specific events happening sequentially

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to narrative transitions and events in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Had
    -0.92
    oided
    -0.88
     depended
    -0.84
     existed
    -0.83
     lacked
    -0.83
     benefited
    -0.83
     constituted
    -0.82
     mattered
    -0.81
     differed
    -0.80
     relied
    -0.79
    POSITIVE LOGITS
     begins
    1.17
     emerges
    1.14
     announces
    1.12
     realizes
    1.09
     yells
    1.09
     decides
    1.08
     disappears
    1.08
     arrives
    1.08
     enters
    1.04
     explodes
    1.03
    Act Density 0.520%

    No Known Activations