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

    Neuronpedia

    INDEX
    Explanations

    occurrences of events marking the beginning or end of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant milestones or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     polled
    -0.79
     depended
    -0.69
     consulted
    -0.69
     smelled
    -0.68
     depends
    -0.67
     inquired
    -0.65
     cared
    -0.65
    queue
    -0.64
     Wouldn
    -0.64
     Supported
    -0.64
    POSITIVE LOGITS
     culmination
    1.30
     beginning
    1.22
     pinnacle
    1.21
     departure
    1.17
     beginnings
    1.07
     arrival
    1.06
     rebirth
    1.06
     continuation
    1.03
     milestone
    1.00
     emergence
    0.99
    Act Density 0.100%

    No Known Activations