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

    Neuronpedia

    INDEX
    Explanations

    terms indicating significant changes or impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.94
     Rooms
    -0.92
    redients
    -0.87
    tags
    -0.87
    coins
    -0.87
    rooms
    -0.87
    Tickets
    -0.86
    stories
    -0.86
    speak
    -0.84
    mates
    -0.84
    POSITIVE LOGITS
     uptick
    1.29
     resurgence
    1.24
     crackdown
    1.14
     shortage
    1.14
     deterioration
    1.14
     backlash
    1.12
     rethink
    1.11
     spate
    1.11
     influx
    1.10
     decline
    1.10
    Act Density 0.155%

    No Known Activations