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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completion or ending of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.70
     AMA
    -0.69
     circles
    -0.68
     Readers
    -0.65
    =-=-=-=-
    -0.65
    osity
    -0.64
    Gs
    -0.62
     greets
    -0.62
     portrays
    -0.62
     interacts
    -0.61
    POSITIVE LOGITS
    rated
    1.15
    kill
    1.07
    priced
    1.06
    awed
    1.04
    blown
    1.03
    loading
    0.96
    haul
    0.95
    grown
    0.94
    stated
    0.93
    reaching
    0.92
    Act Density 0.042%

    No Known Activations