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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emphasizing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icons
    -0.98
    hens
    -0.95
    hops
    -0.84
    ridges
    -0.83
    renches
    -0.80
    ournaments
    -0.79
    packages
    -0.79
    anches
    -0.78
    icles
    -0.78
    brates
    -0.78
    POSITIVE LOGITS
     trend
    1.15
     notion
    1.06
     sentiment
    1.06
     phenomenon
    1.05
     tendency
    1.05
     aspect
    1.02
     assumption
    1.01
     limitation
    1.00
     distinction
    1.00
     latter
    0.99
    Act Density 0.168%

    No Known Activations