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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions, statements, and reactions made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements that involve condemnation or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    effic
    -0.73
    population
    -0.73
    iencies
    -0.73
    iage
    -0.72
     biodiversity
    -0.71
    rosis
    -0.70
     gangs
    -0.70
     specialization
    -0.69
     sexes
    -0.68
    itaire
    -0.68
    POSITIVE LOGITS
     uttered
    1.33
     echoed
    1.20
     echoing
    1.03
     rhetorical
    1.01
     conveyed
    1.00
     misinterpret
    0.99
     reson
    0.98
     retweet
    0.98
     tone
    0.98
     prophetic
    0.97
    Act Density 0.471%

    No Known Activations