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

    Neuronpedia

    INDEX
    Explanations

    information about strained relationships or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impending change or disruption in relationships or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.62
     auxiliary
    -0.56
     maneu
    -0.54
    anan
    -0.53
     anonym
    -0.53
     advoc
    -0.53
     subcontract
    -0.50
     helpers
    -0.50
     organizing
    -0.50
     paras
    -0.50
    POSITIVE LOGITS
     anytime
    1.21
     anymore
    1.18
     someday
    1.08
     sooner
    0.99
    unless
    0.95
     foreseeable
    0.92
     tomorrow
    0.87
     unless
    0.85
     EVER
    0.84
    soon
    0.83
    Act Density 0.776%

    No Known Activations