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

    Neuronpedia

    INDEX
    Explanations

    phrases related to topics of high importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or crucial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.91
     Carbuncle
    -0.78
    Kay
    -0.75
     Leone
    -0.73
    uated
    -0.72
    fred
    -0.71
     Fever
    -0.71
    artney
    -0.70
    Shock
    -0.69
    ulia
    -0.69
    POSITIVE LOGITS
     distinction
    1.05
     distinctions
    0.97
     milestone
    0.95
     ingredient
    0.89
     milestones
    0.89
     role
    0.88
     decisions
    0.87
     breakthrough
    0.87
     constituent
    0.87
     aspects
    0.86
    Act Density 0.107%

    No Known Activations