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

    Neuronpedia

    INDEX
    Explanations

    documents and articles related to various news, events, and topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of news articles, reports, and sources related to current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.08
    3:0.06
    4:0.03
    5:0.05
    6:0.08
    7:0.02
    8:0.36
    9:0.08
    10:0.06
    11:0.02
    Negative Logits
    peat
    -1.62
     apologize
    -1.55
     salute
    -1.49
     forgotten
    -1.47
    blooded
    -1.47
     unnoticed
    -1.43
     apologise
    -1.43
     untouched
    -1.42
     closet
    -1.42
    ardless
    -1.39
    POSITIVE LOGITS
    glers
    1.82
     Vance
    1.60
     Beir
    1.45
     Annotations
    1.44
    miah
    1.43
     HIP
    1.41
    ecd
    1.36
     Caldwell
    1.36
     Grape
    1.35
    alion
    1.32
    Act Density 0.109%

    No Known Activations