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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.18
    2:0.04
    3:0.05
    4:0.07
    5:0.03
    6:0.12
    7:0.04
    8:0.07
    9:0.04
    10:0.20
    11:0.03
    Negative Logits
     Honduras
    -1.99
     Hond
    -1.97
     Craigslist
    -1.97
     Papa
    -1.96
     Corinth
    -1.95
     Syri
    -1.94
    fax
    -1.89
     Guatem
    -1.88
     discont
    -1.83
     Antioch
    -1.82
    POSITIVE LOGITS
    ウス
    2.34
    Thumbnail
    2.02
    sson
    1.99
    oglu
    1.92
     antioxidant
    1.88
     versatile
    1.88
    rawdownloadcloneembedreportprint
    1.85
     greenhouse
    1.74
     photon
    1.74
    uclear
    1.73
    Act Density 0.002%

    No Known Activations