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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.12
    2:0.04
    3:0.06
    4:0.19
    5:0.05
    6:0.08
    7:0.02
    8:0.07
    9:0.08
    10:0.09
    11:0.05
    Negative Logits
    condition
    -2.09
    ":
    -2.01
    ISION
    -1.91
    inventoryQuantity
    -1.91
     unden
    -1.86
    notations
    -1.84
    ilogy
    -1.84
    onda
    -1.82
    cry
    -1.82
    Fram
    -1.81
    POSITIVE LOGITS
    uggest
    2.64
     resorted
    2.24
     undertook
    2.15
     maintains
    2.11
     exert
    2.07
     reminded
    2.01
     wrote
    1.99
     regularly
    1.94
     complained
    1.93
     reminds
    1.91
    Act Density 0.040%

    No Known Activations