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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.27
    3:0.09
    4:0.16
    5:0.06
    6:0.03
    7:0.02
    8:0.07
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
     eleph
    -1.63
    rador
    -1.44
    ilial
    -1.35
    ム
    -1.34
    ascript
    -1.32
    arial
    -1.30
    ertation
    -1.23
    rities
    -1.23
    etheless
    -1.22
    bidden
    -1.19
    POSITIVE LOGITS
    EStream
    1.34
    anski
    1.29
    hole
    1.27
    gger
    1.21
    orthy
    1.21
     Lumpur
    1.17
    oman
    1.17
     Mercenary
    1.16
    nova
    1.16
    oslav
    1.15
    Act Density 0.003%

    No Known Activations