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

    Neuronpedia

    INDEX
    Explanations

    prominent individuals and groups within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.28
    2:0.04
    3:0.03
    4:0.03
    5:0.23
    6:0.03
    7:0.02
    8:0.07
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     Benefit
    -1.85
     independents
    -1.74
     NCT
    -1.66
    .–
    -1.63
     Integrity
    -1.62
    rir
    -1.62
     Outs
    -1.60
    arus
    -1.57
    usra
    -1.56
     Thieves
    -1.56
    POSITIVE LOGITS
     wrote
    2.30
    zinski
    2.07
    wrote
    1.99
    Written
    1.96
    artz
    1.95
     scrib
    1.94
    tml
    1.90
     penned
    1.89
     quoted
    1.81
     writes
    1.78
    Act Density 0.006%

    No Known Activations