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

    Neuronpedia

    INDEX
    Explanations

    words related to motivation and persuasive arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.09
    3:0.10
    4:0.26
    5:0.02
    6:0.07
    7:0.17
    8:0.03
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    ationally
    -1.57
     sqor
    -1.48
    ioch
    -1.47
     withd
    -1.44
    oaded
    -1.39
    culosis
    -1.36
    pora
    -1.36
    utenberg
    -1.35
    enary
    -1.35
    QL
    -1.34
    POSITIVE LOGITS
     Krypt
    1.55
     magazines
    1.54
     sarc
    1.53
     Chemistry
    1.52
     weeds
    1.52
     Tant
    1.42
     Doomsday
    1.40
     ashes
    1.39
     towels
    1.38
     Brill
    1.36
    Act Density 0.003%

    No Known Activations