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

    Neuronpedia

    INDEX
    Explanations

    expressions related to creation or imagination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.09
    3:0.19
    4:0.03
    5:0.03
    6:0.07
    7:0.06
    8:0.05
    9:0.19
    10:0.07
    11:0.10
    Negative Logits
    anwhile
    -1.57
     incentiv
    -1.47
    ailability
    -1.41
     discretion
    -1.27
    seek
    -1.25
     turnover
    -1.18
    commit
    -1.17
    leneck
    -1.15
    ocre
    -1.15
     spons
    -1.15
    POSITIVE LOGITS
     Mata
    1.39
    �
    1.38
     FANTASY
    1.38
     Ghosts
    1.36
     QUEST
    1.22
     Flames
    1.20
     Yates
    1.20
     Poc
    1.17
     Zi
    1.16
     IL
    1.15
    Act Density 0.001%

    No Known Activations