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

    Neuronpedia

    INDEX
    Explanations

    concepts related to control and power dynamics in various systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubre
    -0.19
    æı´
    -0.16
     Müz
    -0.14
    tık
    -0.14
    WP
    -0.14
    anio
    -0.14
    ub
    -0.14
    bor
    -0.13
    AEA
    -0.13
    367
    -0.13
    POSITIVE LOGITS
     reserved
    0.22
     belongs
    0.22
    å½Ĵ
    0.21
     ÙĨص
    0.20
    reserved
    0.20
     transfer
    0.19
     reserv
    0.19
    å±ŀäºİ
    0.19
     handed
    0.18
    Reserved
    0.18
    Act Density 0.244%

    No Known Activations