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

    Neuronpedia

    INDEX
    Explanations

    terms associated with legal or bureaucratic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     m
    -0.18
    gor
    -0.16
     pomp
    -0.15
    KT
    -0.15
     va
    -0.15
     Hollow
    -0.15
     foul
    -0.14
     n
    -0.14
     formal
    -0.14
    ello
    -0.14
    POSITIVE LOGITS
    лÑİ
    0.19
    odyn
    0.17
    å¼
    0.16
    -alist
    0.16
    retty
    0.16
    defgroup
    0.15
    bose
    0.15
    anship
    0.15
    ampie
    0.14
    ÌĨ
    0.14
    Act Density 0.012%

    No Known Activations