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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant numerical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aroo
    -0.18
    ies
    -0.15
    ep
    -0.15
    ÑĨе
    -0.15
    graf
    -0.15
    aben
    -0.15
    108
    -0.15
     Ying
    -0.14
    ÑĢалÑĮ
    -0.14
    Stmt
    -0.14
    POSITIVE LOGITS
    oq
    0.18
    oque
    0.16
    çªģ
    0.15
    SSIP
    0.15
    iable
    0.15
    ettel
    0.15
    icias
    0.15
    enment
    0.15
    ials
    0.15
     plate
    0.15
    Act Density 0.001%

    No Known Activations