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

    Neuronpedia

    INDEX
    Explanations

    phrases related to roles and identities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quam
    -0.14
     cref
    -0.13
    lý
    -0.13
    ÃĦŸ
    -0.13
    pcl
    -0.13
    üc
    -0.13
    pga
    -0.13
    xba
    -0.13
     kia
    -0.13
    mür
    -0.13
    POSITIVE LOGITS
     âĢ¦↵
    0.23
    âĢ¦↵
    0.22
     “âĢ¦
    0.18
     ...↵
    0.18
     âĢ¦
    0.17
    âĢ¦
    0.16
    ÂŃing
    0.15
    âĢIJ
    0.15
    âĢ¦↵↵↵
    0.15
    ...↵
    0.14
    Act Density 3.401%

    No Known Activations