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

    Neuronpedia

    INDEX
    Explanations

    statements related to governance and leadership decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eree
    -0.17
    adla
    -0.17
    _ITER
    -0.15
     Woj
    -0.15
    istics
    -0.14
    meer
    -0.14
     condem
    -0.14
    isle
    -0.13
    istas
    -0.13
    çī
    -0.13
    POSITIVE LOGITS
    cü
    0.15
    fsp
    0.15
     Kumar
    0.15
    à¸ķะ
    0.15
    -enable
    0.14
    olar
    0.14
    ãģıãģ¨
    0.14
    اتÛĮ
    0.14
    à¹Ĥà¸ģ
    0.14
    iki
    0.13
    Act Density 0.035%

    No Known Activations