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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting and citation in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upply
    -0.16
    asia
    -0.16
    cairo
    -0.14
    æ²ī
    -0.14
    liqu
    -0.14
    زاÙħ
    -0.14
    implify
    -0.14
    615
    -0.14
    autoload
    -0.13
    chemist
    -0.13
    POSITIVE LOGITS
     \/
    0.15
    νÏĮ
    0.15
    å´
    0.15
    rene
    0.14
    izi
    0.13
    igits
    0.13
    blers
    0.13
    ionales
    0.13
    IDES
    0.13
    à¹Ģสà¸Ļ
    0.13
    Act Density 0.058%

    No Known Activations