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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating professional experience and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Becker
    -0.16
    elson
    -0.15
    ring
    -0.15
     Nil
    -0.15
     Ham
    -0.14
    Nil
    -0.14
     Mir
    -0.14
     union
    -0.14
    оÑĢо
    -0.14
     Hann
    -0.14
    POSITIVE LOGITS
    aign
    0.19
    lfw
    0.15
    EDIA
    0.15
     CreateMap
    0.15
    à¥ģà¤
    0.14
    .idea
    0.14
    ë§ī
    0.14
     Yön
    0.14
    UNCH
    0.14
    unch
    0.14
    Act Density 0.288%

    No Known Activations