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

    Neuronpedia

    INDEX
    Explanations

    entities and significant names related to politics and medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reelection
    -0.18
    azz
    -0.18
     Rever
    -0.16
    ucker
    -0.16
     okay
    -0.15
     versus
    -0.14
     coworkers
    -0.14
    ãĥ¼ãĥĸ
    -0.14
     stead
    -0.14
    unix
    -0.14
    POSITIVE LOGITS
     Mr
    0.28
    Mr
    0.24
     Ms
    0.21
     Calif
    0.18
    Ms
    0.18
     Gov
    0.17
    ble
    0.16
    igli
    0.15
     Mrs
    0.15
    -care
    0.15
    Act Density 0.071%

    No Known Activations