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

    Neuronpedia

    INDEX
    Explanations

    political figures and their positions or relationships with other political entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.23
    ัพท์
    -0.59
    OPHER
    -0.55
    __*/
    -0.51
     wideo
    -0.51
     Kohlen
    -0.51
    tagHelperRunner
    -0.50
    entery
    -0.50
    orrhea
    -0.49
     iNdEx
    -0.49
    POSITIVE LOGITS
     Juf
    1.34
     Rine
    1.32
     Keny
    1.20
     Bartholo
    1.17
     McLaugh
    1.14
     McInt
    1.13
     Augu
    1.13
     Righ
    1.12
     Hez
    1.10
     Vaugh
    1.08
    Act Density 0.410%

    No Known Activations