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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owell
    -0.16
    IGIN
    -0.16
    zza
    -0.15
    illo
    -0.15
    asje
    -0.15
    _TestCase
    -0.14
    oomla
    -0.14
    ÃŃky
    -0.14
    ủng
    -0.14
     toler
    -0.14
    POSITIVE LOGITS
     Biden
    0.27
     Delaware
    0.26
     Beau
    0.23
     Joe
    0.22
     Wilmington
    0.21
     Vice
    0.20
     VP
    0.20
     vice
    0.20
     Hunter
    0.20
     Scr
    0.19
    Act Density 0.019%

    No Known Activations