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

    Neuronpedia

    INDEX
    Explanations

    references to Donald Trump and his campaign

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.80
     ILCS
    -0.76
     à¨
    -0.74
     captcha
    -0.70
    alys
    -0.69
    tml
    -0.68
    ãĤ¹ãĥĪ
    -0.66
    BILITY
    -0.65
    Ú
    -0.63
     Flavoring
    -0.63
    POSITIVE LOGITS
    Care
    1.01
     Jr
    0.99
    care
    0.97
     aides
    0.92
     Tower
    0.91
     confid
    0.89
     surrog
    0.89
     surrogate
    0.86
     supporters
    0.82
     supporter
    0.81
    Act Density 0.046%

    No Known Activations