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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Congress"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Congress and parliament

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VALUE
    -0.74
    Var
    -0.68
     Lov
    -0.66
     hump
    -0.64
     Reincarn
    -0.63
    STD
    -0.63
    Reloaded
    -0.61
    Magic
    -0.60
    ãĤ´ãĥ³
    -0.59
    rex
    -0.59
    POSITIVE LOGITS
    hips
    0.81
     indicted
    0.68
     accredited
    0.67
    hare
    0.66
     who
    0.64
     revoked
    0.64
     alike
    0.63
     testifying
    0.62
    interstitial
    0.62
     representing
    0.60
    Act Density 0.038%

    No Known Activations