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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, particularly presidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, particularly President Obama

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MJ
    -0.76
    PsyNetMessage
    -0.73
    driving
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
     Sleeping
    -0.65
    ãĤ¯
    -0.65
    MpServer
    -0.63
    NP
    -0.62
    coins
    -0.61
    Sov
    -0.60
    POSITIVE LOGITS
     vetoed
    1.01
     congratulated
    0.94
     appoint
    0.88
     Jinping
    0.85
     appointed
    0.85
     greeted
    0.84
    ÃŃs
    0.83
     dispatched
    0.83
     thanked
    0.81
     praised
    0.81
    Act Density 0.095%

    No Known Activations