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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, particularly Rex Tillerson and James Mattis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¦
    -0.86
    lihood
    -0.81
    âĸ¬
    -0.72
    VID
    -0.71
    ibli
    -0.68
    ãĥ©
    -0.68
    irc
    -0.67
    Irish
    -0.67
     à¨
    -0.67
    Interstitial
    -0.66
    POSITIVE LOGITS
     Tillerson
    1.40
     Jinping
    1.05
    igon
    0.89
    ongyang
    0.87
    achev
    0.84
    rolet
    0.81
    enei
    0.80
    psey
    0.79
    ascus
    0.77
    ython
    0.77
    Act Density 0.005%

    No Known Activations