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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals named "Joe" with varying degrees of significance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    NESS
    -0.89
    hips
    -0.87
     glim
    -0.78
    igators
    -0.75
    igated
    -0.73
    mble
    -0.72
    ancies
    -0.70
    iments
    -0.68
    chwitz
    -0.68
     narrator
    -0.67
    POSITIVE LOGITS
     Biden
    0.96
    ppo
    0.92
    pport
    0.89
     Arpaio
    0.87
    zzi
    0.83
     Camel
    0.82
    xtap
    0.81
     Rog
    0.80
     Lieberman
    0.79
    xon
    0.79
    Act Density 0.016%

    No Known Activations