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

    Neuronpedia

    INDEX
    Explanations

    mentions of various universities

    oai_token-act-pair · gpt-3.5-turbo

    references to universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.74
    adesh
    -0.67
     deductions
    -0.67
     vectors
    -0.67
    downs
    -0.66
    itiveness
    -0.65
     claws
    -0.65
     blot
    -0.64
     combust
    -0.64
     matt
    -0.64
    POSITIVE LOGITS
     Sao
    0.92
     Ot
    0.87
     Notre
    0.84
     California
    0.84
     Rochester
    0.83
     Tokyo
    0.82
     Pennsylvania
    0.81
     Warwick
    0.81
     Southern
    0.80
     Chicago
    0.79
    Act Density 0.048%

    No Known Activations