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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions, specifically focusing on Columbia University

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Columbia University

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cher
    -0.82
    chers
    -0.79
    hered
    -0.79
    olkien
    -0.74
    lessly
    -0.73
    esthetic
    -0.70
    visor
    -0.70
    ched
    -0.67
    rha
    -0.67
    odic
    -0.67
    POSITIVE LOGITS
     Heights
    1.08
     Pictures
    1.08
     Journalism
    1.02
     River
    1.02
     Broadcasting
    0.98
     University
    0.89
     Gorge
    0.88
     Harbor
    0.84
     Crew
    0.83
     Canal
    0.83
    Act Density 0.036%

    No Known Activations