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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific location, which is Columbia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Columbia."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esthetic
    -0.89
    odic
    -0.74
    cher
    -0.74
    chers
    -0.72
    ugal
    -0.71
    hered
    -0.71
    olkien
    -0.70
    visor
    -0.67
    ochemical
    -0.66
    ¯¯¯¯
    -0.66
    POSITIVE LOGITS
     Heights
    1.16
     Pictures
    0.98
     River
    0.92
     Broadcasting
    0.87
     Canal
    0.85
     Journalism
    0.84
     Pike
    0.81
     Gorge
    0.76
     Colleges
    0.76
     Skies
    0.74
    Act Density 0.030%

    No Known Activations