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

    Neuronpedia

    INDEX
    Explanations

    archaeological descriptions with information about visibility and distance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     abstinence
    -0.71
    íķ
    -0.70
    allo
    -0.65
    olics
    -0.63
     oblig
    -0.62
     obligated
    -0.61
    bush
    -0.61
    ente
    -0.60
     morals
    -0.59
     endorsed
    -0.59
    POSITIVE LOGITS
     afar
    1.15
     ultraviolet
    1.05
     photograph
    1.03
    phot
    1.03
     photographs
    1.03
     infrared
    1.01
     screenshots
    1.01
     webcam
    0.98
     silhouette
    0.97
     footage
    0.96
    Act Density 0.429%

    No Known Activations