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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to age, time, or generational distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.72
     photographer
    -0.54
     visitor
    -0.53
     skeptics
    -0.52
     reintrodu
    -0.51
     CMS
    -0.50
     sporting
    -0.50
     fencing
    -0.50
     «
    -0.50
     Eric
    -0.49
    POSITIVE LOGITS
    ãĥĺ
    0.75
    Jr
    0.71
    -|
    0.71
    _{
    0.66
    ))))
    0.65
    }.
    0.65
    zon
    0.64
    "/>
    0.64
    âĶĢâĶĢâĶĢâĶĢ
    0.64
    vil
    0.63
    Act Density 0.602%

    No Known Activations