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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.71
     EntityItem
    -0.71
     Lanka
    -0.69
     Sharma
    -0.68
    HCR
    -0.67
     Shaw
    -0.65
    xes
    -0.65
     charms
    -0.65
     AVG
    -0.64
     Lumpur
    -0.63
    POSITIVE LOGITS
    issue
    1.13
    sized
    1.09
    themed
    1.04
    powered
    1.03
    exclusive
    1.00
    level
    0.99
    based
    0.98
    degree
    0.97
    centric
    0.97
    dollar
    0.96
    Act Density 0.367%

    No Known Activations