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

    Neuronpedia

    INDEX
    Explanations

    words related to computer programming or technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "yp" and similar variations across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.76
    creen
    -0.70
     Templar
    -0.67
    wagon
    -0.66
    ved
    -0.65
     Canal
    -0.65
    Va
    -0.64
    piece
    -0.63
     Meditation
    -0.63
     Reb
    -0.63
    POSITIVE LOGITS
    posium
    0.91
    enic
    0.86
    ensions
    0.85
    ical
    0.82
    onymous
    0.80
    nosis
    0.79
    asta
    0.79
    gments
    0.79
    atl
    0.78
    orkshire
    0.78
    Act Density 0.043%

    No Known Activations