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

    Neuronpedia

    INDEX
    Explanations

    words ending in 'ier' or 'iest'

    oai_token-act-pair · gpt-3.5-turbo

    comparative adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unexplained
    -0.70
     NCT
    -0.62
     expired
    -0.59
     minds
    -0.56
     persons
    -0.54
     womb
    -0.53
     Latest
    -0.53
     constant
    -0.53
     bu
    -0.53
     coinc
    -0.53
    POSITIVE LOGITS
    ier
    4.46
    iers
    3.04
    iest
    2.48
    IER
    2.37
    iness
    2.09
    iere
    2.06
    ily
    1.97
    ieri
    1.91
    lier
    1.61
    iera
    1.45
    Act Density 0.020%

    No Known Activations