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

    Neuronpedia

    INDEX
    Explanations

    words related to blogs or blogging

    oai_token-act-pair · gpt-3.5-turbo

    references to cognitive processes or concepts related to the mind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.81
     Leilan
    -0.67
    IDENT
    -0.66
    staking
    -0.66
    ensional
    -0.66
     inadequ
    -0.60
     calculus
    -0.59
    birth
    -0.59
    PRES
    -0.58
    wcs
    -0.57
    POSITIVE LOGITS
    gers
    1.25
    roup
    1.20
    glers
    1.18
    roups
    1.17
    allery
    1.12
    gy
    1.11
    ues
    1.08
    raphic
    1.06
    lio
    1.00
    raphics
    0.99
    Act Density 0.027%

    No Known Activations