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

    Neuronpedia

    INDEX
    Explanations

    words related to restructuring or reorganizing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.83
    SHIP
    -0.71
    etheless
    -0.68
    theless
    -0.65
     Labrador
    -0.64
    DragonMagazine
    -0.64
    tips
    -0.63
     Guilty
    -0.63
    gom
    -0.62
     Fr
    -0.62
    POSITIVE LOGITS
    uling
    1.09
    aped
    1.07
    aping
    0.99
     resh
    0.99
    uler
    0.97
    ape
    0.96
    atche
    0.92
    oles
    0.91
    atters
    0.90
    ooting
    0.89
    Act Density 0.015%

    No Known Activations