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

    Neuronpedia

    INDEX
    Explanations

    terms related to addiction or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.29
    plier
    -0.28
    Ø©
    -0.26
    thing
    -0.24
    ember
    -0.23
    ible
    -0.22
    ت
    -0.21
    aurant
    -0.21
    istrator
    -0.20
    à¸ģาร
    -0.19
    POSITIVE LOGITS
    uards
    0.18
     Wolff
    0.18
    ../../../
    0.15
    tÃŃ
    0.15
    days
    0.15
    íļĮìĿĺ
    0.15
    umbn
    0.15
    UNET
    0.14
    uzey
    0.14
    e
    0.14
    Act Density 0.390%

    No Known Activations