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

    Neuronpedia

    INDEX
    Explanations

    terms related to approval and endorsement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ums
    -0.16
    gow
    -0.14
    uten
    -0.14
    Ь
    -0.14
    race
    -0.14
    å¸Ī
    -0.14
    alog
    -0.14
    -browser
    -0.14
    Advisor
    -0.14
    udiantes
    -0.13
    POSITIVE LOGITS
    ably
    0.20
    able
    0.19
    ance
    0.18
    /lic
    0.17
    -ÑĤаки
    0.15
    zech
    0.15
    edList
    0.15
    ANCE
    0.14
    ABLE
    0.14
    atsapp
    0.14
    Act Density 0.018%

    No Known Activations