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

    Neuronpedia

    INDEX
    Explanations

    references to time constraints or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    илÑı
    -0.15
    azzi
    -0.15
     mojo
    -0.14
    ppelin
    -0.14
    stial
    -0.14
    ngth
    -0.14
    APPER
    -0.14
    eniable
    -0.13
    cff
    -0.13
    anas
    -0.13
    POSITIVE LOGITS
     pro
    0.15
    祥
    0.15
     detached
    0.15
     pec
    0.14
    lev
    0.14
    .liferay
    0.14
     away
    0.14
    ingle
    0.14
    opleft
    0.14
    728
    0.14
    Act Density 0.044%

    No Known Activations