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

    Neuronpedia

    INDEX
    Explanations

    references to significant events and introductions related to specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emet
    -0.22
    eriod
    -0.20
    ustos
    -0.19
    adol
    -0.16
     cref
    -0.16
    Ī
    -0.15
     Incre
    -0.15
    ÑĢÑĥб
    -0.15
    нам
    -0.14
    erne
    -0.14
    POSITIVE LOGITS
    andro
    0.17
    ">//
    0.15
     bulk
    0.15
    adier
    0.14
     Rog
    0.14
    OTA
    0.14
     ab
    0.14
     ut
    0.13
    ÅĻes
    0.13
    so
    0.13
    Act Density 0.067%

    No Known Activations