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

    Neuronpedia

    INDEX
    Explanations

    expressions related to advancements and achievements in academia and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.16
    ou
    -0.16
    ellen
    -0.15
    á»ģ
    -0.15
    ancellor
    -0.14
    son
    -0.14
    arse
    -0.14
    èĤ
    -0.14
    ise
    -0.13
    nel
    -0.13
    POSITIVE LOGITS
    iculty
    0.17
    hiba
    0.16
    stras
    0.15
    ltra
    0.15
    illance
    0.15
    ezier
    0.15
    _AF
    0.14
    ecast
    0.14
    ÅĻÃŃž
    0.14
    jar
    0.14
    Act Density 2.063%

    No Known Activations