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

    Neuronpedia

    INDEX
    Explanations

    descriptive words related to health and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.15
    до
    -0.15
    etes
    -0.14
     Vladim
    -0.14
    utin
    -0.14
     encount
    -0.14
     Slee
    -0.14
    anik
    -0.13
     Ekim
    -0.13
     áº
    -0.13
    POSITIVE LOGITS
    Ñģли
    0.15
    ãĤ¤ãĥ³ãĥĪ
    0.15
    oter
    0.14
    cem
    0.14
     recall
    0.14
     pos
    0.14
    ocus
    0.13
     mdl
    0.13
     Omni
    0.13
    ìŀIJ기
    0.13
    Act Density 0.004%

    No Known Activations