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

    Neuronpedia

    INDEX
    Explanations

    comments or annotations in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aha
    -0.17
    yen
    -0.16
    ing
    -0.15
     Shel
    -0.14
    ying
    -0.14
     spell
    -0.13
    ingo
    -0.13
     Agenda
    -0.13
     Pru
    -0.13
    สาร
    -0.13
    POSITIVE LOGITS
    amus
    0.16
    ãĥ«ãĤ¯
    0.15
    abor
    0.14
    ë§ŀ
    0.14
    βο
    0.14
    lov
    0.14
    eÅŁ
    0.14
    onn
    0.14
    oplan
    0.14
    marsh
    0.14
    Act Density 0.006%

    No Known Activations