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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers related to scientific publications or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orz
    -0.16
    ãĥ³ãĥĶ
    -0.15
    WG
    -0.15
    arra
    -0.15
    óc
    -0.14
    bout
    -0.14
    assi
    -0.14
     Verm
    -0.14
    ogi
    -0.14
    erah
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĤ¹
    0.16
    edException
    0.15
    745
    0.14
     OMIT
    0.14
    657
    0.13
     Sanford
    0.13
     Miz
    0.13
    é±
    0.13
     successor
    0.13
    ancel
    0.13
    Act Density 0.009%

    No Known Activations