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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating mathematical definitions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oro
    -0.18
     Bol
    -0.15
    ÑģÑĤи
    -0.15
     elucid
    -0.15
     Prim
    -0.15
    koli
    -0.14
    ilies
    -0.14
     den
    -0.14
    ãĤ¹ãĤ«
    -0.14
    ÑĥÑĪ
    -0.14
    POSITIVE LOGITS
     approximately
    0.21
    approximately
    0.19
     recover
    0.18
     diagonal
    0.18
     Approximately
    0.17
     cast
    0.17
     param
    0.17
     Recover
    0.17
     accom
    0.16
     construct
    0.16
    Act Density 0.092%

    No Known Activations