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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "dogs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhn
    -0.15
    RG
    -0.15
    bjerg
    -0.14
     RG
    -0.14
    onia
    -0.14
     Aff
    -0.14
     aff
    -0.14
    bury
    -0.14
     libertin
    -0.13
    Ù¹
    -0.13
    POSITIVE LOGITS
     Gotham
    0.17
    edor
    0.16
    edBy
    0.16
    ystack
    0.16
    ]=>
    0.16
    UPLE
    0.15
    emen
    0.15
    ey
    0.15
    uds
    0.15
    .scalablytyped
    0.15
    Act Density 0.006%

    No Known Activations