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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inalg
    -0.15
    ãĥ³ãĤ¯
    -0.15
    èĪį
    -0.14
    ¯u
    -0.14
    ÏĦη
    -0.14
    erdem
    -0.14
    âk
    -0.14
    ÐIJÐł
    -0.13
     dán
    -0.13
    .substr
    -0.13
    POSITIVE LOGITS
    (L
    0.17
    urette
    0.17
     l
    0.15
    (Log
    0.15
    arn
    0.15
     LU
    0.15
     rec
    0.15
    /L
    0.15
     cub
    0.14
    (LP
    0.14
    Act Density 0.192%

    No Known Activations