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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the word "my" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.16
    åŃĿ
    -0.16
     pig
    -0.15
    oves
    -0.15
    ries
    -0.15
    ible
    -0.15
    gan
    -0.14
    pig
    -0.14
    agen
    -0.14
    s
    -0.14
    POSITIVE LOGITS
     own
    0.19
    own
    0.16
    adow
    0.16
    shake
    0.15
    ombine
    0.15
    Own
    0.15
    lyn
    0.15
    èŃ
    0.14
     Shore
    0.14
    ä¸Ģ页
    0.14
    Act Density 0.051%

    No Known Activations