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

    Neuronpedia

    INDEX
    Explanations

    instances of repetition and related terms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erea
    -0.15
    akin
    -0.15
    ought
    -0.14
    yz
    -0.14
    Ùħز
    -0.14
    ye
    -0.14
    pop
    -0.14
    yard
    -0.14
    okol
    -0.13
    link
    -0.13
    POSITIVE LOGITS
    ency
    0.16
    able
    0.15
    ìľ¨
    0.14
    ucci
    0.14
    ively
    0.14
    çı¾
    0.14
    ative
    0.14
    /single
    0.14
    ATTERN
    0.14
    μÏĢ
    0.14
    Act Density 0.032%

    No Known Activations