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

    Neuronpedia

    INDEX
    Explanations

    second person pronouns that directly address the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untas
    -0.17
    ibt
    -0.15
    olist
    -0.14
    rous
    -0.14
    rp
    -0.14
    .getRaw
    -0.14
    aug
    -0.14
     Æ°u
    -0.14
    bons
    -0.14
    auge
    -0.14
    POSITIVE LOGITS
    kil
    0.17
    avr
    0.17
    ths
    0.17
    Tube
    0.15
    ảo
    0.14
    fulness
    0.14
    interp
    0.14
    ãĥ©ãĥĥãĤ¯
    0.14
     Sorted
    0.14
    ediator
    0.14
    Act Density 0.070%

    No Known Activations