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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "compared," indicating comparisons between different items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ship
    -0.16
    roti
    -0.15
    GU
    -0.14
    ambre
    -0.14
    ordes
    -0.14
    readcr
    -0.14
    ful
    -0.14
     automát
    -0.13
    istr
    -0.13
    ãģ¤ãģ¶
    -0.13
    POSITIVE LOGITS
    etto
    0.17
    eker
    0.16
    aeda
    0.15
    olly
    0.14
    unga
    0.14
    unto
    0.14
    reon
    0.13
    OLON
    0.13
    adero
    0.13
    fy
    0.13
    Act Density 0.014%

    No Known Activations