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

    Neuronpedia

    INDEX
    Explanations

    references to favorite things or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /xhtml
    -0.15
    taire
    -0.15
    -dismiss
    -0.15
    \<^
    -0.14
    ullo
    -0.14
    illon
    -0.14
    .gc
    -0.14
    ATUS
    -0.14
    celed
    -0.14
    ови
    -0.14
    POSITIVE LOGITS
    º
    0.21
    æ¯ķ
    0.16
    unker
    0.16
    omi
    0.14
    erte
    0.14
    astr
    0.14
    IVAL
    0.14
    place
    0.14
    kö
    0.13
    arde
    0.13
    Act Density 0.013%

    No Known Activations