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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "ar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endor
    -0.17
    ãĥ¥
    -0.16
    gos
    -0.15
    urb
    -0.15
    awy
    -0.15
     Schul
    -0.15
    plex
    -0.14
    itters
    -0.14
    kil
    -0.14
    bru
    -0.14
    POSITIVE LOGITS
    PFN
    0.17
    untime
    0.17
    ónico
    0.14
    aji
    0.14
    heid
    0.14
    CEPTION
    0.14
    beiter
    0.14
    ierz
    0.13
    é¸
    0.13
     Rue
    0.13
    Act Density 0.086%

    No Known Activations