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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugs
    -0.17
    byn
    -0.17
    odge
    -0.16
    FO
    -0.15
    _FOREACH
    -0.15
    \Doctrine
    -0.14
    linger
    -0.14
    è¢ĸ
    -0.14
    ÙĪÙĦÙĩ
    -0.14
    COD
    -0.14
    POSITIVE LOGITS
    aten
    0.16
    hiba
    0.14
    ough
    0.14
    oldem
    0.14
    êµIJ
    0.14
     Reception
    0.14
     Vig
    0.14
    vá
    0.14
     Suc
    0.13
    γμα
    0.13
    Act Density 0.005%

    No Known Activations