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

    Neuronpedia

    INDEX
    Explanations

    the word "to" in various contexts, indicating its prevalence or grammatical function in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    au
    -0.18
    naire
    -0.17
    ford
    -0.17
    ĥn
    -0.17
    udu
    -0.16
    usive
    -0.16
    uit
    -0.16
    ro
    -0.15
    up
    -0.15
    173
    -0.15
    POSITIVE LOGITS
    hiba
    0.21
     whom
    0.21
    ledo
    0.19
    aster
    0.19
    oldown
    0.19
    è¾¾
    0.18
    onces
    0.18
    iler
    0.18
    ilers
    0.18
    å¤Ħ
    0.17
    Act Density 0.061%

    No Known Activations