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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "To" or variations thereof, typically in the context of functions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ro
    -0.18
    up
    -0.18
    au
    -0.17
    wood
    -0.16
    t
    -0.16
    k
    -0.16
    173
    -0.16
    سÙĪ
    -0.16
     anc
    -0.15
    wy
    -0.15
    POSITIVE LOGITS
    xic
    0.22
    aster
    0.21
    oldown
    0.19
    /from
    0.18
    hiba
    0.18
    ledo
    0.18
    plevel
    0.18
    Ïģκ
    0.18
    è¾¾
    0.17
    .LENGTH
    0.17
    Act Density 0.081%

    No Known Activations