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

    Neuronpedia

    INDEX
    Explanations

    the word "to" at the beginning of sentences indicating intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mente
    -0.17
    venue
    -0.16
    bred
    -0.16
    nee
    -0.15
    pp
    -0.15
    naire
    -0.15
    man
    -0.15
    nt
    -0.14
    define
    -0.14
    cribe
    -0.14
    POSITIVE LOGITS
     date
    0.25
     sum
    0.22
    -date
    0.20
    ile
    0.20
    ombs
    0.20
    ptal
    0.20
     paraph
    0.20
     quote
    0.19
    okit
    0.18
     further
    0.18
    Act Density 0.056%

    No Known Activations