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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and other forms of the verb indicating intention or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cio
    -0.17
    tracted
    -0.17
     Buchanan
    -0.14
    ional
    -0.14
     mint
    -0.14
    ãĤĪãĤĬ
    -0.14
    ero
    -0.14
    629
    -0.14
    tera
    -0.13
     Jud
    -0.13
    POSITIVE LOGITS
     hearing
    0.21
     hear
    0.21
     having
    0.18
     finally
    0.18
     me
    0.18
    having
    0.17
     have
    0.17
     HAVE
    0.17
    linger
    0.17
     Have
    0.17
    Act Density 0.081%

    No Known Activations