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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and related prepositional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fors
    -0.14
    ä
    -0.14
     UN
    -0.14
    Dev
    -0.14
    ile
    -0.14
    alian
    -0.14
    illa
    -0.13
    Æ
    -0.13
    ight
    -0.13
    HL
    -0.13
    POSITIVE LOGITS
    iná
    0.15
    SharedPointer
    0.15
    anches
    0.15
    ë¨
    0.15
    озÑı
    0.15
    icut
    0.15
    memberof
    0.14
     âĸ¼
    0.14
     Harold
    0.14
     vic
    0.14
    Act Density 0.013%

    No Known Activations