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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    to followed by verbs or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.61
    +#+#
    -0.60
     Мексичка
    -0.59
    rungsseite
    -0.59
     bluzka
    -0.56
     فريبيس
    -0.55
     damskie
    -0.54
    NameInMap
    -0.54
     feroit
    -0.53
     htons
    -0.52
    POSITIVE LOGITS
     del
    0.42
     gut
    0.42
     Del
    0.41
     decipher
    0.40
     persist
    0.39
    amente
    0.39
     comprome
    0.38
    athus
    0.37
    CVS
    0.37
     kaarangay
    0.37
    Act Density 0.065%

    No Known Activations