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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the" and its variations in various contexts

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

    the [noun/adjective]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.68
    iſche
    -0.63
    WriteTagHelper
    -0.60
     queſta
    -0.59
     ſind
    -0.59
    -0.58
    iſchen
    -0.58
     geweſen
    -0.57
    <unused53>
    -0.57
    <unused39>
    -0.57
    POSITIVE LOGITS
    ന്ന്
    0.34
    msgSender
    0.33
    memset
    0.33
     Herrn
    0.33
    enumi
    0.33
     typeof
    0.31
    meisters
    0.30
    def
    0.30
    toBe
    0.30
    zegovina
    0.29
    Act Density 0.296%

    No Known Activations