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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts, often related to setting or assigning values

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

    setting something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.82
    évaluateur
    -0.59
    ſelf
    -0.58
     يتيمه
    -0.57
     disambiguazione
    -0.56
    createServer
    -0.56
    rungsseite
    -0.56
     Administrativna
    -0.55
    windowFixed
    -0.54
    tagHelperRunner
    -0.54
    POSITIVE LOGITS
     something
    0.84
     Something
    0.55
    something
    0.54
     whatever
    0.53
     "
    0.53
    Something
    0.52
     “
    0.50
     be
    0.50
     somethin
    0.49
     anything
    0.49
    Act Density 0.066%

    No Known Activations