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

    Neuronpedia

    INDEX
    Explanations

    sentences emphasizing the point of view or actions of the author

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

    "We" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    we + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HomeComponent
    -0.61
     davvero
    -0.56
     glows
    -0.52
    validates
    -0.51
     veramente
    -0.51
     dries
    -0.51
     REALLY
    -0.50
    truly
    -0.49
    衔
    -0.49
    Become
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.79
     سكانية
    0.70
    UnusedPrivate
    0.64
    verwijspagina
    0.61
    >[]
    0.61
    titleMargin
    0.60
     بيها
    0.58
     expect
    0.58
     Preg
    0.57
    InjectAttribute
    0.57
    Act Density 0.692%

    No Known Activations