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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations and exclusions in legal or warranty contexts

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

    "but not" phrases

    np_acts-logits-general · gemini-2.0-flash

    but not limited to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.80
     externi
    -0.66
    رشف
    -0.65
    RenderAtEndOf
    -0.63
     חיצוניים
    -0.62
    rungsseite
    -0.61
    ("$.
    -0.60
    Jegyzetek
    -0.60
    таратура
    -0.58
    сылкі
    -0.58
    POSITIVE LOGITS
    ribut
    0.53
    ipot
    0.52
    õi
    0.52
    allax
    0.50
     buts
    0.50
    gaande
    0.49
    taje
    0.48
    gehende
    0.48
    かもし
    0.48
    řez
    0.47
    Act Density 0.154%

    No Known Activations