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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating a refusal or lack

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

    not followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PTT
    -0.48
    __((
    -0.47
     leu
    -0.46
     &___
    -0.45
     Sar
    -0.45
     Zon
    -0.42
     PDA
    -0.41
     SPI
    -0.41
     SPE
    -0.41
     PTC
    -0.41
    POSITIVE LOGITS
    berdayakan
    0.58
     Erscheinung
    0.56
     Grüsse
    0.54
     aislada
    0.51
    XmlRootElement
    0.51
     Estructura
    0.50
    GEBURTSDATUM
    0.50
     mariposas
    0.50
     productivo
    0.49
     ilustracja
    0.48
    Act Density 0.129%

    No Known Activations