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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or emotions expressed in text

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

    words starting with auto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plufieurs
    -0.70
     zoude
    -0.64
     kasarigan
    -0.63
     mijne
    -0.60
    intéress
    -0.60
     tää
    -0.59
     Grüsse
    -0.59
     ocasi
    -0.58
     tärke
    -0.58
     increí
    -0.57
    POSITIVE LOGITS
     auto
    0.78
     Auto
    0.71
    Auto
    0.70
    Autowired
    0.66
    auto
    0.63
     AUTO
    0.63
    autoconfigure
    0.57
    setAuto
    0.54
    AUTO
    0.54
    autoload
    0.50
    Act Density 0.004%

    No Known Activations