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

    Neuronpedia

    INDEX
    Explanations

    terms related to negative impacts and effects, particularly in financial and health-related contexts

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

    Adjectives describing severity or intensity

    np_acts-logits-general · gemini-2.0-flash

    describing intensity or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.78
    Хьажоргаш
    -0.71
    Hentet
    -0.68
    ynchronously
    -0.67
    yntaxException
    -0.66
    osoba
    -0.65
    Diwedd
    -0.62
    ValueStyle
    -0.60
    ########.
    -0.59
    adpleegd
    -0.59
    POSITIVE LOGITS
     noticeable
    0.99
     severe
    0.97
     palpable
    0.90
     significant
    0.88
     pervasive
    0.85
     evident
    0.84
     greater
    0.83
     acute
    0.82
    severe
    0.81
     profound
    0.81
    Act Density 0.688%

    No Known Activations