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

    Neuronpedia

    INDEX
    Explanations

    words that describe high-quality attributes or characteristics in various contexts

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

    ending in "-self" or foreign words

    np_acts-logits-general · gemini-2.0-flash

    descriptive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     évent
    -0.46
     hoped
    -0.46
     enz
    -0.45
     eller
    -0.44
     sort
    -0.44
     later
    -0.44
     rất
    -0.44
     atau
    -0.43
     else
    -0.43
    ){\
    -0.43
    POSITIVE LOGITS
     themſelves
    0.87
    ſelf
    0.86
     myſelf
    0.83
     itſelf
    0.82
     himſelf
    0.80
     disambiguazione
    0.78
    Personensuche
    0.76
    oa̍t
    0.75
     purpoſe
    0.74
     whoſe
    0.72
    Act Density 0.148%

    No Known Activations