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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of new sections or paragraphs within a text

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

    the beginning of a new document or section

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

    celebrity and media attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.56
     înal
    -0.54
     aici
    -0.52
     ratify
    -0.52
     âme
    -0.52
     grève
    -0.51
     locaux
    -0.51
     morgon
    -0.50
     față
    -0.49
    umbersome
    -0.49
    POSITIVE LOGITS
     fans
    0.81
     paparazzi
    0.78
    fans
    0.73
    Fans
    0.71
     Fans
    0.70
     celebrity
    0.69
     netizens
    0.67
     Instagram
    0.66
     revealed
    0.64
     singer
    0.64
    Act Density 0.002%

    No Known Activations