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

    Neuronpedia

    INDEX
    Explanations

    references to awards and recognitions in various contexts

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

    Follows nouns such as titles, universities, and sports teams

    np_acts-logits-general · gemini-2.0-flash

    specific entities followed by punctuation or descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sometimes
    -0.73
     Sometimes
    -0.72
     Occasionally
    -0.66
     ibland
    -0.64
    endforeach
    -0.64
    によっては
    -0.63
     etc
    -0.61
     occasional
    -0.60
     иногда
    -0.60
     frequent
    -0.60
    POSITIVE LOGITS
     amidst
    0.72
     replacing
    0.72
     nadat
    0.71
     nachdem
    0.71
     marking
    0.71
     alongside
    0.70
     menyus
    0.69
    following
    0.69
     after
    0.69
    replacing
    0.68
    Act Density 0.522%

    No Known Activations