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

    Neuronpedia

    INDEX
    Explanations

    notations of negation and legal terminology

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

    Followed by a restrictive clause

    np_acts-logits-general · gemini-2.0-flash

    not less than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.99
     eighty
    -0.81
     sixty
    -0.79
     Eighty
    -0.76
     seventy
    -0.75
     fifty
    -0.74
     Seventy
    -0.72
     forty
    -0.72
     ninety
    -0.71
     thirty
    -0.70
    POSITIVE LOGITS
     كومونز
    0.74
    ⓧ
    0.74
     الحره
    0.71
    Portail
    0.66
     Мексичка
    0.64
    ArgsConstructor
    0.64
    IsContent
    0.63
     EnglishChoose
    0.63
    SequentialGroup
    0.62
    tagHelperRunner
    0.62
    Act Density 0.844%

    No Known Activations