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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to negation and the absence of elements or conditions

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

    Comparative adverbs ("more," "no"...)

    np_acts-logits-general · gemini-2.0-flash

    more easily,more than,more accurately,no longer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    клопе
    -0.52
     насељу
    -0.50
     whereas
    -0.47
     {}".
    -0.47
     whichever
    -0.47
     keď
    -0.47
    ieważ
    -0.46
    zło
    -0.46
    hichever
    -0.46
     wenn
    -0.45
    POSITIVE LOGITS
    ingly
    0.97
    matically
    0.92
    fully
    0.87
    atively
    0.84
    lessly
    0.83
    etheless
    0.83
    arily
    0.82
    ously
    0.79
    følgelig
    0.78
    ILY
    0.77
    Act Density 0.322%

    No Known Activations