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

    Neuronpedia

    INDEX
    Explanations

    adverbs that intensify the degree of an attribute or action

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers indicating high degrees of quality or severity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eto
    -0.68
    igi
    -0.68
    okes
    -0.67
    lins
    -0.67
    ajo
    -0.67
    isms
    -0.67
    fulness
    -0.66
    agra
    -0.66
    ies
    -0.66
    Runner
    -0.66
    POSITIVE LOGITS
     difficult
    1.02
     rare
    0.94
     unlikely
    0.92
     expensive
    0.91
     profitable
    0.90
     valuable
    0.89
     beneficial
    0.88
     inefficient
    0.87
     efficient
    0.86
     important
    0.86
    Act Density 0.046%

    No Known Activations