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

    Neuronpedia

    INDEX
    Explanations

    comparisons of degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the intensity or degree of a concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.88
    İĭ
    -0.71
    piracy
    -0.71
    ysc
    -0.70
     Tags
    -0.70
    anyl
    -0.69
     Releases
    -0.68
    abad
    -0.67
    ictions
    -0.67
    GD
    -0.65
    POSITIVE LOGITS
     simpler
    1.10
     easier
    1.08
     nicer
    1.08
     appreciated
    1.07
     cheaper
    0.99
     closer
    0.97
     safer
    0.96
     quieter
    0.95
     quicker
    0.95
     smarter
    0.95
    Act Density 0.051%

    No Known Activations