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

    Neuronpedia

    INDEX
    Explanations

    the concept of novelty

    oai_token-act-pair · gpt-3.5-turbo

    terms related to novelty and innovation, particularly in the context of technology or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PRESIDENT
    -0.78
    rael
    -0.73
    acters
    -0.72
    ogl
    -0.68
     redes
    -0.67
     sacked
    -0.66
    athetic
    -0.66
    thur
    -0.65
    undreds
    -0.64
    bern
    -0.64
    POSITIVE LOGITS
     novelty
    0.88
     Discovery
    0.80
    arily
    0.73
    Reason
    0.73
    pole
    0.73
    ĸļ
    0.72
    orph
    0.69
     Offense
    0.68
     rele
    0.68
    ability
    0.68
    Act Density 0.014%

    No Known Activations