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

    Neuronpedia

    INDEX
    Explanations

    adjectives highlighting a specific degree or extent of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "particularly" and its repeated use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.71
    sic
    -0.70
    tein
    -0.69
    ÅĤ
    -0.65
    Pod
    -0.65
    URE
    -0.64
     facade
    -0.63
    else
    -0.63
    kel
    -0.62
    okes
    -0.62
    POSITIVE LOGITS
     noteworthy
    0.94
     advantageous
    0.93
     susceptible
    0.90
    wcs
    0.88
     identifiable
    0.87
     frequ
    0.86
     noticeable
    0.85
     favourable
    0.84
    eatures
    0.84
     appreci
    0.82
    Act Density 0.017%

    No Known Activations