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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "isse" at varying relevance levels

    oai_token-act-pair · gpt-3.5-turbo

    references to connoisseurship and discussions about quality in various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kev
    -0.64
     peril
    -0.62
     Defenders
    -0.61
    angering
    -0.59
    emonic
    -0.58
     Sixth
    -0.57
     parks
    -0.57
    healthy
    -0.56
     ILCS
    -0.56
    groups
    -0.56
    POSITIVE LOGITS
    isse
    1.05
    isen
    0.98
    udo
    0.93
    mination
    0.92
    lette
    0.91
    clair
    0.90
     horizont
    0.89
    zon
    0.88
    vier
    0.87
    zes
    0.84
    Act Density 0.004%

    No Known Activations