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

    Neuronpedia

    INDEX
    Explanations

    instances where the word 'formal' appears

    oai_token-act-pair · gpt-3.5-turbo

    references to formal processes or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.86
    =-=-=-=-=-=-=-=-
    -0.82
    =-=-=-=-
    -0.69
     Stanton
    -0.69
     Indies
    -0.67
    okemon
    -0.66
    EVA
    -0.66
    ONES
    -0.66
     Expand
    -0.65
    Phones
    -0.65
    POSITIVE LOGITS
    ities
    1.23
    ized
    1.00
    ité
    0.92
     formal
    0.92
    ised
    0.91
    lly
    0.86
    ITY
    0.85
    isations
    0.85
    tions
    0.85
    ction
    0.80
    Act Density 0.020%

    No Known Activations