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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating clarity and definite categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «ĺ
    -0.71
    aughs
    -0.68
    untarily
    -0.66
    FactoryReloaded
    -0.65
    psey
    -0.65
    iannopoulos
    -0.64
     dearly
    -0.63
    jan
    -0.61
    aturdays
    -0.61
     awkwardly
    -0.61
    POSITIVE LOGITS
     unlaw
    0.76
     borders
    0.75
     outlines
    0.74
     outline
    0.68
    bold
    0.67
     unamb
    0.66
    ItemImage
    0.66
     concise
    0.65
    onen
    0.64
     unequiv
    0.63
    Act Density 0.211%

    No Known Activations