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

    Neuronpedia

    INDEX
    Explanations

    mentions of a variety of things or topics in a document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'various' to indicate diversity or multiple aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.73
    vest
    -0.72
    O
    -0.70
    abad
    -0.69
    itten
    -0.67
    cher
    -0.65
     thence
    -0.64
    athing
    -0.64
    uberty
    -0.63
    $$$$
    -0.63
    POSITIVE LOGITS
    iating
    1.29
     kinds
    1.28
     sorts
    1.12
     aspects
    1.06
     iterations
    1.03
     facets
    1.02
     types
    1.01
     parts
    0.96
    iated
    0.95
     degrees
    0.94
    Act Density 0.021%

    No Known Activations