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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases indicating that someone or something is not the only one of its kind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    only
    -0.78
     until
    -0.69
     ONLY
    -0.69
    Only
    -0.66
     EVEN
    -0.66
     +++
    -0.66
    thood
    -0.66
     ALWAYS
    -0.65
     Only
    -0.64
    >>\
    -0.64
    POSITIVE LOGITS
     troubled
    0.77
     woes
    0.77
     disgruntled
    0.73
     questionable
    0.71
     bizarre
    0.71
     politic
    0.70
     misfortune
    0.70
     grievances
    0.70
     trouble
    0.69
     struggles
    0.69
    Act Density 0.315%

    No Known Activations