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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparison or dual aspect

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction 'and' used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uel
    -0.76
    Ļ½
    -0.74
    eks
    -0.73
    ÃĽ
    -0.71
    IJ
    -0.71
    rance
    -0.71
    ³
    -0.70
    ivid
    -0.70
    oor
    -0.68
    iper
    -0.66
    POSITIVE LOGITS
     ours
    0.80
    nam
    0.71
     hers
    0.70
     sexes
    0.67
    chard
    0.66
     autobiography
    0.65
     theirs
    0.65
     CPI
    0.63
     nons
    0.62
     imperson
    0.61
    Act Density 0.169%

    No Known Activations