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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the conjunction ',' followed by numbers which indicates the presence of numerical data or statistics

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.66
    olves
    -0.66
    APH
    -0.65
    ulz
    -0.65
    aukee
    -0.63
    interstitial
    -0.62
    è£ħ
    -0.61
    ield
    -0.61
    ruck
    -0.60
    ORPG
    -0.60
    POSITIVE LOGITS
     alas
    0.98
     although
    0.96
     albeit
    0.93
     despite
    0.86
     whereas
    0.80
     according
    0.80
     somew
    0.79
     yes
    0.79
     namely
    0.77
     unless
    0.77
    Act Density 0.152%

    No Known Activations