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

    Neuronpedia

    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.74
    uria
    -0.67
    anwhile
    -0.65
    éĥ
    -0.63
     parity
    -0.62
     wise
    -0.60
     correctness
    -0.60
    éĹĺ
    -0.60
    urrencies
    -0.59
    76561
    -0.59
    POSITIVE LOGITS
    verse
    0.95
    onian
    0.91
    leys
    0.86
    stown
    0.85
    sonian
    0.85
     Brothers
    0.83
    issance
    0.79
     River
    0.79
    nian
    0.79
    ville
    0.75
    Act Density 0.229%

    No Known Activations