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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Aitken" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.74
    accompan
    -0.72
    ENCY
    -0.71
    pmwiki
    -0.70
     EB
    -0.69
    ESA
    -0.68
     pestic
    -0.68
     cryst
    -0.68
    onse
    -0.64
     Bahá
    -0.63
    POSITIVE LOGITS
    ken
    1.16
    azi
    1.05
    burgh
    0.98
    ners
    0.98
    feld
    0.89
    ning
    0.88
    wald
    0.86
    wich
    0.86
    igans
    0.84
    berry
    0.83
    Act Density 0.009%

    No Known Activations