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

    Neuronpedia

    INDEX
    Explanations

    Biblical references and old English language patterns

    oai_token-act-pair · gpt-3.5-turbo

    archaic pronouns and terms of address

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mand
    -0.72
    ingham
    -0.70
     Typ
    -0.70
    Serv
    -0.70
     Saunders
    -0.69
    aldo
    -0.68
    owicz
    -0.68
     Epstein
    -0.67
    assisted
    -0.67
    raised
    -0.66
    POSITIVE LOGITS
    selves
    1.32
    self
    0.91
     sons
    0.78
     mates
    0.74
    sels
    0.73
     own
    0.73
     tha
    0.73
     regenerate
    0.73
     shalt
    0.72
     sands
    0.71
    Act Density 0.039%

    No Known Activations