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

    Neuronpedia

    INDEX
    Explanations

    references to specific places or names

    oai_token-act-pair · gpt-3.5-turbo

    the term "ark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.72
     unnecess
    -0.69
     fertility
    -0.66
     wed
    -0.63
    ahon
    -0.63
     fertile
    -0.63
     sund
    -0.63
     Romeo
    -0.63
     reckoned
    -0.60
     diapers
    -0.59
    POSITIVE LOGITS
    ansas
    1.32
    ozy
    1.07
    enment
    0.86
    itect
    0.86
    eting
    0.84
    esian
    0.83
    anian
    0.82
    reath
    0.80
    er
    0.80
    ed
    0.78
    Act Density 0.013%

    No Known Activations