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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or implications of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.72
     Shaksp
    -0.65
     Etr
    -0.64
     Shakspeare
    -0.63
     Atiku
    -0.62
     himſelf
    -0.61
     fevere
    -0.61
     garmin
    -0.60
     înainte
    -0.60
     mohair
    -0.59
    POSITIVE LOGITS
     the
    1.33
     a
    0.99
    .}(
    0.96
     an
    0.94
    .)}
    0.94
     their
    0.93
     its
    0.90
     OF
    0.90
    "])
    0.89
    sted
    0.88
    Act Density 1.445%

    No Known Activations