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

    Neuronpedia

    INDEX
    Explanations

    references to significant changes in physical states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     den
    -0.48
    enging
    -0.43
     i
    -0.41
     C
    -0.40
    antası
    -0.40
     Zimmerman
    -0.39
     [
    -0.39
    <eos>
    -0.39
     -
    -0.38
     (
    -0.38
    POSITIVE LOGITS
     itſelf
    0.96
     greateſt
    0.94
     StatelessWidget
    0.94
     myſelf
    0.94
     Majefty
    0.93
     Efq
    0.93
     Diſ
    0.93
     Jefus
    0.93
     ſeveral
    0.92
     reaſon
    0.89
    Act Density 0.529%

    No Known Activations