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

    Neuronpedia

    INDEX
    Explanations

    quantitative terms and expressions related to mathematical or statistical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -1.22
     purpoſe
    -1.22
     itſelf
    -1.18
     ſche
    -1.18
     ſtate
    -1.15
     Majefty
    -1.14
     myſelf
    -1.13
     Мексичка
    -1.10
     raiſ
    -1.10
     ―――――
    -1.10
    POSITIVE LOGITS
     a
    1.11
     the
    1.03
    :
    0.99
     
    0.97
     an
    0.79
     The
    0.70
     (
    0.68
    .
    0.63
     in
    0.59
     two
    0.59
    Act Density 0.600%

    No Known Activations