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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "supposed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tok
    -0.73
     flare
    -0.65
    ক
    -0.65
     tok
    -0.64
     field
    -0.63
    Ck
    -0.62
     Cal
    -0.62
     fil
    -0.62
     
    -0.62
     palo
    -0.61
    POSITIVE LOGITS
     Majefty
    1.05
    Sup
    0.96
    Сюжет
    0.96
     suprême
    0.94
     automatico
    0.91
    原始内容存档于
    0.90
    abetes
    0.90
     Sup
    0.89
     superiores
    0.89
     exclusivas
    0.87
    Act Density 0.176%

    No Known Activations