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

    Neuronpedia

    INDEX
    Explanations

    specific special characters in text, especially with numbers appended

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities with the symbol "Ļ."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.85
     contrace
    -0.84
     disadvant
    -0.79
     Palestin
    -0.79
     Soviets
    -0.75
     vulner
    -0.74
     fortun
    -0.73
     welf
    -0.72
     traffickers
    -0.72
     misunder
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.14
    tre
    0.90
    ï¸
    0.89
    ski
    0.88
    lime
    0.84
    eric
    0.83
    ship
    0.82
    CEO
    0.80
    pine
    0.75
    better
    0.74
    Act Density 0.307%

    No Known Activations