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

    Neuronpedia

    INDEX
    Explanations

    words related to specific religious text references, physical places, and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or terms associated with a structured format or pattern in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.96
    eln
    -0.76
    arnaev
    -0.75
    ablishment
    -0.71
     Muller
    -0.70
    osit
    -0.70
    osta
    -0.69
    oration
    -0.69
    oleon
    -0.68
    uncture
    -0.68
    POSITIVE LOGITS
     Ø
    1.38
    ¹
    1.14
    Ù
    1.05
     اÙĦ
    0.99
     Ùħ
    0.99
     Ù
    0.98
    اØ
    0.98
    ©
    0.96
    ¨
    0.96
    Ø
    0.93
    Act Density 0.010%

    No Known Activations