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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to regulations and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     еÑij
    -0.19
     еÑīÑij
    -0.18
     Ø£ÙĬض
    -0.15
    â
    -0.15
    âĢij
    -0.14
    fried
    -0.14
    ab
    -0.14
    ãĢį↵↵
    -0.13
    Ùĭا
    -0.13
    cond
    -0.13
    POSITIVE LOGITS
     nuest
    0.21
    ̧
    0.19
    marvin
    0.16
    jeme
    0.16
    %c
    0.15
    hazi
    0.15
    ansa
    0.15
    ÌĨ
    0.15
    itele
    0.15
    ÌĪ
    0.15
    Act Density 0.551%

    No Known Activations