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

    Neuronpedia

    INDEX
    Explanations

    assertive statements regarding the qualities and characteristics of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    伸
    -0.14
     automát
    -0.14
    ÑĢиз
    -0.14
    REATE
    -0.14
     ÄijÃłn
    -0.14
    pek
    -0.13
     SetLastError
    -0.13
    558
    -0.13
    ÙĨÙĬÙĨ
    -0.13
    ungal
    -0.13
    POSITIVE LOGITS
     sure
    0.39
     Sure
    0.28
    sure
    0.27
    Sure
    0.24
     anything
    0.23
     surely
    0.22
     guaranteed
    0.21
     ones
    0.20
     Surely
    0.20
     ready
    0.19
    Act Density 0.115%

    No Known Activations