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

    Neuronpedia

    INDEX
    Explanations

    references to the duality and comparison of different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dorf
    -0.19
    _RTC
    -0.15
    æĹ¥ãģ®
    -0.15
    ÑİваннÑı
    -0.15
    onta
    -0.14
    eÄį
    -0.14
    .atan
    -0.14
    CN
    -0.14
    ãİ
    -0.14
     Tome
    -0.14
    POSITIVE LOGITS
     pedig
    0.24
     dit
    0.21
     theirs
    0.20
     ones
    0.19
     likewise
    0.18
     hers
    0.18
     Dit
    0.17
     is
    0.16
    åīĩ
    0.16
    atform
    0.15
    Act Density 0.226%

    No Known Activations