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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addon
    -0.16
    jian
    -0.16
    orama
    -0.15
    ocker
    -0.15
    ernals
    -0.14
    udev
    -0.14
    737
    -0.14
    _PS
    -0.13
    æ·¡
    -0.13
    our
    -0.13
    POSITIVE LOGITS
     until
    0.25
    until
    0.24
     Until
    0.22
    Until
    0.22
     existence
    0.20
    enha
    0.19
     hasta
    0.19
     till
    0.18
    existence
    0.17
    à¸Īà¸Ļ
    0.17
    Act Density 0.015%

    No Known Activations