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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reflection on personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undi
    -0.18
     زد
    -0.14
    æĦ
    -0.14
    _SUPPORTED
    -0.14
    ania
    -0.14
    ëįĶëĭĪ
    -0.14
    æĮģ
    -0.14
     dil
    -0.14
    .HtmlControls
    -0.14
    ignon
    -0.13
    POSITIVE LOGITS
     looking
    0.73
     look
    0.70
    looking
    0.66
     Looking
    0.65
     Look
    0.63
     looked
    0.61
     looks
    0.61
    Looking
    0.61
    look
    0.59
    -looking
    0.59
    Act Density 0.124%

    No Known Activations