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

    Neuronpedia

    INDEX
    Explanations

    complex emotional responses and reflections on interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     we
    -0.16
    æĪij们
    -0.15
    ehler
    -0.14
     scroll
    -0.14
     yourselves
    -0.14
    æĪijåĢij
    -0.14
    asca
    -0.13
     ìļ°ë¦¬ëĬĶ
    -0.13
     ourselves
    -0.13
    üzel
    -0.13
    POSITIVE LOGITS
     deep
    0.38
    deep
    0.32
     Deep
    0.29
    Deep
    0.25
    _deep
    0.24
     deeper
    0.21
     deepest
    0.21
    æ·±
    0.20
     logic
    0.20
     remaining
    0.19
    Act Density 0.528%

    No Known Activations