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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nên
    -0.17
     proven
    -0.16
    oli
    -0.15
    APA
    -0.14
    ernes
    -0.14
     tweeting
    -0.14
    oku
    -0.14
     proved
    -0.13
    alley
    -0.13
    astes
    -0.13
    POSITIVE LOGITS
     loved
    0.26
     Loved
    0.26
     used
    0.22
     would
    0.21
    liked
    0.20
    _used
    0.20
     always
    0.20
     often
    0.20
    used
    0.19
     liked
    0.19
    Act Density 0.159%

    No Known Activations