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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical research and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yen
    -0.15
     susceptibility
    -0.15
    osto
    -0.15
    ôi
    -0.14
     dirig
    -0.14
     æ¯
    -0.13
    á»ķ
    -0.13
    à¥įà¤
    -0.13
    lifetime
    -0.13
    TypeInfo
    -0.13
    POSITIVE LOGITS
     scores
    0.26
     score
    0.24
     Scores
    0.23
     Osw
    0.22
     improvements
    0.22
     Improvement
    0.21
     Score
    0.21
     improvement
    0.20
    æĶ¹
    0.20
    scores
    0.19
    Act Density 0.017%

    No Known Activations