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

    Neuronpedia

    INDEX
    Explanations

    words that are likely to be related to health topics or physical conditions, specifically focusing on serious or critical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.17
    ufen
    -0.15
    å¾½
    -0.15
    Ñ
    -0.15
    loth
    -0.15
    haven
    -0.15
    HAV
    -0.14
     sno
    -0.14
     Spy
    -0.14
    anka
    -0.14
    POSITIVE LOGITS
    bek
    0.25
    bay
    0.21
    jon
    0.21
    алÑĭ
    0.20
    xon
    0.19
    mur
    0.18
    ulla
    0.18
    beg
    0.18
     Duis
    0.18
     Seit
    0.18
    Act Density 0.033%

    No Known Activations