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

    Neuronpedia

    INDEX
    Explanations

    references to sensitive areas and environments that require protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.63
    JpaRepository
    -0.62
    SpringBootTest
    -0.52
    AnimationsModule
    -0.50
    ]};
    -0.50
    addressed
    -0.49
    fromnode
    -0.49
     diri
    -0.49
    ביוגרפיה
    -0.49
     سكانية
    -0.48
    POSITIVE LOGITS
     sensitive
    0.66
     fragile
    0.63
     sacred
    0.61
     precious
    0.60
    好不容易
    0.59
     empfind
    0.58
    LLocation
    0.56
     delicate
    0.55
     sagrado
    0.55
     Exactos
    0.54
    Act Density 0.510%

    No Known Activations