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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and the authors of those studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.75
    uxxxx
    -0.70
     Efq
    -0.63
     Nerv
    -0.63
    mtliche
    -0.63
     cherchés
    -0.62
     iNdEx
    -0.61
    Explicación
    -0.61
    RUnlock
    -0.60
     Ams
    -0.60
    POSITIVE LOGITS
    InjectAttribute
    0.48
     niets
    0.48
    CrossOrigin
    0.48
    droje
    0.47
     ویکی
    0.46
    ThroughAttribute
    0.45
     ketahui
    0.45
     Effect
    0.44
     beira
    0.44
    posites
    0.43
    Act Density 0.179%

    No Known Activations