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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the philosophical or moral implications of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.18
    ầy
    -0.16
    alg
    -0.15
    beros
    -0.15
    ovsky
    -0.15
    ÙĦÙģØ©
    -0.14
    iat
    -0.14
    æĢĿãģĦ
    -0.14
    abr
    -0.13
     Yar
    -0.13
    POSITIVE LOGITS
     Factory
    0.17
    Factory
    0.15
    /or
    0.14
     Giles
    0.14
    factory
    0.14
    irth
    0.14
    rics
    0.14
     Phelps
    0.13
     Aviv
    0.13
     factory
    0.13
    Act Density 1.023%

    No Known Activations