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

    Neuronpedia

    INDEX
    Explanations

    references to moral and ethical justifications related to violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FileDescriptor
    -0.35
     Auss
    -0.33
     Uda
    -0.33
    -0.32
    боро
    -0.30
     examining
    -0.30
     examination
    -0.29
     audit
    -0.29
    <bos>
    -0.28
     Uncle
    -0.28
    POSITIVE LOGITS
     المعيارى
    0.67
    endpush
    0.67
    ChildScrollView
    0.66
     voordelen
    0.64
    rungsseite
    0.59
     htons
    0.58
    ofollow
    0.57
     EconPapers
    0.57
     BorderLayout
    0.56
    Carriera
    0.56
    Act Density 1.068%

    No Known Activations