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

    Neuronpedia

    INDEX
    Explanations

    references to white supremacist organizations and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fuse
    -0.16
     Strip
    -0.15
     hostages
    -0.15
    fection
    -0.15
    Orm
    -0.15
    765
    -0.14
     hostage
    -0.14
    Fuse
    -0.14
     bourgeois
    -0.14
    oppel
    -0.13
    POSITIVE LOGITS
     Ku
    0.28
     neo
    0.25
    -Nazi
    0.24
     Klan
    0.24
     white
    0.23
     Neo
    0.22
     Charlottesville
    0.22
    Neo
    0.21
     Odin
    0.21
     supremacist
    0.21
    Act Density 0.105%

    No Known Activations