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

    Neuronpedia

    INDEX
    Explanations

    terms associated with social inequality and political critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     standpoint
    -0.17
     approach
    -0.17
    /downloads
    -0.16
    arena
    -0.16
     attempt
    -0.15
    realm
    -0.14
    phere
    -0.14
    Uvs
    -0.14
    sphere
    -0.14
    panse
    -0.14
    POSITIVE LOGITS
     amounts
    0.33
     levels
    0.27
    -looking
    0.24
     versions
    0.21
    ly
    0.20
     quantities
    0.20
    ily
    0.20
     proportions
    0.20
     combinations
    0.18
    levels
    0.18
    Act Density 0.528%

    No Known Activations