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

    Neuronpedia

    INDEX
    Explanations

    references to cultural and social issues, particularly those relating to identity and community narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     talents
    -0.16
    issen
    -0.15
     backbone
    -0.14
    alus
    -0.14
     dinosaurs
    -0.14
     Techniques
    -0.14
     complexities
    -0.14
    νο
    -0.13
     skills
    -0.13
    ft
    -0.13
    POSITIVE LOGITS
     literature
    0.31
     circles
    0.30
     popular
    0.24
     everyday
    0.22
    popular
    0.22
     mainstream
    0.22
     daily
    0.20
     pop
    0.20
     Literature
    0.19
    daily
    0.19
    Act Density 0.356%

    No Known Activations