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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific topics such as safety, taxation, gender, aviation, electricity, eating habits, religious settings, military defense, music, teaching, sexual health, energy efficiency, medical treatment, public speaking, beverage services, performing arts, LGBTQ+ issues, dietary advice, technology applications, audio equipment

    oai_token-act-pair · gpt-3.5-turbo

    topics related to law enforcement, public policy, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anasia
    -0.56
    imens
    -0.56
     Vert
    -0.55
    ŃĶ
    -0.54
    Xi
    -0.54
    ç«
    -0.54
    akeru
    -0.54
    ä½ľ
    -0.54
    )=(
    -0.53
    spir
    -0.51
    POSITIVE LOGITS
    /
    0.53
    ico
    0.49
     detox
    0.48
     or
    0.48
     hook
    0.47
    onda
    0.47
    /_
    0.47
     rehab
    0.46
     themed
    0.46
     swim
    0.46
    Act Density 1.426%

    No Known Activations