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

    Neuronpedia

    INDEX
    Explanations

    words related to specific groups of people or nationalities

    oai_token-act-pair · gpt-3.5-turbo

    references to various ethnic or national groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABLE
    -0.71
    ASED
    -0.69
     increments
    -0.69
    ORY
    -0.65
    abus
    -0.64
    PDATE
    -0.64
    ANC
    -0.63
    ISON
    -0.63
    stre
    -0.62
     judgment
    -0.62
    POSITIVE LOGITS
    aurus
    1.37
    ervative
    1.08
    ervatives
    1.03
    hare
    1.03
    hip
    1.03
    hips
    1.02
    paces
    1.01
     Anonymous
    0.94
    kaya
    0.93
    cale
    0.92
    Act Density 0.128%

    No Known Activations