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

    Neuronpedia

    INDEX
    Explanations

    words related to political and religious figures

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to individuals associated with extremist groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Titanic
    -0.81
     Chloe
    -0.76
     gears
    -0.75
     ponies
    -0.74
     Takeru
    -0.73
    erella
    -0.73
     Velvet
    -0.73
     roller
    -0.72
     pitchers
    -0.71
     butterflies
    -0.70
    POSITIVE LOGITS
    aq
    1.43
    awi
    1.38
    qqa
    1.32
    qa
    1.23
    ayn
    1.20
    iyah
    1.17
    Allah
    1.13
    azi
    1.12
    abi
    1.11
    Islam
    1.10
    Act Density 0.267%

    No Known Activations