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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups associated with radical ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vertisement
    -0.17
    ather
    -0.17
    ayar
    -0.15
    окÑĢем
    -0.14
     ach
    -0.14
    amerate
    -0.14
     Hv
    -0.14
    sein
    -0.14
    ictim
    -0.14
    abus
    -0.14
    POSITIVE LOGITS
     Lumpur
    0.17
    -large
    0.15
     vá»±c
    0.15
     base
    0.15
     Klan
    0.15
    -big
    0.15
     Bryce
    0.14
    base
    0.14
    etz
    0.14
    stk
    0.14
    Act Density 0.019%

    No Known Activations