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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding violence and its justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajas
    -0.15
    hausen
    -0.14
    Td
    -0.14
    endas
    -0.14
    _ENV
    -0.13
    onse
    -0.13
    dings
    -0.13
    uster
    -0.13
    _Tis
    -0.13
    stu
    -0.13
    POSITIVE LOGITS
     lo
    0.30
     Loot
    0.28
     loot
    0.25
     riot
    0.25
     cur
    0.24
     Mayor
    0.23
     nightly
    0.22
     downtown
    0.22
     destructive
    0.22
    /lo
    0.22
    Act Density 0.010%

    No Known Activations