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

    Neuronpedia

    INDEX
    Explanations

    references to violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehen
    -0.16
    eder
    -0.16
    egov
    -0.16
    eza
    -0.16
    edException
    -0.16
    spender
    -0.15
    ierz
    -0.15
    Ñıд
    -0.15
    å¼ķãģį
    -0.15
    ingles
    -0.15
    POSITIVE LOGITS
    ating
    0.18
    LETTE
    0.18
    ante
    0.17
    ancel
    0.17
    lette
    0.17
     viol
    0.17
    ayet
    0.16
    -viol
    0.16
    ated
    0.16
    -force
    0.15
    Act Density 0.009%

    No Known Activations