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

    Neuronpedia

    INDEX
    Explanations

    discussions about the treatment and rights of marginalized groups, particularly focusing on the injustices they face

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stället
    -0.58
     silicona
    -0.54
     chrétienne
    -0.54
    zło
    -0.54
     cref
    -0.53
     Зачем
    -0.51
    افظة
    -0.51
    spyOn
    -0.49
    frey
    -0.48
    jonal
    -0.47
    POSITIVE LOGITS
     treatment
    0.69
    treatment
    0.68
    待遇
    0.67
     treated
    0.67
    Treatment
    0.62
    treated
    0.61
     Treatment
    0.60
     TREATMENT
    0.60
     Treated
    0.59
    justice
    0.58
    Act Density 0.486%

    No Known Activations