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

    Neuronpedia

    INDEX
    Explanations

    terms related to systemic issues or concerns

    oai_token-act-pair · gpt-3.5-turbo

    themes related to systemic issues and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nance
    -0.92
    isher
    -0.85
    nery
    -0.84
    etsk
    -0.83
    ramer
    -0.76
    furt
    -0.72
    quet
    -0.71
    quer
    -0.71
    ishable
    -0.71
    ishers
    -0.69
    POSITIVE LOGITS
    ultural
    0.76
     systemic
    0.76
     sclerosis
    0.76
    helle
    0.72
     racism
    0.70
     societal
    0.67
     failures
    0.67
     offender
    0.65
     effects
    0.65
     proportions
    0.65
    Act Density 0.031%

    No Known Activations