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

    Neuronpedia

    INDEX
    Explanations

    social issues related to gender disparities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    jured
    -0.58
     ..."
    -0.57
    ocular
    -0.56
     ['
    -0.56
    tein
    -0.55
    uminium
    -0.54
    )"
    -0.54
    ozyg
    -0.53
    ooter
    -0.52
    shoot
    -0.51
    POSITIVE LOGITS
     increasingly
    0.91
     policymakers
    0.87
     fundamentally
    0.81
     unavoid
    0.76
     biases
    0.75
    etheless
    0.74
     broadly
    0.73
     often
    0.73
     disproportionately
    0.72
     ecosystems
    0.72
    Act Density 1.364%

    No Known Activations