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

    Neuronpedia

    INDEX
    Explanations

    terms related to gender and demographics

    oai_token-act-pair · gpt-3.5-turbo

    references to sex and gender

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.87
    £ı
    -0.84
    BLIC
    -0.75
    arij
    -0.75
    Dispatch
    -0.74
    EMP
    -0.71
    atche
    -0.71
    ¶ħ
    -0.70
    REC
    -0.69
    OY
    -0.68
    POSITIVE LOGITS
    ido
    0.96
    ually
    0.88
     hormones
    0.83
     chromosome
    0.83
     steroids
    0.82
     chromosomes
    0.82
    ily
    0.81
     steroid
    0.80
    iest
    0.79
     trafficking
    0.76
    Act Density 0.019%

    No Known Activations