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

    Neuronpedia

    INDEX
    Explanations

    terms related to race and racial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.98
     utafitiHapana
    -0.95
     Theſe
    -0.89
     itſelf
    -0.85
     themſelves
    -0.84
     FormsModule
    -0.83
     himſelf
    -0.83
     varandra
    -0.81
     againſt
    -0.79
     ſeveral
    -0.78
    POSITIVE LOGITS
     inclusive
    0.76
    TagMode
    0.75
    inclusive
    0.72
    Inclusive
    0.69
     racial
    0.65
     Inclusive
    0.64
     alloys
    0.64
     alloy
    0.64
     Racial
    0.61
     ско
    0.57
    Act Density 0.062%

    No Known Activations