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

    Neuronpedia

    INDEX
    Explanations

    phrases related to race or racial issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to religion and racial identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irable
    -0.71
    reality
    -0.71
    agonist
    -0.69
    iffe
    -0.68
    roud
    -0.67
    osponsors
    -0.67
    agonists
    -0.65
     exhib
    -0.65
     challeng
    -0.63
    ieg
    -0.63
    POSITIVE LOGITS
     religiously
    2.59
     racially
    1.05
     sling
    0.71
     slack
    0.65
     Tus
    0.62
    rompt
    0.60
     Ins
    0.58
    nw
    0.58
    onne
    0.58
    atically
    0.57
    Act Density 0.011%

    No Known Activations