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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fairness or justice, especially in the context of treatment experienced by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of treatment, particularly in social or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zyme
    -0.74
    sky
    -0.66
     enz
    -0.60
     frying
    -0.60
     dreaming
    -0.60
    raper
    -0.58
     brainstorm
    -0.58
     Downing
    -0.58
     Bour
    -0.58
     scramble
    -0.57
    POSITIVE LOGITS
    reatment
    0.89
    payer
    0.85
    terness
    0.83
    ifference
    0.82
    reated
    0.79
    phia
    0.77
    Reviewer
    0.77
    treated
    0.76
    ttes
    0.75
    Gender
    0.75
    Act Density 0.025%

    No Known Activations