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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fairness and justice

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fairness and social equity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orio
    -0.58
    onto
    -0.54
    idi
    -0.52
    requires
    -0.52
    arta
    -0.51
    fet
    -0.49
    aka
    -0.49
    arget
    -0.49
    psey
    -0.48
    onga
    -0.48
    POSITIVE LOGITS
     last
    0.59
     yesterday
    0.58
     originally
    0.57
     initially
    0.55
     earlier
    0.53
    terday
    0.50
     Yanuk
    0.49
     beforehand
    0.49
     enthusi
    0.48
    iscons
    0.48
    Act Density 2.973%

    No Known Activations