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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uay
    -0.83
    ntil
    -0.81
     Murd
    -0.78
    rick
    -0.78
    oil
    -0.74
    ellen
    -0.73
    achus
    -0.72
    ocene
    -0.72
    icka
    -0.72
    Diamond
    -0.71
    POSITIVE LOGITS
     matters
    0.83
     drastic
    0.81
    ities
    0.81
    ties
    0.81
     mundane
    0.78
     blatant
    0.76
     kinds
    0.74
     minded
    0.74
     things
    0.74
     sentiments
    0.73
    Act Density 0.268%

    No Known Activations