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

    Neuronpedia

    INDEX
    Explanations

    words related to societal issues such as racism, authority, and power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with race and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.78
     Yose
    -0.71
    Enlarge
    -0.63
     Pryor
    -0.62
     Rack
    -0.59
     Grimes
    -0.58
     Genetics
    -0.57
     Rare
    -0.56
     Reported
    -0.56
     Reck
    -0.55
    POSITIVE LOGITS
    ifies
    0.86
    heartedly
    0.84
    izes
    0.83
    tarians
    0.82
    bably
    0.80
    iates
    0.80
     sucks
    0.79
    gered
    0.79
    handedly
    0.77
    fully
    0.77
    Act Density 0.633%

    No Known Activations