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

    Neuronpedia

    INDEX
    Explanations

    phrases related to raising awareness about social issues or causes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    --+
    -0.74
    verages
    -0.68
    ulla
    -0.68
     glide
    -0.67
    Iterator
    -0.66
    ée
    -0.64
    OE
    -0.63
    */(
    -0.63
    keys
    -0.62
    oult
    -0.62
    POSITIVE LOGITS
     injust
    1.05
     wrongdoing
    1.00
     atrocities
    0.93
     misogyny
    0.90
     injustice
    0.89
     issues
    0.88
     corruption
    0.88
     homosexuality
    0.87
     crimes
    0.86
     sexism
    0.86
    Act Density 0.373%

    No Known Activations