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

    Neuronpedia

    INDEX
    Explanations

    phrases related to firearms and potentially violent or controversial societal issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    itable
    -1.16
    fman
    -1.05
    stasy
    -1.04
    iners
    -0.96
    bara
    -0.93
    gregation
    -0.92
    ctions
    -0.91
    bub
    -0.90
    vironment
    -0.90
    itably
    -0.89
    POSITIVE LOGITS
    age
    1.11
    aic
    1.03
    entimes
    1.02
    bol
    0.99
    aire
    0.94
    ORN
    0.92
    ucket
    0.92
     Vaugh
    0.92
    warm
    0.90
    aneously
    0.90
    Act Density 1.962%

    No Known Activations