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

    Neuronpedia

    INDEX
    Explanations

    information related to crime, legal proceedings, and law enforcement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    edIn
    -0.64
    Sund
    -0.59
    free
    -0.56
    ãģĵ
    -0.55
    Unity
    -0.55
    Pand
    -0.53
    anan
    -0.52
     strutConnector
    -0.52
    Grab
    -0.52
     Submission
    -0.51
    POSITIVE LOGITS
    ources
    0.83
    omet
    0.73
    igmatic
    0.73
    ourced
    0.72
    olutions
    0.71
    ixties
    0.71
    leeve
    0.70
    atellite
    0.69
    iblings
    0.68
    lander
    0.68
    Act Density 13.032%

    No Known Activations