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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protection and defense

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    miah
    -0.79
    ftime
    -0.78
    raq
    -0.76
    meal
    -0.74
    chin
    -0.72
    ynes
    -0.72
    ppa
    -0.71
    iken
    -0.69
    unny
    -0.68
    Clar
    -0.68
    POSITIVE LOGITS
     harm
    1.18
     impending
    1.11
     dangers
    1.06
     future
    1.04
     predators
    1.03
     undue
    1.01
     repr
    1.01
     exploitation
    1.00
     imminent
    0.98
     lawsuits
    0.98
    Act Density 0.113%

    No Known Activations