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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing opinions or beliefs about moral or ethical issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    isode
    -0.75
    76561
    -0.73
    ãĤ©
    -0.71
    ertodd
    -0.65
    details
    -0.65
    cific
    -0.64
    ffe
    -0.64
    nergy
    -0.62
     trailed
    -0.62
    ttp
    -0.60
    POSITIVE LOGITS
     imperative
    1.31
     permissible
    1.27
     advisable
    1.23
     possible
    1.22
     impossible
    1.20
     conceivable
    1.16
     incumbent
    1.11
     feasible
    1.11
     desirable
    1.11
     prudent
    1.10
    Act Density 0.212%

    No Known Activations