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

    Neuronpedia

    INDEX
    Explanations

    terms related to defending or protecting entities or individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.75
     guiActiveUnfocused
    -0.73
    SPONSORED
    -0.70
    Mode
    -0.69
     NEWS
    -0.66
     describes
    -0.65
    cart
    -0.65
    Mass
    -0.64
    OUT
    -0.63
     describing
    -0.62
    POSITIVE LOGITS
     integrity
    1.14
     dignity
    1.11
     confidentiality
    0.99
     secrets
    0.97
    yrights
    0.92
     indef
    0.89
     interests
    0.89
    egu
    0.88
     freedoms
    0.88
     privacy
    0.88
    Act Density 0.353%

    No Known Activations