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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protection and security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to protection and safeguarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.77
    HC
    -0.69
    asking
    -0.68
     describes
    -0.68
    Mass
    -0.66
     explains
    -0.65
    gomery
    -0.65
    storms
    -0.64
     resembled
    -0.63
     msec
    -0.63
    POSITIVE LOGITS
     integrity
    1.23
     dignity
    1.09
     confidentiality
    1.07
     indef
    1.04
     secrets
    1.04
     rights
    1.02
     anonymity
    1.02
     purity
    0.99
     privacy
    0.98
     interests
    0.97
    Act Density 0.181%

    No Known Activations