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

    Neuronpedia

    INDEX
    Explanations

    keywords related to respect and dignity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dignity and respect for individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concoct
    -0.80
     Lans
    -0.72
    otine
    -0.72
    uggest
    -0.70
     torpedo
    -0.68
     ferry
    -0.67
     cram
    -0.67
     Nether
    -0.67
    NetMessage
    -0.65
     Summoner
    -0.65
    POSITIVE LOGITS
    ably
    1.21
    ability
    1.14
    fully
    1.00
    ibly
    0.94
    rity
    0.90
    able
    0.90
    FUL
    0.89
    ful
    0.87
    ility
    0.85
    amental
    0.84
    Act Density 0.017%

    No Known Activations