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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and security

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quit
    -0.85
     Flames
    -0.78
    arro
    -0.74
    twitch
    -0.74
    qt
    -0.72
    addon
    -0.71
    quet
    -0.70
     Craw
    -0.70
    ombies
    -0.68
    wic
    -0.66
    POSITIVE LOGITS
     dignity
    1.24
     freedoms
    1.22
     decency
    1.20
     integrity
    1.15
     morals
    1.13
     equality
    1.12
     liberties
    1.10
     fairness
    1.09
     wellbeing
    1.07
    Privacy
    1.06
    Act Density 0.239%

    No Known Activations