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

    references to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itcher
    -0.69
     Alone
    -0.67
     Conver
    -0.66
     Trees
    -0.64
    arre
    -0.64
     Beet
    -0.64
     Craw
    -0.64
    rots
    -0.63
     Characters
    -0.63
     Saw
    -0.63
    POSITIVE LOGITS
     wellbeing
    1.13
     efficacy
    1.04
     hygiene
    0.99
     confidentiality
    0.98
     prosperity
    0.93
     sanitation
    0.93
     wellness
    0.89
     dignity
    0.89
     privacy
    0.88
     security
    0.88
    Act Density 0.088%

    No Known Activations