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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating fear or concern

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fear and concerns about safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĵĺ
    -0.70
     Vikings
    -0.70
    started
    -0.65
    nova
    -0.65
     ATL
    -0.65
    elta
    -0.65
    xit
    -0.64
    Registered
    -0.64
    enum
    -0.62
     mound
    -0.62
    POSITIVE LOGITS
     confidentiality
    0.85
     risking
    0.83
     prud
    0.81
     necessity
    0.81
     safety
    0.81
     jeopard
    0.80
     retribution
    0.79
     deterrence
    0.79
     threats
    0.78
     reasons
    0.78
    Act Density 0.824%

    No Known Activations