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

    Neuronpedia

    INDEX
    Explanations

    words related to potential future events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contingency planning and unexpected situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orters
    -0.88
    Ģ
    -0.85
    eh
    -0.80
    Ĺ
    -0.79
    ķ
    -0.79
    Ķ
    -0.76
    ¶æ
    -0.74
    arb
    -0.74
    ulton
    -0.73
    ĵ
    -0.73
    POSITIVE LOGITS
     contingency
    1.35
     conting
    1.20
    plan
    0.89
     emergencies
    0.88
    ptoms
    0.83
     scenarios
    0.78
     planning
    0.77
     planners
    0.77
     wills
    0.77
     redundancy
    0.76
    Act Density 0.012%

    No Known Activations