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

    Neuronpedia

    INDEX
    Explanations

    instances where there is a small or insignificant amount of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating scarcity or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ules
    -0.83
    olds
    -0.78
    agents
    -0.78
    adows
    -0.76
    asions
    -0.76
    mates
    -0.76
    hov
    -0.75
    ategories
    -0.74
    roo
    -0.73
    ħĭ
    -0.72
    POSITIVE LOGITS
     incentive
    1.15
     indication
    1.10
     recourse
    1.04
     opportunity
    1.03
     overlap
    1.01
     evidence
    1.00
     chance
    1.00
     appetite
    0.97
     clarity
    0.97
     oversight
    0.95
    Act Density 0.123%

    No Known Activations