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

    Neuronpedia

    INDEX
    Explanations

    references to comparison with a specific entity in a positive context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    isters
    -0.84
    onics
    -0.76
    acles
    -0.72
    ensibly
    -0.70
    staking
    -0.69
    ernels
    -0.68
    ethe
    -0.67
    igers
    -0.65
    undreds
    -0.64
    riages
    -0.63
    POSITIVE LOGITS
    worldly
    1.45
     aspect
    0.97
     circumstance
    0.96
     conceivable
    0.95
     outlet
    0.87
     entity
    0.86
     imaginable
    0.85
     mammal
    0.85
    where
    0.84
    iator
    0.84
    Act Density 0.036%

    No Known Activations