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

    Neuronpedia

    INDEX
    Explanations

    differences or gaps between various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    key distinctions and differences between various groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SpaceEngineers
    -0.80
    outine
    -0.72
     standby
    -0.70
     Lent
    -0.69
    ributes
    -0.69
    raid
    -0.67
    dule
    -0.67
     instructions
    -0.66
    mission
    -0.65
     preparations
    -0.64
    POSITIVE LOGITS
     blurred
    1.19
     widening
    1.14
    between
    1.08
     blurry
    1.06
     widened
    1.05
     narrowing
    1.01
     widen
    1.01
     stark
    1.01
     gaping
    0.99
     between
    0.99
    Act Density 0.243%

    No Known Activations