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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons such as "much higher" or "weaker plan."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "much" indicating a significant degree of change or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tags
    -0.80
    ysc
    -0.73
     Releases
    -0.70
     Walls
    -0.65
    querade
    -0.65
    mson
    -0.65
    imester
    -0.64
    anamo
    -0.64
    ensing
    -0.63
    psons
    -0.63
    POSITIVE LOGITS
     simpler
    1.19
     larger
    1.19
     nicer
    1.19
     bigger
    1.15
     smaller
    1.15
     clearer
    1.14
     wider
    1.12
     stronger
    1.12
     narrower
    1.12
     stricter
    1.11
    Act Density 0.041%

    No Known Activations