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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "excess" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of excess or surplus in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achi
    -0.68
     Scan
    -0.67
    circle
    -0.64
    tl
    -0.64
    tle
    -0.64
    Story
    -0.63
    team
    -0.63
    Rod
    -0.63
    SEE
    -0.63
    leon
    -0.63
    POSITIVE LOGITS
     excess
    4.09
     excessive
    1.61
     surplus
    1.47
     undue
    1.18
     exceed
    1.17
     deficiency
    1.15
     accumulated
    1.14
    cess
    1.13
     shortfall
    1.12
     extravag
    1.11
    Act Density 0.012%

    No Known Activations