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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "excess"

    oai_token-act-pair · gpt-3.5-turbo

    references to an abundance or surplus of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.76
    hran
    -0.76
    andum
    -0.72
    herer
    -0.71
    chens
    -0.71
    glas
    -0.70
    ramid
    -0.70
    uzzle
    -0.69
    HCR
    -0.69
    ching
    -0.68
    POSITIVE LOGITS
     excess
    0.92
     baggage
    0.87
     overfl
    0.83
    atile
    0.76
     accumulation
    0.75
    es
    0.75
     capacity
    0.74
    ceed
    0.71
     leakage
    0.71
     workload
    0.69
    Act Density 0.007%

    No Known Activations