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

    Neuronpedia

    INDEX
    Explanations

    percentage changes or fluctuations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant decreases or increases, particularly with numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.71
    finished
    -0.70
    Finish
    -0.68
    itialized
    -0.66
    jad
    -0.65
    hid
    -0.64
    psc
    -0.62
    rar
    -0.62
    aine
    -0.61
    ollo
    -0.61
    POSITIVE LOGITS
     leaps
    1.25
     fractions
    0.98
     approximately
    0.96
     20
    0.94
     25
    0.93
     50
    0.92
     roughly
    0.91
     trillions
    0.90
     nearly
    0.90
     15
    0.89
    Act Density 0.063%

    No Known Activations