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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "numbers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.84
    Interstitial
    -0.79
    OPLE
    -0.76
    INTON
    -0.73
     Conditions
    -0.71
    POSE
    -0.68
    Accessory
    -0.67
    ovie
    -0.64
    aples
    -0.64
    agall
    -0.63
    POSITIVE LOGITS
    metry
    0.92
    paces
    0.81
    pace
    0.81
    matic
    0.80
    ynthesis
    0.79
    ynt
    0.77
     regress
    0.74
    hare
    0.73
     Numbers
    0.71
     crunch
    0.71
    Act Density 0.024%

    No Known Activations