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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to quantities or measurements, possibly in the context of technology or statistics

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers, particularly in a formatted or structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krit
    -0.79
    warts
    -0.79
    icka
    -0.73
    wald
    -0.72
    swick
    -0.69
    fruit
    -0.68
    igmat
    -0.66
    agan
    -0.66
    ifice
    -0.65
    heit
    -0.64
    POSITIVE LOGITS
    +
    0.96
     crore
    0.89
    Hz
    0.89
    +)
    0.86
    gp
    0.85
     Hz
    0.82
     000
    0.82
    mAh
    0.81
    000
    0.81
     gp
    0.79
    Act Density 0.064%

    No Known Activations