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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a wide variety of ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.17
    mong
    -0.17
    why
    -0.17
     why
    -0.16
    l
    -0.16
    aries
    -0.15
    321
    -0.15
    essen
    -0.15
    anto
    -0.15
    nt
    -0.15
    POSITIVE LOGITS
    :NSMakeRange
    0.29
     Rover
    0.19
    OfString
    0.18
    ependency
    0.17
    lider
    0.16
    erset
    0.16
    åĽ²
    0.16
    alen
    0.16
    led
    0.16
    yro
    0.16
    Act Density 0.032%

    No Known Activations