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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is intended or appropriate for a specific group or purpose

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "for" and its context in relation to inclusivity and purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.65
    soever
    -0.65
     vom
    -0.64
    ÃŁ
    -0.63
    Witness
    -0.62
    Sus
    -0.61
    Russ
    -0.60
     Ples
    -0.59
     thereafter
    -0.59
    urus
    -0.58
    POSITIVE LOGITS
    bidden
    1.48
    ked
    1.19
    geries
    1.09
     sale
    1.08
    gotten
    1.07
    gettable
    1.02
    giving
    0.95
    bid
    0.94
    going
    0.93
    aging
    0.93
    Act Density 0.104%

    No Known Activations