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

    Neuronpedia

    INDEX
    Explanations

    The neuron primarily looks for phrases mentioning comparisons using the phrase "at least."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a minimum or a comparative sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bj
    -0.68
    rend
    -0.66
    rence
    -0.63
    hr
    -0.63
    taboola
    -0.62
    kefeller
    -0.62
    dal
    -0.61
    ses
    -0.60
    shr
    -0.59
    iph
    -0.59
    POSITIVE LOGITS
    uner
    0.75
     partly
    0.73
     toler
    0.72
    fair
    0.68
     squares
    0.67
     partially
    0.65
    een
    0.65
     judging
    0.64
     theoretically
    0.62
    Station
    0.61
    Act Density 0.021%

    No Known Activations