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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "traditional"

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional methods or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wanted
    -0.74
    upon
    -0.69
    anders
    -0.64
    hung
    -0.63
     Seat
    -0.63
    ————————————————
    -0.62
     hereafter
    -0.62
     Aware
    -0.62
    mentation
    -0.61
    Phones
    -0.60
    POSITIVE LOGITS
    arily
    0.94
    ties
    0.86
    ised
    0.82
    izations
    0.79
    ists
    0.74
     wisdom
    0.73
    ized
    0.72
    IZ
    0.72
    urally
    0.72
    ization
    0.71
    Act Density 0.020%

    No Known Activations