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

    Neuronpedia

    INDEX
    Explanations

    the word "latter" in a comparison

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "latter" in comparative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bows
    -0.76
    Cola
    -0.70
    ashes
    -0.68
    opian
    -0.67
    aukee
    -0.66
    arij
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    Maps
    -0.65
     Clover
    -0.64
    Magn
    -0.64
    POSITIVE LOGITS
    mentioned
    1.00
     stages
    0.77
    nder
    0.76
     half
    0.74
    worldly
    0.74
    most
    0.73
     part
    0.72
     halves
    0.70
    liest
    0.68
     category
    0.68
    Act Density 0.038%

    No Known Activations