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

    Neuronpedia

    INDEX
    Explanations

    locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.81
    LOG
    -0.69
    uria
    -0.69
    scape
    -0.69
    loads
    -0.68
    arians
    -0.64
    Measure
    -0.63
    ata
    -0.63
    notation
    -0.63
    adding
    -0.62
    POSITIVE LOGITS
     behest
    1.38
     helm
    1.16
     outset
    1.06
     expense
    1.03
     forefront
    1.02
     intersection
    0.97
     airport
    0.89
     end
    0.89
     doorstep
    0.88
     docks
    0.85
    Act Density 0.146%

    No Known Activations