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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a repetitive or recurring action or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etics
    -0.77
    then
    -0.76
    ees
    -0.75
    forts
    -0.75
    abouts
    -0.75
    conom
    -0.74
    utics
    -0.74
    rers
    -0.74
    alties
    -0.74
    =-=-=-=-
    -0.72
    POSITIVE LOGITS
     reminder
    1.06
     installment
    1.03
     disappointing
    0.92
     example
    0.89
     disappointment
    0.89
     notch
    0.89
     confirmation
    0.88
     batch
    0.85
     setback
    0.84
     glimpse
    0.84
    Act Density 0.166%

    No Known Activations