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

    Neuronpedia

    INDEX
    Explanations

    terms related to small size or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "small" or phrases indicating smallness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rencies
    -0.91
    gans
    -0.90
    events
    -0.83
     Attacks
    -0.82
    laws
    -0.80
     Votes
    -0.77
    agles
    -0.77
    çļ
    -0.76
    rollers
    -0.75
    osponsors
    -0.75
    POSITIVE LOGITS
     handful
    1.04
     glimpse
    0.95
     snippet
    0.92
     portion
    0.90
     exception
    0.90
     fraction
    0.89
     amount
    0.89
     glance
    0.88
     subset
    0.88
     chunk
    0.84
    Act Density 0.091%

    No Known Activations