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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions indicating quantity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as many as" indicating quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nap
    -0.66
    ocy
    -0.65
    MD
    -0.64
    onomy
    -0.64
    HOME
    -0.63
    IGHT
    -0.61
    GAME
    -0.60
    SQL
    -0.60
    eu
    -0.60
    nce
    -0.59
    POSITIVE LOGITS
     Sabha
    0.64
    ceed
    0.62
    vernment
    0.61
    ggles
    0.61
     facult
    0.60
    cffff
    0.57
    respect
    0.57
     Fiji
    0.57
    pent
    0.56
    pell
    0.56
    Act Density 0.099%

    No Known Activations