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

    Neuronpedia

    INDEX
    Explanations

    fractions or proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportional relationships or fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¡
    -0.93
    Marginal
    -0.78
    Ù
    -0.74
    raltar
    -0.72
    æ³
    -0.72
    ALLY
    -0.70
    sym
    -0.68
    é¾
    -0.67
    ãĤŃ
    -0.67
    atu
    -0.65
    POSITIVE LOGITS
    avin
    0.69
     latitude
    0.68
     Clover
    0.65
     GDP
    0.64
     Sutherland
    0.64
    icial
    0.63
    ffic
    0.61
    ordinary
    0.61
    iler
    0.60
    angler
    0.60
    Act Density 0.051%

    No Known Activations