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

    Neuronpedia

    INDEX
    Explanations

    phrases related to doubling or growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terminology related to increases or changes in quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĬ
    -0.73
    hra
    -0.66
    ouri
    -0.66
    arted
    -0.66
    ãĤĮ
    -0.66
    utic
    -0.66
    çĦ
    -0.65
    lan
    -0.65
     sar
    -0.65
    league
    -0.64
    POSITIVE LOGITS
    xual
    0.77
     digit
    0.73
     digits
    0.72
    elsius
    0.69
    cedes
    0.69
     exponentially
    0.68
    peak
    0.68
     submer
    0.67
     immersion
    0.66
     tripled
    0.66
    Act Density 0.019%

    No Known Activations