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

    Neuronpedia

    INDEX
    Explanations

    words related to authority figures or institutions

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "by" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atem
    -0.65
    idate
    -0.63
    itto
    -0.63
    allo
    -0.60
    asy
    -0.58
    ettes
    -0.56
    Saharan
    -0.56
    abul
    -0.55
    ati
    -0.54
    chuk
    -0.54
    POSITIVE LOGITS
     virtue
    1.02
    laws
    0.83
    products
    0.83
     fiat
    0.67
    akuya
    0.66
    product
    0.66
    catch
    0.65
    gone
    0.64
     multiplying
    0.63
     STATS
    0.60
    Act Density 0.127%

    No Known Activations