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

    Neuronpedia

    INDEX
    Explanations

    numbers with decimals

    oai_token-act-pair · gpt-3.5-turbo

    rarity or uniqueness in context, particularly in regards to percentages and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shrinking
    -0.71
    ĺħ
    -0.68
     Kard
    -0.68
     dotted
    -0.66
     truck
    -0.66
     centrif
    -0.63
     Ford
    -0.62
     Journal
    -0.62
     succeeding
    -0.61
     later
    -0.61
    POSITIVE LOGITS
    perty
    0.89
    aroo
    0.86
    thia
    0.83
    brate
    0.79
    asper
    0.78
    chieve
    0.78
    istration
    0.77
    rama
    0.76
    brates
    0.76
    pex
    0.74
    Act Density 0.075%

    No Known Activations