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

    Neuronpedia

    INDEX
    Explanations

    numbers associated with years

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations, especially regarding ages or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.69
    ãĤ¯
    -0.67
    LAN
    -0.67
    aucus
    -0.66
    isSpecialOrderable
    -0.64
    ivities
    -0.62
    HER
    -0.62
     CM
    -0.60
    MAC
    -0.59
     multiplier
    -0.57
    POSITIVE LOGITS
     thousand
    0.99
    yo
    0.89
     percent
    0.86
     hundred
    0.85
     pounds
    0.83
    ths
    0.81
    een
    0.81
    ish
    0.81
     cents
    0.80
    ishly
    0.76
    Act Density 0.042%

    No Known Activations