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

    Neuronpedia

    INDEX
    Explanations

    instances where something is singled out or specified

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of a minimum quantity or requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bryce
    -0.71
    ãĤ¬
    -0.69
    stocks
    -0.66
     Launch
    -0.65
     Markets
    -0.63
     Bacon
    -0.62
    uay
    -0.62
    Launch
    -0.62
    MSN
    -0.62
    Cash
    -0.60
    POSITIVE LOGITS
    dozen
    0.89
     dozen
    0.87
     sidx
    0.73
    ipop
    0.70
    temp
    0.67
    è¦ļéĨĴ
    0.66
    eger
    0.66
    hetti
    0.66
     externalToEVAOnly
    0.66
    ukemia
    0.65
    Act Density 0.073%

    No Known Activations