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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of uncertainty and speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.24
    7:0.05
    8:0.07
    9:0.23
    10:0.03
    11:0.04
    Negative Logits
    akura
    -4.50
    Raven
    -4.03
    Ky
    -3.86
    roman
    -3.74
     Ky
    -3.70
     Ku
    -3.62
     boxed
    -3.61
    displayText
    -3.55
     Cardinals
    -3.47
    amsung
    -3.43
    POSITIVE LOGITS
     Ethan
    8.64
     Eth
    7.10
     Meth
    6.83
     Seth
    6.12
     Beth
    5.94
    Eth
    5.82
    eth
    5.69
     ETH
    5.57
     Ether
    5.38
    ETH
    5.32
    Act Density 0.003%

    No Known Activations