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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions with the verb "have" followed by a past participle

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.78
    Winged
    -0.67
     srfAttach
    -0.66
     SetTextColor
    -0.65
     Enhancement
    -0.64
    çĶ°
    -0.64
     sqor
    -0.64
    isin
    -0.64
     Dise
    -0.63
    Kings
    -0.63
    POSITIVE LOGITS
     anymore
    1.50
     bothered
    1.14
     necessarily
    1.13
     bother
    1.04
     nor
    1.02
     anywhere
    1.01
    yet
    0.97
     anything
    0.94
     slightest
    0.92
     any
    0.92
    Act Density 0.252%

    No Known Activations