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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating returning to a previous state or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.52
    styleable
    -0.51
     expan
    -0.51
    expandindo
    -0.47
    oneofs
    -0.47
    ьаж
    -0.47
     بيها
    -0.44
    Билгалдахарш
    -0.43
     delegation
    -0.43
    /**
    -0.42
    POSITIVE LOGITS
     wró
    0.63
     tilbake
    0.60
     FetchType
    0.59
     tilbage
    0.59
     revisit
    0.57
     reverting
    0.57
     revert
    0.56
     tillbaka
    0.54
     tornare
    0.53
     Rückkehr
    0.52
    Act Density 0.220%

    No Known Activations