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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or clauses indicating uncertainty or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.52
    [,]
    -0.46
    ponses
    -0.46
     GLE
    -0.45
     tert
    -0.44
     فريبيس
    -0.43
    PointerException
    -0.41
    WriteBarrier
    -0.41
    Lange
    -0.41
     spect
    -0.41
    POSITIVE LOGITS
     nanti
    0.80
     someday
    0.77
     tomorrow
    0.74
    IVEREF
    0.70
     nantinya
    0.70
     gelingt
    0.68
     demain
    0.68
    featureID
    0.67
     inderdaad
    0.67
    كويكب
    0.67
    Act Density 0.260%

    No Known Activations