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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating social awareness and communal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TableAdapter
    -0.46
     initWith
    -0.45
    bibitem
    -0.44
    expandindo
    -0.44
    BufferException
    -0.43
     lenker
    -0.42
     endian
    -0.40
    WriteTagHelper
    -0.40
     getSelected
    -0.40
     theorems
    -0.38
    POSITIVE LOGITS
     simplemente
    0.45
    
    0.43
     verkligen
    0.43
     simplesmente
    0.43
     paš
    0.42
     lisäksi
    0.42
    ícil
    0.42
     autorización
    0.41
     quelquefois
    0.41
    basically
    0.40
    Act Density 0.095%

    No Known Activations