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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks, particularly slashes and slashes followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     costas
    -0.48
    almaz
    -0.47
     hvil
    -0.46
     tölt
    -0.44
    ppure
    -0.43
     azonban
    -0.43
     on
    -0.42
     alis
    -0.42
    움
    -0.41
     waves
    -0.41
    POSITIVE LOGITS
     GenerationType
    1.03
    %/
    0.98
    bootstrapcdn
    0.85
     للمعارف
    0.85
     ostavi
    0.85
     Orrell
    0.83
    ----</
    0.82
    NamedQueries
    0.82
     ModelRenderer
    0.82
    FieldBuilder
    0.82
    Act Density 0.231%

    No Known Activations