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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases indicating the beginning of a new topic or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.89
    rawDesc
    -0.88
    sizeCache
    -0.84
    awtextra
    -0.84
    antMatchers
    -0.83
     Савезне
    -0.83
     doInBackground
    -0.81
    SharedCtor
    -0.80
     CreateTagHelper
    -0.79
     oprot
    -0.79
    POSITIVE LOGITS
    ↵↵
    0.65
    <eos>
    0.58
    sätzlich
    0.51
    </table>
    0.46
    xae
    0.46
    .(*
    0.45
     cata
    0.44
     can
    0.43
     Pas
    0.42
     doute
    0.41
    Act Density 0.063%

    No Known Activations