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

    Neuronpedia

    INDEX
    Explanations

    terms related to vocabulary and language structure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    uras
    -0.60
    +#+#
    -0.58
     BSD
    -0.57
     विश्वसनीयता
    -0.53
    TypeDef
    -0.52
    post
    -0.51
    BSD
    -0.50
     Post
    -0.50
     post
    -0.50
     nisi
    -0.50
    POSITIVE LOGITS
     vocabulary
    1.23
     vocab
    1.21
    vocabulary
    1.21
     Vocabulary
    1.16
    Vocab
    1.02
    Vocabulary
    0.96
    cabulary
    0.94
    vocab
    0.93
    ABULARY
    0.88
    TagHelper
    0.79
    Act Density 0.006%

    No Known Activations