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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    θεν
    -0.15
    AGMA
    -0.15
     มห
    -0.14
    ÄĽÅ¾
    -0.14
    ndern
    -0.14
    ague
    -0.14
    abcdefghijkl
    -0.14
    Äł
    -0.14
    CSI
    -0.14
    IFn
    -0.14
    POSITIVE LOGITS
    enas
    0.17
    amel
    0.15
    ryn
    0.15
    nem
    0.14
     Rank
    0.13
    cxx
    0.13
    eya
    0.13
    yll
    0.13
    gt
    0.13
    .doc
    0.13
    Act Density 0.194%

    No Known Activations